ALBERT

All Library Books, journals and Electronic Records Telegrafenberg

Ihre E-Mail wurde erfolgreich gesendet. Bitte prüfen Sie Ihren Maileingang.

Leider ist ein Fehler beim E-Mail-Versand aufgetreten. Bitte versuchen Sie es erneut.

Vorgang fortführen?

Exportieren
Filter
  • Artikel  (154)
  • Weitere Quellen
  • neural networks
  • Springer  (154)
  • 2005-2009
  • 1995-1999  (154)
  • 1
    Digitale Medien
    Digitale Medien
    Springer
    Journal of geographical systems 1 (1999), S. 3-22 
    ISSN: 1435-5949
    Schlagwort(e): Key words: Classification ; neural networks ; G15 ; JEL classification: C88 ; C63 ; C45 ; C44
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Geographie
    Notizen: Abstract. Neural Networks are now established computational tools used for search minimisation and data classification. They offer some highly desirable features for landuse classification problems since they are able to take in a variety of data types, recorded on different statistical scales, and combine them. As such, neural networks should offer advantages of increased accuracy. However, a barrier to their general acceptance and use by all but `experts' is the difficulty of configuring the network initially.  This paper describes the architectural problems of applying neural networks to landcover classification exercises in geography and details some of the latest developments from an ongoing research project aimed at overcoming these problems. A comprehensive strategy for the configuration of neural networks is presented, whereby the network is automatically constructed by a process involving initial analysis of the training data. By careful study of the functioning of each part of the network it is possible to select the architecture and initial weights on the node connections so the constructed network is `right first time'. Further adaptations are described to control network behaviour, to optimise functioning from the perspective of landcover classification. The entire configuration process is encapsulated by a single application which may be treated by the user as a `black box', allowing the network to the applied in much the same way as a maximum likelihood classifier, with no further effort being required of the user.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 2
    Digitale Medien
    Digitale Medien
    Springer
    Journal of geographical systems 1 (1999), S. 37-60 
    ISSN: 1435-5949
    Schlagwort(e): Key words: Computational intelligence ; glacier hydrology ; genetic programming ; neural networks ; fuzzy logic ; self-organizing map ; JEL classification: C61 ; C63 ; C80
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Geographie
    Notizen: Abstract. Measurements of water pressure beneath Trapridge Glacier, Yukon Territory, Canada show that the basal water system is highly heterogeneous. Three types of behaviour were recorded: pressure records which are strongly correlated, records which are strongly anticorrelated, and records which alternate between strong correlation and strong anticorrelation. We take the pressure in bore-holes that are connected to the evacuation route for basal water as the forcing, and the other pressures as the response to this forcing. Previous work (Murray and Clarke 1995) has shown that these relationships can be modelled using low-order nonlinear differential equations optimized by inversion. However, despite optimizing the model parameters we cannot be sure that the final model forms are themselves optimal. Computational intelligence techniques provide alternative methods for fitting models and are robust to missing or noisy data, applicable to non-smooth models, and attempt to derive optimal model forms as well as optimal model parameters. Four computational intelligence techniques have been used and the results compared with the more conventional mathematical model. These methods were genetic programming, artificial neural networks, fuzzy logic and self-organizing maps. We compare each technique and offer an evaluation of their suitability for modelling the pressure data. The evaluation criteria are threefold: (1) goodness of fit and an ability to predict subsequent data under different surface weather conditions; (2) interpretability, and the extent and significance of any new insights offered into the physics of the glacier; (3) computation time. The results suggest that the suitability of the computational intelligence techniques to model these data increases with the complexity of the system to be modelled.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 3
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 8 (1997), S. 227-234 
    ISSN: 1572-8145
    Schlagwort(e): Proportional hazards models ; neural networks ; accelerated life testing
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract Because of increased manufacturing competitiveness, new methods for reliability estimation are being developed. Intelligent manufacturing relies upon accurate component and product reliability estimates for determining warranty costs, as well as optimal maintenance, inspection, and replacement schedules. Accelerated life testing is one approach that is used for shortening the life of products or components or hastening their performance degradation with the purpose of obtaining data that may be used to predict device life or performance under normal operating conditions. The proportional hazards (PH) model is a non-parametric multiple regression approach for reliability estimation, in which a baseline hazard function is modified multiplicatively by covariates (i.e. applied stresses). While the PH model is a distribution-free approach, specific assumptions need to be made about the time behavior of the hazard rates. A neural network (NN) is particularly useful in pattern recognition problems that involve capturing and learning complex underlying (but consistent) trends in the data. Neural networks are highly non-linear, and in some cases are capable of producing better approximations than multiple regression. This paper reports on the comparison of PH and NN models for the analysis of time-dependent dielectric breakdown data for a metal-oxide-semiconductor integrated circuit. In this case, the NN model results in a better fit to the data based upon minimizing the mean square error of the predictions when using failure data from an elevated temperature and voltage to predict reliability at a lower temperature and voltage.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 4
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 7 (1996), S. 1-11 
    ISSN: 1572-8145
    Schlagwort(e): Artificial intelligence ; computer vision ; neural networks ; shape recognition ; structural model
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Shape representation and recognition is an important topic in many applications of computer vision and artificial intelligence, including character recognition, pattern recognition, machine monitoring, robot manipulation and production part recognition. In this paper, a structural model based on boundary information is proposed to describe the silhouette of planar objects (especially machined parts). The structural model describes objects by a set of primitives, each of which is represented by three geometric features: its length, curvature, and relative orientation. This representation scheme not only compresses the data, but also provides a compact and meaningful form to facilitate further recognition operations. Based on this model, the object recognition is accomplished by using a multilayered feedforward neural network. The proposed model is transformation invariant, which offers the necessary flexibility for real-time implementation in automated manufacturing systems. In addition, the numerical results for a set of ten reference shapes indicate that the matching engine can achieve very high success rates using short recognition times.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 5
    Digitale Medien
    Digitale Medien
    Springer
    Wireless personal communications 3 (1996), S. 199-214 
    ISSN: 1572-834X
    Schlagwort(e): Image compression ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Elektrotechnik, Elektronik, Nachrichtentechnik
    Notizen: Abstract For efficient cellular communication channel usage, we propose a neural computation model for image coding. In a constant-time unsupervised learning, our neural model approximates optimal pattern clustering from training example images through a memory adaptation process, and builds a compression codebook in its synaptic weight matrix. This neural codebook can be distributed to both ends of a transmission channel for fast codec operations on general images. The transmission is merely the indices of the codebook entries best matching the patterns in the image to be transmitted. These indices can further be compressed through a classical entropy coding method to yield even more transmission reduction. Other advantages of our model are the low training time complexity, high utilization of neurons, robust pattern clustering capability, and simple computation. A VLSI implementation is also highly suitable for the intrinsic parallel nature of neural networks. Our compression results are competitive compared to JPEG and wavelet methods. We also reveal the general codebook's cross-compression results, filtering effects by special training methods, and learning enhancement techniques for obtaining a compact codebook to yield both high compression and picture quality.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 6
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 9 (1998), S. 347-352 
    ISSN: 1572-8145
    Schlagwort(e): Sheet metal parts ; computer-aided process planning ; bending tools ; laminated object modelling ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract The manufacturing of complex bent parts can be supported effectively by computer-aided planning methods. Software systems are already available for unfolding, laser cutting and bending sequence determination. The paper focuses on methods that support the design of non-standard bending tools and the flexible manufacturing of such tools using laminated object modelling (LOM) technology. The developed system allows for concurrent planning and manufacturing of bending parts and tools. Within the framework of this system, neural networks are applied for automated tool design.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 7
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 9 (1998), S. 281-287 
    ISSN: 1572-8145
    Schlagwort(e): Turning ; accuracy ; process control ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract Stochastic and non-deterministic influences have an effect on cutting processes and lead to an unsteady and dynamic process behaviour. Concepts for the improvement of process reliability and for the control of tolerances have to be developed in order to fulfil the increasing requirements on product quality. A concept for the improvement of manufacturing accuracy through artificial neural networks (ANN) will be presented as an example for the turning process. This ANN model makes it possible to predict the dimensional deviation caused by tool wear. Feeding this back in an open loop within the machine controller the deviation can be compensated by using an adaptive control of the depth of cut.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 8
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 8 (1997), S. 203-214 
    ISSN: 1572-8145
    Schlagwort(e): Feature recognition ; feature representation ; neural networks ; ART
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract A self-organizing neural network, ART2, based on adaptive resonance theory (ART), is applied to the problem of feature recognition from a boundary representation (B-rep) solid model. A modified face score vector calculation scheme is adopted to represent the features by continuous-valued vectors, suitable to be input to the network. The face score is a measure of the face complexity based upon the convexity or concavity of the surrounding region. The face score vector depicts the topological relations between a face and its neighbouring faces. The ART2 network clusters similar features together. The similarity of the features within a cluster is controlled by a vigilance parameter. A new feature presented to the net is associated with one of the existing clusters, if the feature is similar to the members of the cluster. Otherwise, the net creates a new cluster. An algorithm of the ART2 network is implemented and tested with nine different features. The results obtained indicate that the network has significant potential for application to the problem of feature recognition.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 9
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 10 (1999), S. 251-265 
    ISSN: 1572-8145
    Schlagwort(e): Feature-based design for manufacture ; feature recognition ; feature families formation ; cell grouping ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract A neural network approach is applied to the problem of integrating design and manufacturing engineering. The self organising map (SOM) neural network recognizes products and parts which are modeled as boundary representation (B-rep) solids using a modified face complexity code scheme adopted, and forms the necessary feature families. Based on the part features, machines, tools and fixtures are selected. These information are then fed into a four layer feed-forward neural network that provides a designer with the desired features that meet the current manufacturing constraints for design of a new product or part. The proposed methodology does not involve training of the neural networks used and is seen to be a significant potential for application in concurrent engineering where design and manufacturing are integrated.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 10
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 10 (1999), S. 289-299 
    ISSN: 1572-8145
    Schlagwort(e): Feature recognition ; feature representation ; neural networks ; BPN
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract A backpropagation neural network (BPN) is applied to the problem of feature recognition from a boundary representation (B-rep) solid model to facilitate process planning of manufactured products. It is based on the use of the face complexity code to represent the features and a neural network for the analysis of the recognition. The face complexity code is a measure of the face complexity of a feature based on the convexity or concavity of the surrounding geometry. The codes for various features are fed to the network for analysis. A backpropagation network is implemented for recognition of features and tested on published results to measure its performance. Any two or more features having significant differences in face complexity codes were used as exemplars for training the network. A new feature presented to the network is associated with one of the existing clusters, if they are similar, or the network creates a new cluster, if otherwise. Experimental results show that the network was consistent in recognizing features, hence is appropriate for application to the problem of feature recognition in automated manufacturing environment.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 11
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 10 (1999), S. 405-421 
    ISSN: 1572-8145
    Schlagwort(e): Flexible manufacturing systems control ; intelligent manufacturing ; neural networks ; simulation ; material handling systems ; automated guided vehicles
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract This paper presents a framework of intelligent manufacturing scheduling and control with specific applications to operations of rail-guided vehicle systems (RGVS). A RGVS control architecture is discussed with a focus on a simulated experiment in operations of the load/unload area of a real industrial flexible manufacturing system (FMS). In the operation stage of a material handling system (MHS), all shop floor data are subject to change as time goes. These data can be collected using a data acquisition device and stored in a dynamic database. The RGVS simulator used in this experimental study is designed to incorporate some possible situations representing existing material handling scenarios in order to evaluate alternative control policies. At the development stage of the controller, all possible combinations of most commonly encountered scenarios such as RGV failures, production schedule changes, machine breakdowns, and rush orders are to be simulated and corresponding results collected. The data are then structured into training data pairs to properly train an artificial neural network. The neural network, trained by using input/output data sets obtained from a number of simulation runs, will then provide control strategy recommendations. At the application stage, whenever an abnormal scenario occurs, a pre-processor will be activated to pre-screen and prepare an input vector for the trained neural network. If such an abnormal scenario falls outside the existing domain of data sets employed to train the neural network, as judged by the MHS supervisory controller, an off-line training module will be activated to eventually update the neural network. The recommended control strategies will be transmitted to the MHS control for real-time execution. If there is no further abnormal event detected, the dynamic data base (DDB) module simply continues to monitor the MHS activities. The proposed MHS control system combines the features of example based neural network technology and simulation modeling for true intelligent, on-line, pseudo real-time control. Not only will the system assure that feasible material handling control actions be taken, but also it will implement better control decisions through continuous learning from experiences captured as the operation time of the MHS accumulates.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 12
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 9 (1998), S. 289-294 
    ISSN: 1572-8145
    Schlagwort(e): Manufacturing process chain ; modelling ; optimization ; neural networks ; evolutionary algorithms
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract Today's manufacturing methods are caught between the growing need for quality, high process safety, minimal manufacturing costs, and short manufacturing times. In order to meet these demands, process setting parameters have to be chosen in the best possible way, according to demand on quality. For such optimization it is necessary to represent the processes in a model. Due to the enormous complexity of many processes and the high number of influencing parameters, however, conventional approaches to modelling and optimization are no longer sufficient. In this article it is shown how, by means of applying neural networks for process modelling, even these highly complex interdependencies can be learned. That way both process and quality parameters can be assessed before or during processing. By connecting them with corresponding cost models, it is possible to optimize processes with the help of evolutionary algorithms. Using examples of different manufacturing processes, the possi bilities for process modelling and optimization with neural networks and evolutionary algorithms are demonstrated.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 13
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 8 (1997), S. 177-190 
    ISSN: 1572-8145
    Schlagwort(e): Nesting ; stock cutting ; neural networks ; optimization ; genetic algorithms
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract In this study, two approaches are explored for the solution of the rectangular stock cutting problem: neuro-optimization, which integrates artificial neural networks and optimization methods; and genetic neuro-nesting, which combines artificial neural networks and genetic algorithms. In the first approach, an artificial neural network architecture is used to generate rectangular pattern configurations, to be used by the optimization model, with an acceptable scrap. Rectangular patterns of different sizes are selected as input to the network to generate the location and rotation of each pattern after they are combined. A mathematical programming model is used to determine the nesting of different sizes of rectangular patterns to meet the demand for rectangular blanks for a given planning horizon. The test data used in this study is generated randomly from a specific normal distribution. The average scrap percentage obtained is within acceptable limits. In the second approach, a genetic algorithm is used to generate sequences of the input patterns to be allocated on a finite width with infinite-length material. Each gene represents the sequence in which the patterns are to be allocated using the allocation algorithm developed. The scrap percentage of each allocation is used as an evaluation criterion for each gene for determining the best allocation while considering successive generations. The allocation algorithm uses the sliding method integrated with an artificial neural network based on the adaptive resonance theory (ART1) paradigm to allocate the patterns according to the sequence generated by the genetic algorithm. It slides an incoming pattern next to the allocated ones and keeps all scrap areas produced, which can be utilized in allocating a new pattern through the ART1 network. If there is a possible match with an incoming pattern and one of the scrap areas, the neural network selects the best match area and assigns the pattern. Both approaches gave satisfactory results. The second approach generated nests having packing densities in the range 95–97%. Improvement in packing densities was possible at the expense of excessive computational time. Parallel implementation of this unconventional approach could well bring a quick and satisfactory solution to this classical problem.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 14
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 9 (1998), S. 353-359 
    ISSN: 1572-8145
    Schlagwort(e): Cold forging ; process planning ; fuzzy logic ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract In this paper, two artificial intelligence (AI) techniques were applied to the problem of process planning in multiple-blow cold forging. Given the reduction in area of the product to be forged and the degree of formability of the material, in the first application a fuzzy logic (FL) technique was used to discriminate whether or not a cold forged product was feasible in a single blow. In the second application, a neural network (NN) architecture was used to identify the correct number of blows necessary to complete the cold forging process.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 15
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 6 (1995), S. 377-387 
    ISSN: 1572-8145
    Schlagwort(e): Job-shop scheduling ; neural networks ; constraint satisfaction ; optimization ; rules of thumb
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Recently neural network architectures have been developed that are capable of solving deterministic job-shop scheduling problems, part of the large class of NP-complete problems. In these architectures, however, no valid optimization criterion has been implemented. In this paper an enhanced neural network architecture for job-shop scheduling is proposed in which general rules of thumb for job-shop scheduling have been incorporated as a local optimization criterion. Implementation of the rules of thumb, by adaptation of the network architecture, results in a network that actually incorporates the optimization criterion, enabling parallel hardware implementation. Owing to the implemented local optimization criterion the performance of the network architecture is superior to previously presented architectures. Comparison with advanced heuristic sequential schedulers showed equal performance with respect to the quality of the solutions and better performance with respect to calculation speed.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 16
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 7 (1996), S. 23-38 
    ISSN: 1572-8145
    Schlagwort(e): Intelligent process control ; molding ; neural networks ; nonlinear optimization ; Taguchi method
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: current investigation focused on neural-network-based control of manufacturing processes utilizing an optimization scheme. In an earlier study, Demirci and Coulter introduced the utilization of neural networks for the intelligent control of molding processes. In that study, a forward model neural network, employed with a search strategy based on the factorial design of experiments method, was shown to successfully control the flow progression during injection molding processes. Recently, Demirciet al. showed that the search mechanism based on the factorial design of experiments method can be intolerable in time during on-line control of manufacturing processes, and suggested an inverse model neural network. This inverse model neural network was shown to be beneficial as it totally eliminated time-consuming parameter searches, but it required a harder mapping than the forward model neural network and thus its performance was inferior. In the present study, the authors investigated two different optimization methods that were utilized in making the search method of the forward control scheme more efficient. The first method was Taguchi's method of parameter design, and the second method was a nonlinear optimization method known as Nelder and Mead's downhill simplex method. These two methods were separately utilized in creating an efficient search method to be used with the forward model neural network. The performance of the resulting two control methods was compared with each other as well as with that of the forward control scheme utilizing a search strategy based on the factorial design of experiments method. Although the applications in this study were on molding processes, the method can be applied to any manufacturing process for which a process model and anin-situ sensing scheme exists.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 17
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 7 (1996), S. 243-250 
    ISSN: 1572-8145
    Schlagwort(e): Job-shop scheduling ; real-time dispatching ; simulation ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: To schedule a job shop, the first task is to select an appropriate scheduling algorithm or rule. Because of the complexity of scheduling problems, no general algorithm sufficient for solving all scheduling problems has yet been developed. Most job-shop scheduling systems offer alternative algorithms for different situations, and experienced human schedulers are needed to select the best dispatching rule in these systems. This paper proposes a new algorithm for job-shop scheduling problems. This algorithm consists of three stages. First, computer simulation techniques are used to evaluate the efficiency of heuristic rules in different scheduling situations. Second, the simulation results are used to train a neural network in order to capture the knowledge which can be used to select the most efficient heuristic rule for each scheduling situation. Finally, the trained neural network is used as a dispatching rule selector in the real-time scheduling process. Research results have shown great potential in using a neural network to replace human schedulers in selecting an appropriate approach for real-time scheduling. This research is part of an ongoing project of developing a real-time planning and scheduling system.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 18
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 7 (1996), S. 329-339 
    ISSN: 1572-8145
    Schlagwort(e): Automated tuning ; electronic circuit ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Manufacturing of electronic circuits for microwave communication boards often requires tuning of different circuit characteristics by manual adjustment of several trimmer components, including the trimmer's resistance and capacitance. This manual tuning process was automated by applying the artificial neural network modeling approach. In the considered tuning process, which required manual adjustment of a set of trimmers, multiple specification criteria had to be satisfied by several trimmer rotations. The tuning process was described in terms of three independent steps: the circuit output measurement, trimmer selection, and trimmer rotation. The trimmer selection was performed by a semi-supervised neural network, which learned the patterns of circuit characteristics and the deviations between the ideal and practical outputs. Another network was developed for determination of trimmer rotation rate. The results, based on computer simulation of the tuning process, showed that the developed system improved performance of the tuning process, allowing for automation of the microwave circuit board tuning task in a real manufacturing environment.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 19
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 9 (1998), S. 303-314 
    ISSN: 1572-8145
    Schlagwort(e): Grinding modelling ; neural networks ; fuzzy set theory ; genetic algorithm ; grinding information system
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract The paper describes different methods for modelling and optimization of grinding processes. First the process and product quality characterizing quantities have to be measured. Afterwards different model types, e.g. physical–empirical basic grinding models as well as empirical process models based on neural networks, fuzzy set theory and standard multiple regression methods, are discussed for an off-line process conceptualization and optimization using a genetic algorithm. The assessment of grinding process results, which build the individuals in the genetic algorithm's population, is carried out using a target tree method. The methods presented are integrated into an existing grinding information system, which is part of a three control loop system for quality assurance.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 20
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 6 (1995), S. 175-190 
    ISSN: 1572-8145
    Schlagwort(e): Concurrent engineering ; cell design ; cell control ; simulation ; knowledge-based expert system ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract One of the major thrusts of ‘agile/lean/responsive’ manufacturing strategies of the twentyfirst century is to introduce advanced information technology into manufacturing. This paper presents a framework for robust manufacturing system design with the integration of simulation, neural networks and knowledge-based expert system tools. An operation/ cost-driven cell design methodology was applied to concurrently consider cell physical design and the complexity of cell control functions. Simulation was exercised to estimate performance measures based on input parameters and given cell configurations. A rulebased expert system was employed to store the acquired expert knowledge regarding the relation between cell control complexities, cost of cell controls, performance measures and cell configuration. Neural networks were applied to predict the cell design configuration and corresponding complexities of cell control functions. Training of neural networks was performed with both forward and backward methods by using the same pair of data sets. Hence, trained neural networks will be able to predict either input or output parameters. This innovative new design methodology was illustrated via a successful implementation exercise resulting in actually acquiring an automated cell at industrial settings. The experience learned from this exercise indicates that the proposed design methodology works well as an effective decision support system for cell designers and the management in determining appropriate cell configuration and cell control functions at the design stage.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 21
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 8 (1997), S. 167-175 
    ISSN: 1572-8145
    Schlagwort(e): Pattern recognition ; neural networks ; time series ; feature extraction
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract This paper presents a new approach for automated parts recognition. It is based on the use of the signature and autocorrelation functions for feature extraction and a neural network for the analysis of recognition. The signature represents the shapes of boundaries detected in digitized binary images of the parts. The autocorrelation coefficients computed from the signature are invariant to transformations such as scaling, translation and rotation of the parts. These unique extracted features are fed to the neural network. A multilayer perceptron with two hidden layers, along with a backpropagation learning algorithm, is used as a pattern classifier. In addition, the position information of the part for a robot with a vision system is described to permit grasping and pick-up. Experimental results indicate that the proposed approach is appropriate for the accurate and fast recognition and inspection of parts in automated manufacturing systems.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 22
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent manufacturing 9 (1998), S. 447-455 
    ISSN: 1572-8145
    Schlagwort(e): Cutting ; tool condition monitoring ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract Cutting forces and acoustic emission measures as a function of tool wear are presented for different cutting parameters and their applicability for tool condition monitoring is evaluated. The best of them, together with cutting parameters, were chosen as inputs to a feedforward, back propagation (FFBP) neural network; some training techniques were applied and their effectiveness is also evaluated. Conventional training of FFBP neural networks very soon leads to overtraining, hence to deterioration in the net response. Training of these nets depends very much on the initial weight values. A good way of finding satisfactory results is to introduce random distortions to the weight system, which efficiently push the net out of a local minimum of testing errors. An even more effective method may be to employ temporary shifts in the weights, alternately negative and positive. This has two advantages: (1) it brings the net to balance between training and testing errors and (2) it enables a great reduction in the number of hidden nodes.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 23
    Digitale Medien
    Digitale Medien
    Springer
    Computational & mathematical organization theory 5 (1999), S. 129-145 
    ISSN: 1572-9346
    Schlagwort(e): collective action ; informal control ; social influence ; neural networks ; computer simulation
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Mathematik
    Notizen: Abstract This study extends previous research that showed how informal social sanctions can backfire when members prefer friendship over enforcement of group norms. We use a type of neural network to model the coordination of informal social control in a small group of adaptive agents confronted with a social dilemma. This model incorporates two mechanisms of social influence, informal sanctions and imitation. Both mechanisms vary with the strength of the social tie between source and target. Previous research focused on the effects of social sanctions. Here, we demonstrate a curvilinear effect of imitation on compliance with prosocial norms. Moderate doses of imitation reduce the coordination complexity of self-organized collective action and help the network achieve satisfactory levels of cooperation. High doses, however, undermine the agent-based learning required to find cooperative solutions. Increasing group size also diminishes compliance due to increased complexity, with larger groups requiring more imitation to overcome the coordination problem.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 24
    Digitale Medien
    Digitale Medien
    Springer
    Annals of operations research 63 (1996), S. 511-623 
    ISSN: 1572-9338
    Schlagwort(e): Artificial intelligence ; bibliography ; combinatorial optimization ; constraint logic programming ; evolutionary computation ; genetic algorithms ; greedy random adaptive search procedure ; heuristics ; hybrids ; local search ; metaheuristics ; neural networks ; non-monotonic search strategies ; problem-space method ; simulated annealing ; tabu search ; threshold algorithms
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Mathematik , Wirtschaftswissenschaften
    Notizen: Abstract Metaheuristics are the most exciting development in approximate optimization techniques of the last two decades. They have had widespread successes in attacking a variety of difficult combinatorial optimization problems that arise in many practical areas. This bibliography provides a classification of a comprehensive list of 1380 references on the theory and application of metaheuristics. Metaheuristics include but are not limited to constraint logic programming; greedy random adaptive search procedures; natural evolutionary computation; neural networks; non-monotonic search strategies; space-search methods; simulated annealing; tabu search; threshold algorithms and their hybrids. References are presented in alphabetical order under a number of subheadings.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 25
    Digitale Medien
    Digitale Medien
    Springer
    International journal of flexible manufacturing systems 7 (1995), S. 147-175 
    ISSN: 1572-9370
    Schlagwort(e): inductive learning ; intelligent scheduling ; neural networks ; FMS
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau
    Notizen: Abstract With the growing uncertainty and complexity in the manufacturing environment, most scheduling problems have been proven to be NP-complete and this can degrade the performance of conventional operations research (OR) techniques. This article presents a system-attribute-oriented knowledge-based scheduling system (SAOSS) with inductive learning capability. With the rich heritage from artificial intelligence (AI), SAOSS takes a multialgorithm paradigm which makes it more intelligent, flexible, and suitable than others for tackling complicated, dynamic scheduling problems. SAOSS employs an efficient and effective inductive learning method, a continuous iterative dichotomister 3 (CID3) algorithm, to induce decision rules for scheduling by converting corresponding decision trees into hidden layers of a self-generated neural network. Connection weights between hidden units imply the scheduling heuristics, which are then formulated into scheduling rules. An FMS scheduling problem is also given for illustration. The scheduling results show that the system-attribute-oriented knowledge-based approach is capable of addressing dynamic scheduling problems.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 26
    Digitale Medien
    Digitale Medien
    Springer
    Journal of heuristics 1 (1995), S. 67-76 
    ISSN: 1572-9397
    Schlagwort(e): neural networks ; traveling salesman problem
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Mathematik
    Notizen: Abstract In this article, we focus on implementing the elastic net method to solve the traveling salesman problem using a hierarchical approach. The result is a significant speed-up, which is studied both analytically and experimentally.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 27
    Digitale Medien
    Digitale Medien
    Springer
    Advances in computational mathematics 5 (1996), S. 245-268 
    ISSN: 1572-9044
    Schlagwort(e): Analytic geometry ; theory of exponentials ; neural networks ; regression
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Mathematik
    Notizen: Abstract This paper deals with nonlinear least-squares problems involving the fitting to data of parameterized analytic functions. For generic regression data, a general result establishes the countability, and under stronger assumptions finiteness, of the set of functions giving rise to critical points of the quadratic loss function. In the special case of what are usually called “single-hidden layer neural networks”, which are built upon the standard sigmoidal activation tanh(x) (or equivalently (1 +e −x )−1), a rough upper bound for this cardinality is provided as well.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 28
    Digitale Medien
    Digitale Medien
    Springer
    Acta applicandae mathematicae 55 (1999), S. 303-311 
    ISSN: 1572-9036
    Schlagwort(e): neural networks ; density ; complexity ; sigmoidal functions ; ridge-type functions ; hyperbolic-type functions
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Mathematik
    Notizen: Abstract In the following paper, we present a brief and easily accessible introduction to the theory of neural networks under special emphasis on the rôle of pure and applied mathematics in this interesting field of research. In order to allow a quick and direct approach even for nonspecialists, we only consider three-layer feedforward networks with sigmoidal transfer functions and do not cover general multi-layer, recursive or radial-basis-function networks. Moreover, we focus our attention on density and complexity results while construction problems based on operator techniques are not discussed in detail. Especially, in connection with complexity results, we show that neural networks in general have the power to approximate certain function spaces with a minimal number of free parameters. In other words, under this specific point of view neural networks represent one of the best possible approximation devices available. Besides pointing out this remarkable fact, the main motivation for presenting this paper is to give some more mathematicians an idea of what is going on in the theory of neural networks and, perhaps, to encourage, at least a few of them, to start working in this highly interdisciplinary and promising field, too.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 29
    Digitale Medien
    Digitale Medien
    Springer
    Advances in computational mathematics 5 (1996), S. 137-151 
    ISSN: 1572-9044
    Schlagwort(e): Uniform approximation ; constructive ; multivariate ; superposition ; algorithm ; neural networks ; 26B40 ; 41A63 ; 65D15
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Mathematik
    Notizen: Abstract In this paper, we develop two algorithms for Chebyshev approximation of continuous functions on [0, 1] n using the modulus of continuity and the maximum norm estimated by a given finite data system. The algorithms are based on constructive versions of Kolmogorov's superposition theorem. One of the algorithms we apply to neural networks.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 30
    Digitale Medien
    Digitale Medien
    Springer
    Optical review 2 (1995), S. 159-162 
    ISSN: 1349-9432
    Schlagwort(e): mathematical morphology ; nonlinear filter ; image processing ; simulated annealing ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Physik
    Notizen: Abstract An efficient algorithm based on the simulated annealing for the learning optimization of morphological filters is proposed. The learning stage is divided into two consecutive parts; the initial-learning stage finds and fixes the most important parts of the structuring elements, and the precise-learning stage determines details of the rest. This method significantly reduces the number of trials for the modification of structuring elements. The proposed algorithm is applied to the learning optimization of the bipolar morphological operation, whose optimization problem has not yet been investigated. It is shown experimentally that the algorithm optimizes the operator as efficiently as the conventional one and reduces the amount of calculation.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 31
    Digitale Medien
    Digitale Medien
    Springer
    Informatik, Forschung und Entwicklung 12 (1997), S. 30-37 
    ISSN: 0949-2925
    Schlagwort(e): Schlüsselwörter: RBF ; Radiale Basisfunktionen ; flexible Metrik ; Funktionsapproximation ; Neuronale Netze ; höherdimensionale Funktionen ; selbstlernend ; Keywords: RBF ; Radial Basis Functions ; flexible metrics ; function approximation ; neural networks ; multi-dimensional inputs ; data driven ; CR Subject Classification: F.1.1. ; F.2.2. ; G.1.1. ; G.1.2. ; G.1.6. ; H.3.3. ; I.5.1.
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Beschreibung / Inhaltsverzeichnis: Abstract. Radial Basis Functions (RBF) are a popular method of function approximation with neural networks. However, the radial shape of the basis functions does not always reflect the function's characteristics adequately. Whenever a function's output varies differently according to different input variables, generalizing the radial shape to an ellipsoidal shape (GRBF) is appropriate. Free orientations of the ellipsoids are useful whenever variations occur not only along the input variables, but also along their linear combinations. Since existing adaptation algorithms for GRBFs usually use gradient descent or unsupervised learning to adjust the parameters of the GRBFs, they need a vast number of training iterations. In this article, we propose the new adaptation algorithm Growing Ellipsoids for GRBFs. It is based on a geometric concept, considering the elliptical shape of the GRBFs explicitly. New units are inserted sequentially at data points with high approximation error. The new unit's parameters are adapted immediately trying to eliminate the approximation error locally. The algorithm operates off-line on an available data set.
    Notizen: Zusammenfassung. Radiale Basisfunktionen (RBF) sind eine Methode zur Funktionsapproximation. Sie finden im Gebiet der Neuronalen Netze breite Verbreitung. Nicht immer jedoch wird die radialsymmetrische Form der Basisfunktionen der zu approximierenden Funktion gerecht. Hängt der Funktionswert unterschiedlich stark von unterschiedlichen Eingabedimensionen ab, so ermöglicht erst eine Generalisierung von radialen zu ellipsoiden Basisfunktionen (GRBF) eine adäquate Modellierung. Freie Orientierungen der GRBF sind sinnvoll, falls starke Variationen nicht nur entlang der Komponenten des Eingaberaumes, sondern auch entlang beliebiger Linearkombinationen liegen. Existierende Adaptionsalgorithmen für GRBF-Netze ziehen meist Gradientenabstieg oder unüberwachtes Lernen heran, und erfordern somit sehr viele Trainingsiterationen und damit lange Laufzeiten. In diesem Artikel stellen wir den neuartigen neuronalen Adaptionsalgorithmus Growing Ellipsoids vor, der auf einer geometrischen Anschauung beruht, indem die ellipsoide Form der Units explizit betrachtet wird. Neue Units werden sequentiell am Ort großer Approximationsfehler eingefügt. Die Parameter der neuen Units werden mit dem Ziel adaptiert, lokal den Approximationsfehler zu minimieren. Der Algorithmus arbeitet off-line auf einem vorhandenen Datensatz.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 32
    ISSN: 0885-6125
    Schlagwort(e): robot control ; neural networks ; uncertainty compensation ; stability and performance
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract In this article, an approach to improving the performance of robot continuous-path operation is proposed. This approach utilizes a multilayer feedforward neural network to compensate for model uncertainty associated with the robotic operation. Closed-loop stability and performance are analyzed. It is shown that the closed-loop system is stable in the sense that all signals are bounded; it is further proved that the performance of the closed-loop system is improved in the sense that certain erro measure of the closed-loop system decreases as the network learning process is iterated. These analytical results are confirmed by computer simulation. The effectiveness of the proposed approach is demonstrated through a laboratory experiment.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 33
    Digitale Medien
    Digitale Medien
    Springer
    Computers and the humanities 30 (1996), S. 1-10 
    ISSN: 1572-8412
    Schlagwort(e): neural networks ; function words ; authorship attribution ; The Federalist Papers
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Medien- und Kommunikationswissenschaften, Kommunikationsdesign
    Notizen: Abstract Neural Networks have recently been a matter of extensive research and popularity. Their application has increased considerably in areas in which we are presented with a large amount of data and we have to identify an underlying pattern. This paper will look at their application to stylometry. We believe that statistical methods of attributing authorship can be coupled effectively with neural networks to produce a very powerful classification tool. We illustrate this with an example of a famous case of disputed authorship, The Federalist Papers. Our method assigns the disputed papers to Madison, a result which is consistent with previous work on the subject.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 34
    Digitale Medien
    Digitale Medien
    Springer
    Minds and machines 9 (1999), S. 3-28 
    ISSN: 1572-8641
    Schlagwort(e): physical symbols ; formal programs ; neural networks ; designation ; interpretation ; representation ; semantics ; intensional meaning ; extensional meaning ; causal capacities ; emergence ; levels
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Philosophie
    Notizen: Abstract The purpose of this article is to show why consciousness and thought are not manifested in digital computers. Analyzing the rationale for claiming that the formal manipulation of physical symbols in Turing machines would emulate human thought, the article attempts to show why this proved false. This is because the reinterpretation of ‘designation’ and ‘meaning’ to accommodate physical symbol manipulation eliminated their crucial functions in human discourse. Words have denotations and intensional meanings because the brain transforms the physical stimuli received from the microworld into a qualitative, macroscopic representation for consciousness. Lacking this capacity as programmed machines, computers have no representations for their symbols to designate and mean. Unlike human beings in which consciousness and thought, with their inherent content, have emerged because of their organic natures, serial processing computers or parallel distributed processing systems, as programmed electrical machines, lack these causal capacities.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 35
    Digitale Medien
    Digitale Medien
    Springer
    Computers and the humanities 29 (1995), S. 259-270 
    ISSN: 1572-8412
    Schlagwort(e): author attribution ; content analysis ; discriminant analysis ; lexical statistics ; neural networks ; The Federalist
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Medien- und Kommunikationswissenschaften, Kommunikationsdesign
    Notizen: Abstract In studies of author attribution, measurement of differential use of function words is the most common procedure, though lexical statistics are often used. Content analysis has seldom been employed. We compare the success of lexical statistics, content analysis, and function words in classifying the 12 disputedFederalist papers. Of course, Mosteller and Wallace (1964) have presented overwhelming evidence that all 12 were by James Madison rather than by Alexander Hamilton. Our purpose is not to challenge these attributions but rather to useThe Federalist as a test case. We found lexical statistics to be of no use in classifying the disputed papers. Using both classical canonical discriminant analysis and a neural-network approach, content analytic measures — the Harvard III Psychosociological Dictionary and semantic differential indices — were found to be successful at attributing most of the disputed papers to Madison. However, a function-word approach is more successful. We argue that content analysis can be useful in cases where the function-word approach does not yield compelling conclusions and, perhaps, in preliminary screening in cases where there are a large number of possible authors.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 36
    Digitale Medien
    Digitale Medien
    Springer
    Artificial intelligence and law 3 (1995), S. 267-275 
    ISSN: 1572-8382
    Schlagwort(e): Legal Expert Systems ; sequenced transition networks ; neural networks ; ID3 algorithm ; Toulmin Argument Structures ; case-based reasoning ; production rule expert system ; divorce ; property division ; explanation
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Rechtswissenschaft
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 37
    Digitale Medien
    Digitale Medien
    Springer
    Computers and the humanities 29 (1995), S. 449-461 
    ISSN: 1572-8412
    Schlagwort(e): neural networks ; stylometric analysis ; Shakespeare ; Fletcher ; discrimination ; classification
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Medien- und Kommunikationswissenschaften, Kommunikationsdesign
    Notizen: Abstract In this paper we show, for the first time, how Radial Basis Function (RBF) network techniques can be used to explore questions surrounding authorship of historic documents. The paper illustrates the technical and practical aspects of RBF's, using data extracted from works written in the early 17th century by William Shakespeare and his contemporary John Fletcher. We also present benchmark comparisons with other standard techniques for contrast and comparison.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 38
    Digitale Medien
    Digitale Medien
    Springer
    Artificial intelligence and law 7 (1999), S. 115-128 
    ISSN: 1572-8382
    Schlagwort(e): analogy ; fuzzy logic ; learning ; legal formalism ; neural networks ; vagueness
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Rechtswissenschaft
    Notizen: Abstract Computational approaches to the law have frequently been characterized as being formalistic implementations of the syllogistic model of legal cognition: using insufficient or contradictory data, making analogies, learning through examples and experiences, applying vague and imprecise standards. We argue that, on the contrary, studies on neural networks and fuzzy reasoning show how AI & law research can go beyond syllogism, and, in doing that, can provide substantial contributions to the law.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 39
    Digitale Medien
    Digitale Medien
    Springer
    Artificial intelligence and law 7 (1999), S. 129-151 
    ISSN: 1572-8382
    Schlagwort(e): connectionism ; legal philosophy ; legal theory ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Rechtswissenschaft
    Notizen: Abstract This paper examines the use of connectionism (neural networks) in modelling legal reasoning. I discuss how the implementations of neural networks have failed to account for legal theoretical perspectives on adjudication. I criticise the use of neural networks in law, not because connectionism is inherently unsuitable in law, but rather because it has been done so poorly to date. The paper reviews a number of legal theories which provide a grounding for the use of neural networks in law. It then examines some implementations undertaken in law and criticises their legal theoretical naïvete. It then presents a lessons from the implementations which researchers must bear in mind if they wish to build neural networks which are justified by legal theories.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 40
    Digitale Medien
    Digitale Medien
    Springer
    Mathematical physics, analysis and geometry 1 (1998), S. 107-144 
    ISSN: 1572-9656
    Schlagwort(e): Hopfield model ; neural networks ; metastates ; replica symmetry ; Brascamp–Lieb inequalities
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Mathematik , Physik
    Notizen: Abstract We study the finite dimensional marginals of the Gibbs measure in the Hopfield model at low temperature when the number of patterns, M, is proportional to the volume with a sufficiently small proportionality constant α 〉 0. It is shown that even when a single pattern is selected (by a magnetic field or by conditioning), the marginals do not converge almost surely, but only in law. The corresponding limiting law is constructed explicitly. We fit our result in the recently proposed language of ‘metastates’ which we discuss some length. As a byproduct, in a certain regime of the parameters α and β (the inverse temperature), we also give a simple proof of Talagrand’s recent result that the replica symmetric solution found by Amit, Gutfreund, and Sompolinsky can be rigorously justified.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 41
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 23 (1998), S. 105-128 
    ISSN: 1573-0409
    Schlagwort(e): neural networks ; robust control ; back stepping control ; adaptive control
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract Neural network (NN) controllers for the robust back stepping control of robotic systems in both continuous and discrete-time are presented. Control action is employed to achieve tracking performance for unknown nonlinear system. Tuning methods are derived for the NN based on delta rule. Novel weight tuning algorithms for the NN are obtained that are similar to ε-modification in the case of continuous-time adaptive control. Uniform ultimate boundedness of the tracking error and the weight estimates are presented without using the persistency of excitation (PE) condition. Certainty equivalence is not used and regression matrix is not computed. No learning phase is needed for the NN and initialization of the network weights is straightforward. Simulation results justify the theoretical conclusions.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 42
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 25 (1999), S. 121-132 
    ISSN: 1573-0409
    Schlagwort(e): invariant object recognition ; pattern recognition ; neural networks ; flexible manufacturing
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract A small flexible production cell has been built around a selectively compliant articulated robot arm. Moving on a conveyor belt, boxes marked with different labels are presented to the robot in a random order. Using a camera and a vision card, the labels on the boxes are recognized. Each one of the labels can be rotated, translated or scaled. Three different invariant feature extraction methods (signature, invariant moments of Hu and Zernike) are compared. A neural net is used to classify the labels. The task of the SCARA robot is to pick up the moving boxes and to sort them according to their labels.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 43
    Digitale Medien
    Digitale Medien
    Springer
    Marketing letters 6 (1995), S. 251-263 
    ISSN: 1573-059X
    Schlagwort(e): neural networks ; logistic regression ; back-propagation ; empirical comparison ; sigmoid function ; C-Index
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Wirtschaftswissenschaften
    Notizen: Abstract The purpose of this paper is to critically compare a neural network technique with the established statistical technique of logistic regression for modeling decisions for several marketing situations. In our study, these two modeling techniques were compared using data collected on the decisions by supermarket buyers whether to add a new product to their shelves or not. Our analysis shows that although neural networks offer a possible alternative approach, they have both strengths and weaknesses that must be clearly understood.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 44
    Digitale Medien
    Digitale Medien
    Springer
    Journal of statistical physics 90 (1998), S. 253-260 
    ISSN: 1572-9613
    Schlagwort(e): Monte Carlo updating schemes ; neural networks ; protein dynamics
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Physik
    Notizen: Abstract A Hopfield neural network was constructed with relevance to protein dynamics. The dynamics of this network was analyzed by determining the distribution of first passage times between memories and its dependence on temperature. The distribution depended on the updating scheme. This illustrates the importance of choosing an updating scheme that leads to physically meaningful results in computational models of dynamic processes, such as in neural networks or molecular dynamics.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 45
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 16 (1996), S. 229-243 
    ISSN: 1573-0409
    Schlagwort(e): Redundant robots ; obstacle avoidance ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract A computationally efficient, obstacle avoidance algorithm for redundant robots is presented in this paper. This algorithm incorporates the neural networks and pseudodistance function D p in the framework of resolved motion rate control. Thus, it is well suited for real-time implementation. Robot arm kinematic control is carried out by the Hopfield network. The connection weights of the network can be determined from the current value of Jacobian matrix at each sampling time, and joint velocity commands can be generated from the outputs of the network. The obstacle avoidance task is achieved by formulating the performance criterion as D p〉d min (d min represents the minimal distance between the redundant robot and obstacles). Its calculation is only related to some vertices which are used to model the robot and obstacles, and the computational times are nearly linear in the total number of vertices. Several simulation cases for a four-link planar manipulator are given to prove that the proposed collision-free trajectory planning scheme is efficient and practical.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 46
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 17 (1996), S. 283-308 
    ISSN: 1573-0409
    Schlagwort(e): manufacturing ; motion in contact ; force/torque sensors ; error detection ; plan monitoring ; uncertainty ; robotics ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract This paper presents a new approach to error detection during motion in contact under uncertainty for robotic manufacturing tasks. In this approach, artificial neural networks are used for perception-based learning. The six force-and-torque signals from the wrist sensor of a robot arm are fed into the network. A self-organizing map is what learns the different contact states in an unsupervised way. The method is intended to work properly in complex real-world manufacturing environments, for which existent approaches based on geometric analytical models may not be feasible, or may be too difficult. It is used for different tasks involving motion in contact, particularly the peg-in-hole insertion task, and complex insertion or extraction operations in a flexible manufacturing system. Several real examples for these cases are presented.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 47
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 17 (1996), S. 327-349 
    ISSN: 1573-0409
    Schlagwort(e): neural networks ; flexible-link robots ; singular perturbation
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract The object in this paper is to achieve tracking control of a partially unknown flexible-link robot arm. It is shown how to stabilize the internal dynamics by selecting a physically meaningful modified performance output for tracking; this output is the slow portion of the link-tip motions. That is, the tracking requirement is relaxed so that the internal dynamics are controllable through a boundary layer correction. The controller is composed of singular-perturbation based fast control and an outer-loop slow control. The slow subsystem is controlled by a neural network (NN) for feedback linearization, plus a PD outer-loop for tracking, and a robustifying term to assure the closed-loop stability. No off-line learning or training is needed for the NN. Tracking and stability are proven using Lyapunov techniques that yield a novel modified NN weight tuning algorithm.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 48
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 22 (1998), S. 351-374 
    ISSN: 1573-0409
    Schlagwort(e): micromanipulation station ; autonomous robots ; microrobots ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract Micromanipulation has become an issue of primary importance in industry and biomedicine, since human manual capabilities are restricted to certain tolerances. The manipulation of biological cells or the assembly of a complete microsystem composed of different microcomponents are examples of the application of piezoelectric-driven microrobots. An automated microrobot-based micromanipulation desktop-station is developed by an interdisciplinary group at the University of Karlsruhe. The process of assembly takes place in the field of view of a light optical microscope. This paper focuses on motion control problems of the microrobots. The ability of an intelligent microsystem to adapt itself to the process requirements is of great importance, especially for assembly robots. The microrobots must be able to operate in a partially defined environment and to ensure reasonable behaviour in unpredicted situations. A neural control concept based on a reference model approach is proposed as a solution. It is shown, that the neural controller is able to learn the desired behaviour. It considerably outperforms an analytically designed linear controller. This is demonstrated both in simulation and in the real environment.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 49
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 24 (1999), S. 43-68 
    ISSN: 1573-0409
    Schlagwort(e): learning robots ; system organization ; optimization ; physical equation ; look-ut table ; neural networks ; fuzzy controllers
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract This paper explores a stepwise learning approach based on a system's decomposition into functional subsystems. Two case studies are examined: a visually guided robot that learns to track a maneuvering object, and a robot that learns to use the information from a force sensor in order to put a peg into a hole. These two applications show the features and advantages of the proposed approach: i) the subsystems naturally arise as functional components of the hardware and software; ii) these subsystems are building blocks of the robot behavior and can be combined in several ways for performing various tasks; iii) this decomposition makes it easier to check the performances and detect the cause of a malfunction; iv) only those subsystems for which a satisfactory solution is not available need to be learned; v) the strategy proposed for coordinating the optimization of all subsystems ensures an improvement at the task-level; vi) the overall system's behavior is significantly improved by the stepwise learning approach.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 50
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 22 (1998), S. 255-267 
    ISSN: 1573-0409
    Schlagwort(e): localisation ; neural networks ; stochastic diffusion
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract This paper introduces the Focused Stochastic Diffusion Network as a novel method of self-localisation for an autonomous wheelchair in a complex, busy environment. The space of possible positions is explored in parallel by a set of cells searching in a competitive co-operative manner for the most likely position of the wheelchair in its environment. Experimental results from the SENARIO autonomous wheelchair project indicate the technique is practical and robust.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 51
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 17 (1996), S. 81-99 
    ISSN: 1573-0409
    Schlagwort(e): forging automation ; compliance control ; neural networks ; dynamic simulation ; finite element models ; recursive algorithms ; intelligent manufacturing
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract Automation of forging processes is important for both safety and efficiency in today's advanced manufacturing operations. This work supports the development of an Intelligent Open Die Forging System which will integrate state-of-the-art modelling techniques, automatic die selection and sequencing, full system dynamic simulation, automatic machine programming and coordination, and sensor-based process control to enable the production of more general and complex workpiece geometries than are achievable using current forging methods. Effective automation of this open die forging system requires the coordination and control of the major system components: press, robot, and furnace. In particular, forces exerted on the robot through its manipulation of the workpiece during forging must be minimized to avoid damage to the manipulator mechanism. In this paper, the application of neural networks for compliance control of the forging robot to minimize these forces is investigated. Effectiveness of the neural network-based compliance control module is evaluated through a full dynamic system simulation, which will later form a central part of the complete Intelligent Forging System. Dynamic simulation of the robot is achieved using an efficient O(N) recursive algorithm, while material flow of the workpiece is modeled with a finite element approach. Simulation and timing results for the complete processing system for a specific open die forging example are presented.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 52
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 20 (1997), S. 295-317 
    ISSN: 1573-0409
    Schlagwort(e): nonholonomic systems ; mobile robots ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract A control structure that makes possible the integration of a kinematiccontroller and a neural network (NN) computed-torque controller fornonholonomic mobile robots is presented. A combined kinematic/torque controllaw is developed and stability is guaranteed by Lyapunov theory. Thiscontrol algorithm is applied to the practical point stabilization problemi.e., stabilization to a small neighborhood of the origin. The NN controllercan deal with unmodeled bounded disturbances and/or unstructured unmodeleddynamics in the vehicle. On-line NN weight tuning algorithms that do notrequire off-line learning yet guarantee small tracking errors and boundedcontrol signals are utilized.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 53
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 20 (1997), S. 181-193 
    ISSN: 1573-0409
    Schlagwort(e): robot manipulators ; adaptive control ; neural networks ; stability analysis
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract In this paper a controller based on neural networks is proposed toachieve output trajectory tracking of rigid robot manipulators. Neuralnetworks used here are one hidden layer ones so that their outputs dependlinearly on the parameters. Our method uses a decomposed connectioniststructure. Each neural network approximate a separate element of thedynamical model. These approximations are used to perform an adaptive stablecontrol law. The controller is based on direct adaptive techniques and theLyapunov approach is used to derive the adaptation laws of the nets’parameters. By using an intrinsic physical property of the manipulator, thesystem is proved to be stable. The performance of the controller depends onthe quality of the approximation, i.e. on the inherent reconstruction errorsof the exact functions.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 54
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 21 (1998), S. 143-154 
    ISSN: 1573-0409
    Schlagwort(e): neural networks ; sensor calibration ; fault detection and isolation
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract Recently, the use of Autoassociative Neural Networks (AANNs) to perform on-line calibration monitoring of process sensors has been shown to not only be feasible, but practical as well. This paper summarizes the results of applying AANNs to instrument surveillance and calibration monitoring at Florida Power Corporation's Crystal River #3 Nuclear Power Plant and at the Oak Ridge National Laboratory High Flux Isotope Reactor. In both cases sensor drifts are detectable at a nominal level of 0.5% instrument's full scale range. This paper will discuss the selection of a five layer neural network architecture, a robust training paradigm, the input selection criteria, and a retuning algorithm.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 55
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 26 (1999), S. 91-100 
    ISSN: 1573-0409
    Schlagwort(e): robots ; neural networks ; adaptiveness ; stability ; approximation
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract An indirect adaptive control approach is developed in this paper for robots with unknown nonlinear dynamics using neural networks (NNs). A key property of the proposed approach is that the actual joint angle values in the control law are replaced by the desired joint angles, angle velocities and accelerators, and the bound on the NN reconstruction errors is assumed to be unknown. Main theoretical results for designing such a neuro-controller are given, and the control performance of the proposed controller is verified with simulation studies.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 56
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 20 (1997), S. 251-273 
    ISSN: 1573-0409
    Schlagwort(e): robot control ; adaptive behavior ; robust intelligent control ; multi-robot systems ; machine learning ; neural networks ; genetic algorithms ; cognitive architecture.
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract The objective of this paper is to present a cognitive architecture thatutilizes three different methodologies for adaptive, robust control ofrobots behaving intelligently in a team. The robots interact within a worldof objects, and obstacles, performing tasks robustly, while improving theirperformance through learning. The adaptive control of the robots has beenachieved by a novel control system. The Tropism-based cognitive architecturefor the individual behavior of robots in a colony is demonstrated throughexperimental investigation of the robot colony. This architecture is basedon representation of the likes and dislikes of the robots. It is shown thatthe novel architecture is not only robust, but also provides the robots withintelligent adaptive behavior. This objective is achieved by utilization ofthree different techniques of neural networks, machine learning, and geneticalgorithms. Each of these methodologies are applied to the tropismarchitecture, resulting in improvements in the task performance of the robotteam, demonstrating the adaptability and robustness of the proposed controlsystem.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 57
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 25 (1999), S. 43-59 
    ISSN: 1573-0409
    Schlagwort(e): PID control ; GAs ; neural networks ; multivariable systems
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract When genetic algorithms (GAs) are applied for PID parameter tuning, since the PID parameters are adjusted almost randomly, it is possible that the plant will be damaged due to abrupt changes in PID parameters. To solve this problem, a neural network will be used to model the plant and the genetic tuning procedure will be performed on the neural network instead of the plant. After determining the PID parameters in this off-line manner, these gains are then applied to the plant for on-line control. Moreover, considering that the neural network model may not be accurate enough, a method is also proposed for on-line fine-tuning of PID parameters. To show the validity of the proposed method, a seesaw system that has one input and two outputs will be used for experimental evaluation
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 58
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 20 (1997), S. 157-180 
    ISSN: 1573-0409
    Schlagwort(e): robot ; PID control ; neural networks ; learning ; generalization
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract In this article, an approach for improving the performance of industrialrobots using multilayer feedforward neural networks is presented. Thecontroller based on this approach consists of two main components: a PIDcontrol and a neural network. The function of the neural network is tocomplement the PID control for the specific purpose of improving theperformance of the system over time. Analytical and experimental resultsconcerning this synthesis of neural networks and PID control are presented.The analytical results assert that the performance of PID-controlledindustrial robots can be improved through proper utilization of the learningand generalization ability of neural networks. The experimental results,obtained through actual implementation using a commercial industrial robot,demonstrate the effectiveness of such control synthesis for practicalapplications. The results of this work suggest that neural networks could beadded to existing PID-controlled industrial robots for performanceimprovement.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 59
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 18 (1997), S. 367-397 
    ISSN: 1573-0409
    Schlagwort(e): virtual reality ; human-machine system ; robotics ; neural networks ; collision avoidance ; trajectory planning ; conglomerate of spheres
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract This paper describes how virtual tools that represent real robot end-effectors are used in conjunction with a generalized conglomerate-of-spheres approach to collision avoidance in such a way that telerobotic trajectory planning can be accomplished using simple gesture phrases such as ‘put that there while avoiding that’. In this concept, an operator (or set of collaborators) need not train for cumbersome telemanipulation on several multiple-link robots, nor do robots need a priori knowledge of operator intent and exhaustive algorithms for evaluating every aspect of a detailed environment model. The human does what humans do best during task specification, while the robot does what machines do best during trajectory planning and execution. Four telerobotic stages were implemented to demonstrate this strategic supervision concept that will facilitate collaborative control between humans and machines. In the first stage, virtual reality tools are selected from a ‘toolbox’ by the operator(s) and then these virtual tools are computationally interwoven into the live video scene with depth correlation. Each virtual tool is a graphic representation of a robot end-effector (gripper, cutter, or other robot tool) that carries tool-use attributes on how to perform a task. An operator uses an instrumented glove to virtually retrieve the disembodied tool, in the shared scene, and place it near objects and obstacles while giving key-point gesture directives, such as ‘cut there while avoiding that’. Collaborators on a network may alter the plan by changing tools or tool positioning to achieve preferred results from their own perspectives. When parties agree, from wherever they reside geographically, the robot(s) create and execute appropriate trajectories suitable to their own particular links and joints. Stage two generates standard joint-interpolated trajectories, and later creates potential field trajectories if necessary. Stage three tests for collisions with obstacles identified by the operator and modeled as conglomerates of spheres. Stage four involves automatic grasping (or cutting etc.) once the robot camera acquires a close-up view of the object during approach. In this paper particular emphasis is placed on the conglomerate-of-spheres approach to collision detection as integrated with the virtual tools concept for a Puma 560 robot by the Virtual Tools and Robotics Group in the Computer Integrated Manufacturing Laboratory at The Pennsylvania State University (Penn State).
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 60
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 21 (1998), S. 155-165 
    ISSN: 1573-0409
    Schlagwort(e): neural networks ; synchronization of signals ; time series
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract Before any multivariate analysis scheme (using typicaly simultaneous measurements) it is useful to readjust in time each measurement so that each one refer to the same element of the model. This problem arises frequently in the modelization of an industrial process. It is sometimes possible to propose a dynamic model after a microscopic study of displacements of matter. However such a study is very complex and cannot be conceived by a machine analysis of the data. In this article we present a practical self-adapting methodology which automates the synchronization of captors. This method use a recurrent neural network for the self auto-adaptivity of the synchronization. This network is model and tune automaticaly by an initialization process based on the local stationary phenomena appearing in measurements.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 61
    Digitale Medien
    Digitale Medien
    Springer
    Journal of intelligent and robotic systems 22 (1998), S. 117-127 
    ISSN: 1573-0409
    Schlagwort(e): path planning for robots ; stochastic uncertainty ; real-time computation ; B-splines ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract The problem of adaptive trajectory planning for robots under stochastic uncertainty is considered, where new information about the robots and their environment is presented on-line. Solving the problem numerically by means of spline approximation and by applying the method of neural networks, the optimal control can be calculated in real-time. Some numerical results are presented.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 62
    Digitale Medien
    Digitale Medien
    Springer
    Machine learning 20 (1995), S. 273-297 
    ISSN: 0885-6125
    Schlagwort(e): pattern recognition ; efficient learning algorithms ; neural networks ; radial basis function classifiers ; polynomial classifiers
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract The support-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data. High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 63
    Digitale Medien
    Digitale Medien
    Springer
    Machine learning 33 (1998), S. 5-39 
    ISSN: 0885-6125
    Schlagwort(e): regression estimation ; prequential model selection ; cross-validation ; neural networks ; rates of convergence ; mixture regression ; integrated mean-squared error ; time-averaged expected prediction error
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract Prequential model selection and delete-one cross-validation are data-driven methodologies for choosing between rival models on the basis of their predictive abilities. For a given set of observations, the predictive ability of a model is measured by the model's accumulated prediction error and by the model's average-out-of-sample prediction error, respectively, for prequential model selection and for cross-validation. In this paper, given i.i.d. observations, we propose nonparametric regression estimators—based on neural networks—that select the number of “hidden units” (or “neurons”) using either prequential model selection or delete-one cross-validation. As our main contributions: (i) we establish rates of convergence for the integrated mean-squared errors in estimating the regression function using “off-line” or “batch” versions of the proposed estimators and (ii) we establish rates of convergence for the time-averaged expected prediction errors in using “on-line” versions of the proposed estimators. We also present computer simulations (i) empirically validating the proposed estimators and (ii) empirically comparing the proposed estimators with certain novel prequential and cross-validated “mixture” regression estimators.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 64
    Digitale Medien
    Digitale Medien
    Springer
    Machine learning 20 (1995), S. 273-297 
    ISSN: 0885-6125
    Schlagwort(e): pattern recognition ; efficient learning algorithms ; neural networks ; radial basis function classifiers ; polynomial classifiers
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract Thesupport-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data. High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 65
    Digitale Medien
    Digitale Medien
    Springer
    Machine learning 22 (1996), S. 251-281 
    ISSN: 0885-6125
    Schlagwort(e): Reinforcement learning ; advice-giving ; neural networks ; Q-learning ; learning from instruction ; theory refinement ; knowledge-based neural networks ; adaptive agents
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract Learning from reinforcements is a promising approach for creating intelligent agents. However, reinforcement learning usually requires a large number of training episodes. We present and evaluate a design that addresses this shortcoming by allowing a connectionist Q-learner to accept advice given, at any time and in a natural manner, by an external observer. In our approach, the advice-giver watches the learner and occasionally makes suggestions, expressed as instructions in a simple imperative programming language. Based on techniques from knowledge-based neural networks, we insert these programs directly into the agent‘s utility function. Subsequent reinforcement learning further integrates and refines the advice. We present empirical evidence that investigates several aspects of our approach and shows that, given good advice, a learner can achieve statistically significant gains in expected reward. A second experiment shows that advice improves the expected reward regardless of the stage of training at which it is given, while another study demonstrates that subsequent advice can result in further gains in reward. Finally, we present experimental results that indicate our method is more powerful than a naive technique for making use of advice.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 66
    Digitale Medien
    Digitale Medien
    Springer
    Machine learning 37 (1999), S. 183-233 
    ISSN: 0885-6125
    Schlagwort(e): graphical models ; Bayesian networks ; belief networks ; probabilistic inference ; approximate inference ; variational methods ; mean field methods ; hidden Markov models ; Boltzmann machines ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract This paper presents a tutorial introduction to the use of variational methods for inference and learning in graphical models (Bayesian networks and Markov random fields). We present a number of examples of graphical models, including the QMR-DT database, the sigmoid belief network, the Boltzmann machine, and several variants of hidden Markov models, in which it is infeasible to run exact inference algorithms. We then introduce variational methods, which exploit laws of large numbers to transform the original graphical model into a simplified graphical model in which inference is efficient. Inference in the simpified model provides bounds on probabilities of interest in the original model. We describe a general framework for generating variational transformations based on convex duality. Finally we return to the examples and demonstrate how variational algorithms can be formulated in each case.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 67
    ISSN: 0885-6125
    Schlagwort(e): neural networks ; database search ; protein classification ; sequence analysis ; superfamily ; singular value decomposition (SVD)
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract A neural network classification method has been developed as an alternative approach to the search/organization problem of protein sequence databases. The neural networks used are three-layered, feed-forward, back-propagation networks. The protein sequences are encoded into neural input vectors by a hashing method that counts occurrences ofn-gram words. A new SVD (singular value decomposition) method, which compresses the long and sparsen-gram input vectors and captures semantics ofn-gram words, has improved the generalization capability of the network. A full-scale protein classification system has been implemented on a Cray supercomputer to classify unknown sequences into 3311 PIR (Protein Identification Resource) superfamilies/families at a speed of less than 0.05 CPU second per sequence. The sensitivity is close to 90% overall, and approaches 100% for large superfamilies. The system could be used to reduce the database search time and is being used to help organize the PIR protein sequence database.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 68
    Digitale Medien
    Digitale Medien
    Springer
    Machine learning 32 (1998), S. 179-201 
    ISSN: 0885-6125
    Schlagwort(e): neural networks ; concept learning ; online algorithms ; variational optimization
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract We review the application of statistical mechanics methods to the study of online learning of a drifting concept in the limit of large systems. The model where a feed-forward network learns from examples generated by a time dependent teacher of the same architecture is analyzed. The best possible generalization ability is determined exactly, through the use of a variational method. The constructive variational method also suggests a learning algorithm. It depends, however, on some unavailable quantities, such as the present performance of the student. The construction of estimators for these quantities permits the implementation of a very effective, highly adaptive algorithm. Several other algorithms are also studied for comparison with the optimal bound and the adaptive algorithm, for different types of time evolution of the rule.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 69
    Digitale Medien
    Digitale Medien
    Springer
    Machine learning 37 (1999), S. 131-141 
    ISSN: 0885-6125
    Schlagwort(e): neural networks ; read-once formulas ; threshold gates ; sigmoidal gates ; PAC learning ; Vapnik-Chervonenkis dimension
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract A neural network is said to be nonoverlapping if there is at most one edge outgoing from each node. We investigate the number of examples that a learning algorithm needs when using nonoverlapping neural networks as hypotheses. We derive bounds for this sample complexity in terms of the Vapnik-Chervonenkis dimension. In particular, we consider networks consisting of threshold, sigmoidal and linear gates. We show that the class of nonoverlapping threshold networks and the class of nonoverlapping sigmoidal networks on n inputs both have Vapnik-Chervonenkis dimension Ω(nlog n). This bound is asymptotically tight for the class of nonoverlapping threshold networks. We also present an upper bound for this class where the constants involved are considerably smaller than in a previous calculation. Finally, we argue that the Vapnik-Chervonenkis dimension of nonoverlapping threshold or sigmoidal networks cannot become larger by allowing the nodes to compute linear functions. This sheds some light on a recent result that exhibited neural networks with quadratic Vapnik-Chervonenkis dimension.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 70
    ISSN: 0885-6125
    Schlagwort(e): robot control ; neural networks ; uncertainty compensation ; stability and performance
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract In this article, an approach to improving the performance of robot continuous-path operation is proposed. This approach utilizes a multilayer feedforward neural network to compensate for model uncertainty associated with the robotic operation. Closed-loop stability and performance are analyzed. It is shown that the closed-loop system is stable in the sense that all signals are bounded: it is further proved that the performance of the closed-loop system is improved in the sense that certain error measure of the closed-loop system decreases as the network learning process is iterated. These analytical results are confirmed by computer simulation. The effectiveness of the proposed approach is demonstrated through a laboratory experiment.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 71
    Digitale Medien
    Digitale Medien
    Springer
    Machine learning 31 (1998), S. 201-222 
    ISSN: 0885-6125
    Schlagwort(e): mobile robots ; neural networks ; machine vision ; robot learning
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract This paper presents the design, implementation and evaluation of a trainable vision guided mobile robot. The robot, CORGI, has a CCD camera as its only sensor which it is trained to use for a variety of tasks. The techniques used for train ing and the choice of natural light vision as the primary sensor makes the methodology immediately applicable to tasks such as trash collection or fruit picking. For example, the robot is readily trained to perform a ball finding task which involves avoiding obstacles and aligning with tennis balls. The robot is able to move at speeds up to 0.8 ms-1 while performing this task, and has never had a collision in the trained environment. It can process video and update the actuators at 11 Hz using a single $20 microprocessor to perform all computation. Further results are shown to evaluate the system for generalization across unseen domains, fault tolerance and dynamic environments.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 72
    Digitale Medien
    Digitale Medien
    Springer
    Machine learning 31 (1998), S. 7-27 
    ISSN: 0885-6125
    Schlagwort(e): robot learning ; concept learning ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract Concept learning in robotics is an extremely challenging problem: sensory data is often high-dimensional, and noisy due to specularities and other irregularities. In this paper, we investigate two general strategies to speed up learning, based on spatial decomposition of the sensory representation, and simultaneous learning of multiple classes using a shared structure. We study two concept learning scenarios: a hallway navigation problem, where the robot has to induce features such as “opening” or “wall”. The second task is recycling, where the robot has to learn to recognize objects, such as a “trash can”. We use a common underlying function approximator in both studies in the form of a feedforward neural network, with several hundred input units and multiple output units. Despite the high degree of freedom afforded by such an approximator, we show the two strategies provide sufficient bias to achieve rapid learning. We provide detailed experimental studies on an actual mobile robot called PAVLOV to illustrate the effectiveness of this approach.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 73
    ISSN: 0885-6125
    Schlagwort(e): neural networks ; database search ; protein classification ; sequence analysis ; superfamily ; singular value decomposition (SVD)
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract A neural network classification method has been developed as an alternative approach to the search/organization problem of protein sequence databases. The neural networks used are three-layered, feed-forward, back-propagation networks. The protein sequences are encoded into neural input vectors by a hashing method that counts occurrences of n-gram words. A new SVD (singular value decomposition) method, which compresses the long and sparse n-gram input vectors and captures semantics of n-gram words, has improved the generalization capability of the network. A full-scale protein classification system has been implemented on a Cray supercomputer to classify unknown sequences into 3311 PIR (Protein Identification Resource) superfamilies/families at a speed of less than 0.05 CPU second per sequence. The sensitivity is close to 90% overall, and approaches 100% for large superfamilies. The system could be used to reduce the database search time and is being used to help organize the PIR protein sequence database.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 74
    Digitale Medien
    Digitale Medien
    Springer
    Machine learning 22 (1996), S. 251-281 
    ISSN: 0885-6125
    Schlagwort(e): Reinforcement learning ; advice-giving ; neural networks ; Q-learning ; learning from instruction ; theory refinement ; knowledge-based neural networks ; adaptive agents
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract Learning from reinforcements is a promising approach for creating intelligent agents. However, reinforcement learning usually requires a large number of training episodes. We present and evaluate a design that addresses this shortcoming by allowing a connectionist Q-learner to accept advice given, at any time and in a natural manner, by an external observer. In our approach, the advice-giver watches the learner and occasionally makes suggestions, expressed as instructions in a simple imperative programming language. Based on techniques from knowledge-based neural networks, we insert these programs directly into the agent's utility function. Subsequent reinforcement learning further integrates and refines the advice. We present empirical evidence that investigates several aspects of our approach and shows that, given good advice, a learner can achieve statistically significant gains in expected reward. A second experiment shows that advice improves the expected reward regardless of the stage of training at which it is given, while another study demonstrates that subsequent advice can result in further gains in reward. Finally, we present experimental results that indicate our method is more powerful than a naive technique for making use of advice.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 75
    Digitale Medien
    Digitale Medien
    Springer
    Soft computing 1 (1997), S. 6-18 
    ISSN: 1433-7479
    Schlagwort(e): Keywords Soft computing ; hybrid systems ; fuzzy systems ; neural networks ; evolutionary systems
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract  The term Soft Computing (SC) represents the combination of emerging problem-solving technologies such as Fuzzy Logic (FL), Probabilistic Reasoning (PR), Neural Networks (NNs), and Genetic Algorithms (GAs). Each of these technologies provide us with complementary reasoning and searching methods to solve complex, real-world problems. After a brief description of each of these technologies, we will analyze some of their most useful combinations, such as the use of FL to control GAs and NNs parameters; the application of GAs to evolve NNs (topologies or weights) or to tune FL controllers; and the implementation of FL controllers as NNs tuned by backpropagation-type algorithms.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 76
    Digitale Medien
    Digitale Medien
    Springer
    Journal of industrial microbiology and biotechnology 15 (1995), S. 401-406 
    ISSN: 1476-5535
    Schlagwort(e): neural networks ; predictive control ; beer fermentation ; ethyl caproate
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Biologie , Werkstoffwissenschaften, Fertigungsverfahren, Fertigung
    Notizen: Abstract The biochemical pathways involved in the production of ethyl caproate, a secondary product of the beer fermentation process, are not well established. Hence, there are no phenomenological models available to control and predict the production of this particular compound as with other related products. In this work, neural networks have been used to fit experimental results with constant and variable pH, giving a good fit of laboratory and industrial scale data. The results at constant pH were also used to predict results at variable pH. Finally, the application of neural networks obtained from laboratory experiments gave excellent predictions of results in industrial breweries and so could be used in the control of industrial operations. The input pattern to the neural network included the accumulated fermentation time, cell dry weight, consumption of sugars and aminoacids and, in some cases, the pH. The output from the neural network was an estimation of quantity of the ethyl caproate ester.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 77
    Digitale Medien
    Digitale Medien
    Springer
    Molecular engineering 5 (1995), S. 229-233 
    ISSN: 1572-8951
    Schlagwort(e): Molecular similarity ; mimetics ; neural networks ; eudismic ratios
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Chemie und Pharmazie
    Notizen: Abstract Molecular similarity provides a quantitative measure of the resemblance of molecules. It is of use in the design of mimetics and in finding relationships between biological activity and molecular properties which incorporate three-dimensional features. Dissimilarity between enantiomeric forms can rationalize the relative potencies of optical isomers.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 78
    Digitale Medien
    Digitale Medien
    Springer
    Applied mathematics and mechanics 19 (1998), S. 457-462 
    ISSN: 1573-2754
    Schlagwort(e): neural networks ; equilibrium ; stability
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau , Mathematik , Physik
    Notizen: Abstract In this paper, some sufficient conditions are obtained for the global asymptotic stability of the equilibrium of neural networks with interneuronal transmission delays of the type $$x'_i (t) = - b_i x_i (t) + \sum\limits_{j = 1}^n {\omega _{\ddot y} f_j (x_j (t - \tau _j )) + p_i (t 〉 0;i = 1,2, \cdots ,n)} $$
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 79
    Digitale Medien
    Digitale Medien
    Springer
    Applied mathematics and mechanics 20 (1999), S. 721-728 
    ISSN: 1573-2754
    Schlagwort(e): Saint-Venant's principle ; variational principles ; neural networks ; computational stock market ; F224.9
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Maschinenbau , Mathematik , Physik
    Notizen: Abstract In this paper, three basic principles for computational stock market are proposed namely, “the Nearest-Time Principle” (NTP), “the Following Tendency Principle” (FTP), and “the Variational Principle on Difference of Supply and Demand” (VPDSD). The issue, expression, mathematical description and applications of these principles are stated. These applications involve the use in neural networks, basic equations of computational stock market, and the prediction of equilibrium price of stocks etc.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 80
    Digitale Medien
    Digitale Medien
    Springer
    Computational economics 10 (1997), S. 279-294 
    ISSN: 1572-9974
    Schlagwort(e): parallel distributed processing ; neural networks ; genetic algorithms.
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Wirtschaftswissenschaften
    Notizen: Abstract A description of a parallel implementation of the Genetic Algorithm for non-linear optimization is presented. The system is implemented with four Intel i860 RISC processors using INMOS transputers for communications. The performance is compared to the Cray Y-MP, Cray J916, an SGI Power Challenge L R8000 75 MHZ workstation, an SGI Challenge L R4400 100 MHZ work-station, an SGI Indy SC R4400 200 MHZ workstation, and both parastation and Paramid parallel I860 machines, each with one to four participating I860s. Comparisons were made for neural network optimization of a limited dependent variable problem and a chaotic time series. A complex rational expectations model was also estimated. The I860 based machines were able to achieve performances comparable to the supercomputers.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 81
    ISSN: 1573-4986
    Schlagwort(e): mucin type O-glycosylation ; specificity ; GalNAc transferase ; prediction ; neural networks ; gp120 ; SIV ; HIV
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Chemie und Pharmazie
    Notizen: Abstract The specificities of the UDP-GalNAc:polypeptide N-acetylgalactosaminyltransferases which link the carbohydrate GalNAc to the side-chain of certain serine and threonine residues in mucin type glycoproteins, are presently unknown. The specificity seems to be modulated by sequence context, secondary structure and surface accessibility. The sequence context of glycosylated threonines was found to differ from that of serine, and the sites were found to cluster. Non-clustered sites had a sequence context different from that of clustered sites. Charged residues were disfavoured at position – 1 and +3. A jury of artificial neural networks was trained to recognize the sequence context and surface accessibility of 299 known and verified mucin type O-glycosylation sites extracted from O-GLYCBASE. The cross-validated NetOglyc network system correctly found 83% of the glycosylated and 90% of the non-glycosylated serine and threonine residues in independent test sets, thus proving more accurate than matrix statistics and vector projection methods. Predictions of O-glycosylation sites in the envelope glycoprotein gp120 from the primate lentiviruses HIV-1, HIV-2 and SIV are presented. The most conserved O-glycosylation signals in these evolutionary-related glycoproteins were found in their first hypervariable loop, V1. However, the strain variation for HIV-1 gp120 was significant. A computer server, available through WWW or E-mail, has been developed for prediction of mucin type O-glycosylation sites in proteins based on the amino acid sequence. The server addresses are http://www.cbs.dtu.dk/services/NetOGlyc/ and netOglyc@cbs.dtu.dk.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 82
    Digitale Medien
    Digitale Medien
    Springer
    Artificial intelligence review 10 (1996), S. 299-319 
    ISSN: 1573-7462
    Schlagwort(e): multimodal interfaces ; speech recognition ; lip-reading ; gesture recognition ; handwriting recognition ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract In this paper, we present an overview of research in our laboratories on Multimodal Human Computer Interfaces. The goal for such interfaces is to free human computer interaction from the limitations and acceptance barriers due to rigid operating commands and keyboards as the only/main I/O-device. Instead we move to involve all available human communication modalities. These human modalities include Speech, Gesture and Pointing, Eye-Gaze, Lip Motion and Facial Expression, Handwriting, Face Recognition, Face Tracking, and Sound Localization.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 83
    Digitale Medien
    Digitale Medien
    Springer
    Artificial intelligence review 12 (1998), S. 163-176 
    ISSN: 1573-7462
    Schlagwort(e): color computer vision ; neural networks ; machine vision ; egg grading ; blood spots ; dirt stains ; cracks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract A blood spot detection neural network was trained, tested, and evaluated entirely on eggs with blood spots and grade A eggs. The neural network could accurately distinguish between grade A eggs and blood spot eggs. However, when eggs with other defects were included in the sample, the accuracy of the neural network was reduced. The accuracy was also reduced when evaluating eggs from other poultry houses. To minimize these sensitivities, eggs with cracks and dirt stains were included in the training data as examples of eggs without blood spots. The training data also combined eggs from different sources. Similar inaccuracies were observed in neural networks for crack detection and dirt stain detection. New neural networks were developed for these defects using the method applied for the blood spot neural network development. The neural network model for blood spot detection had an average accuracy of 92.8%. The neural network model for dirt stained eggs had an average accuracy of 85.0%. The average accuracy of the crack detection neural network was 87.8%. These accuracy levels were sufficient to produce graded samples that would exceed the USDA requirements.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 84
    Digitale Medien
    Digitale Medien
    Springer
    Applied intelligence 11 (1999), S. 5-13 
    ISSN: 1573-7497
    Schlagwort(e): neural networks ; knowledge representation ; structured knowledge reasoning ; connectionism ; symbol processing ; hybrid systems
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract This collection of articles is the first of two parts of a special issue on “Neural Networks and Structured Knowledge.” The contributions to the first part shed some light on the issues of knowledge representation and reasoning with neural networks. Their scope ranges from formal models for mapping discrete structures like graphs or logical formulae onto different types of neural networks, to the construction of practical systems for various types of reasoning. In the second part to follow, the emphasis will be on the extraction of knowledge from neural networks, and on applications of neural networks and structured knowledge to practical tasks.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 85
    Digitale Medien
    Digitale Medien
    Springer
    Applied intelligence 11 (1999), S. 15-30 
    ISSN: 1573-7497
    Schlagwort(e): neural networks ; structured objects ; machine learning ; classification ; similarity ; nearest neighbor
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract Labeled graphs are an appropriate and popular representation of structured objects in many domains. If the labels describe the properties of real world objects and their relations, finding the best match between two graphs turns out to be the weakly defined, NP-complete task of establishing a mapping between them that maps similar parts onto each other preserving as much as possible of their overall structural correspondence. In this paper, former approaches of structural matching and constraint relaxation by spreading activation in neural networks and the method of solving optimization tasks using Hopfield-style nets are combined. The approximate matching task is reformulated as the minimization of a quadratic energy function. The design of the approach enables the user to change the parameters and the dynamics of the net so that knowledge about matching preferences is included easily and transparently. In the last section, some examples demonstrate the successful application of this approach in classification and learning in the domain of organic chemistry.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 86
    Digitale Medien
    Digitale Medien
    Springer
    Information retrieval 1 (1999), S. 193-216 
    ISSN: 1573-7659
    Schlagwort(e): information retrieval ; text mining ; topic spotting ; text categorization ; knowledge management ; problem decomposition ; machine learning ; neural networks ; probabilistic models ; hierarchical models ; performance evaluation
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract With the recent dramatic increase in electronic access to documents, text categorization—the task of assigning topics to a given document—has moved to the center of the information sciences and knowledge management. This article uses the structure that is present in the semantic space of topics in order to improve performance in text categorization: according to their meaning, topics can be grouped together into “meta-topics”, e.g., gold, silver, and copper are all metals. The proposed architecture matches the hierarchical structure of the topic space, as opposed to a flat model that ignores the structure. It accommodates both single and multiple topic assignments for each document. Its probabilistic interpretation allows its predictions to be combined in a principled way with information from other sources. The first level of the architecture predicts the probabilities of the meta-topic groups. This allows the individual models for each topic on the second level to focus on finer discriminations within the group. Evaluating the performance of a two-level implementation on the Reuters-22173 testbed of newswire articles shows the most significant improvement for rare classes.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 87
    Digitale Medien
    Digitale Medien
    Springer
    Neural processing letters 3 (1996), S. 139-149 
    ISSN: 1573-773X
    Schlagwort(e): Steiner tree ; neural networks ; Hopfield model ; optimization
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract Hopfield neural network model for finding the shortest path between two nodes in a graph was proposed recently in some literatures. In this paper, we present a modified version of Hopfield model to a more general problem of searching an optimal tree (least total cost tree) from a source node to a number of destination nodes in a graph. This problem is called Steiner tree in graph theory, where it is proved to be a NP-complete. Through computer simulations, it is shown that the proposed model could always find an optimal or near-optimal valid solution in various graphs.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 88
    Digitale Medien
    Digitale Medien
    Springer
    Neural processing letters 4 (1996), S. 149-155 
    ISSN: 1573-773X
    Schlagwort(e): adaptation ; diploidy ; genetic algorithms ; genotype-phenotype mapping ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract In nature the genotype of many organisms exhibits diploidy, i.e., it includes two copies of every gene. In this paper we describe the results of simulations comparing the behavior of haploid and diploid populations of ecological neural networks living in both fixed and changing environments. We show that diploid genotypes create more variability in fitness in the population than haploid genotypes and buffer better environmental change; as a consequence, if one wants to obtain good results for both average and peak fitness in a single population one should choose a diploid population with an appropriate mutation rate. Some results of our simulations parallel biological findings.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 89
    Digitale Medien
    Digitale Medien
    Springer
    Neural processing letters 5 (1997), S. 83-89 
    ISSN: 1573-773X
    Schlagwort(e): finite element method ; Kohonen ; neural networks ; self-organizing ; topological mapping
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract The usual “Kohonen” algorithm uses samples of points in a domain to develop a topological correspondence between a grid of “neurons” and a continuous domain. “Topological” means that near points are mapped to near points. However, for many applications there are additional constraints, which are given by sets of measure zero, which are not preserved by this method, because of insufficient sampling. In particular, boundary points do not typically map to boundary points because in general the likelihood of a sample point from a two-dimensional domain falling on the boundary is typically zero for continuous data, and extremely small for numerical data. A specific application, (assigning meshes for the finite element method), was recently solved by interweaving a two-dimensional Kohonen mapping on the entire grid with a one-dimensional Kohonen mapping on the boundary. While the precise method of interweaving was heuristic, the underlying rationale seems widely applicable. This general method is problem independent and suggests a direct generalization to higher dimensions as well.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 90
    ISSN: 1573-7462
    Schlagwort(e): CancerLit ; concept spaces ; data mining ; Hopfield net ; information retrieval ; Kohonen net ; medical knowledge ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract This paper discusses several data mining algorithms and techniques thatwe have developed at the University of Arizona Artificial Intelligence Lab.We have implemented these algorithms and techniques into severalprototypes, one of which focuses on medical information developed incooperation with the National Cancer Institute (NCI) and the University ofIllinois at Urbana-Champaign. We propose an architecture for medicalknowledge information systems that will permit data mining across severalmedical information sources and discuss a suite of data mining tools that weare developing to assist NCI in improving public access to and use of theirexisting vast cancer information collections.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 91
    Digitale Medien
    Digitale Medien
    Springer
    Artificial intelligence review 9 (1995), S. 361-385 
    ISSN: 1573-7462
    Schlagwort(e): legal decision support systems ; deduction ; rule based reasoning ; induction ; analogy ; case based reasoning ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract In this paper we discuss the strengths and weaknesses of a range of artificial intelligence approaches used in legal domains. Symbolic reasoning systems which rely on deductive, inductive and analogical reasoning are described and reviewed. The role of statistical reasoning in law is examined, and the use of neural networks analysed. There is discussion of architectures for, and examples of, systems which combine a number of these reasoning strategies. We conclude that to build intelligent legal decision support systems requires a range of reasoning strategies.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 92
    Digitale Medien
    Digitale Medien
    Springer
    Annals of software engineering 1 (1995), S. 141-154 
    ISSN: 1573-7489
    Schlagwort(e): Software complexity metrics ; software quality ; regression analysis ; neural networks ; program faults ; model quality of fit ; model predictive quality ; average relative error
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract Accurately predicting the number of faults in program modules is a major problem in the quality control of large software development efforts. Some software complexity metrics are closely related to the distribution of faults across program modules. Using these relationships, software engineers develop models that provide early estimates of quality metrics that do not become available until late in the development cycle. By considering these early estimates, software engineers can take actions to avoid or prepare for emerging quality problems. Most often, the predictive models are based upon multiple regression analysis. However, measures of software quality and complexity exhibit systematic departures from the assumptions of these analyses. With extreme violations of these assumptions, multiple regression models become unstable and lose most of their predictive quality. Since neural network models carry no data assumptions, these models could be more appropriate than regression models for modeling software faults. In this paper, we explore a neural network methodology for developing models that predict the number of faults in program modules. We apply this methodology to develop neural network models based upon data collected during the development of two commercial software systems. After developing neural network models, we apply multiple linear regression methods to develop regression models on the same data. For the data sets considered, the neural network methodology produced better predictive models in terms of both quality of fit and predictive quality.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 93
    Digitale Medien
    Digitale Medien
    Springer
    Applied intelligence 11 (1999), S. 109-127 
    ISSN: 1573-7497
    Schlagwort(e): hybrid models ; sequential decision making ; neural networks ; reinforcement learning ; cognitive modeling
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract In developing autonomous agents, one usually emphasizes only (situated) procedural knowledge, ignoring more explicit declarative knowledge. On the other hand, in developing symbolic reasoning models, one usually emphasizes only declarative knowledge, ignoring procedural knowledge. In contrast, we have developed a learning model CLARION, which is a hybrid connectionist model consisting of both localist and distributed representations, based on the two-level approach proposed in [40]. CLARION learns and utilizes both procedural and declarative knowledge, tapping into the synergy of the two types of processes, and enables an agent to learn in situated contexts and generalize resulting knowledge to different scenarios. It unifies connectionist, reinforcement, and symbolic learning in a synergistic way, to perform on-line, bottom-up learning. This summary paper presents one version of the architecture and some results of the experiments.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 94
    Digitale Medien
    Digitale Medien
    Springer
    Applied intelligence 11 (1999), S. 169-186 
    ISSN: 1573-7497
    Schlagwort(e): neural networks ; multiple fault diagnosis ; analog circuits
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract This paper presents a neural network system for the diagnosis of analog circuits and shows how the performance of such a system can be affected by the choice of different techniques used by its submodules. In particular we discuss the influence of feature extraction techniques such as Fourier Transforms, Wavelets and Principal Component Analysis. The system uses several different power supplies and as many neural networks “in parallel”. Two different algorithms that can be used to combine the candidate sets produced by each network are also presented. The system is capable of diagnosing multiple faults even if trained on single ones.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 95
    Digitale Medien
    Digitale Medien
    Springer
    Applied intelligence 10 (1999), S. 71-84 
    ISSN: 1573-7497
    Schlagwort(e): encryption ; chaotic attractors ; neural networks ; symmetric-key
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract A new probabilistic symmetric-key encryption scheme based on chaotic-classified properties of Hopfield neural networks is described. In an overstoraged Hopfield Neural Network (OHNN) the phenomenon of chaotic-attractors is well documented and messages in the attraction domain of an attractor are unpredictably related to each other. By performing permutation operations on the neural synaptic matrix, several interesting chaotic-classified properties of OHNN were found and these were exploited in developing a new cryptography technique. By keeping the permutation operation of the neural synaptic matrix as the secret key, we introduce a new probabilistic encryption scheme for a symmetric-key cryptosystem. Security and encryption efficiency of the new scheme are discussed.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 96
    Digitale Medien
    Digitale Medien
    Springer
    Information retrieval 1 (1999), S. 151-173 
    ISSN: 1573-7659
    Schlagwort(e): linear combination ; fusion ; neural networks ; routing ; performance evaluation
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract We present a thorough analysis of the capabilities of the linear combination (LC) model for fusion of information retrieval systems. The LC model combines the results lists of multiple IR systems by scoring each document using a weighted sum of the scores from each of the component systems. We first present both empirical and analytical justification for the hypotheses that such a model should only be used when the systems involved have high performance, a large overlap of relevant documents, and a small overlap of nonrelevant documents. The empirical approach allows us to very accurately predict the performance of a combined system. We also derive a formula for a theoretically optimal weighting scheme for combining 2 systems. We introduce d—the difference between the average score on relevant documents and the average score on nonrelevant documents—as a performance measure which not only allows mathematical reasoning about system performance, but also allows the selection of weights which generalize well to new documents. We describe a number of experiments involving large numbers of different IR systems which support these findings.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 97
    Digitale Medien
    Digitale Medien
    Springer
    Neural processing letters 6 (1997), S. 99-108 
    ISSN: 1573-773X
    Schlagwort(e): identification ; Lipschitz constant ; neural networks
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract This paper describes a method to estimate the Lipschitz gain of an operator through identification with neural networks. It is shown that through simple manipulation of the network coefficients, the Lipschitz constant could be estimated. Illustrations and applications are also given to show the effectiveness and usefulness of this estimation scheme.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 98
    Digitale Medien
    Digitale Medien
    Springer
    Neural processing letters 7 (1998), S. 61-68 
    ISSN: 1573-773X
    Schlagwort(e): blind source separation ; higher-order statistics ; neural networks ; unsupervised learning
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract We present a new learning algorithm for the blind separation of independent source signals having non-zero skewness (the 3rd-order cumulant) (the source signals have non-symmetric probability distribution.), from their linear mixtures. It is shown that for a class of source signals whose probability distribution functions is not symmetric, a simple adaptive learning algorithm using quadratic function (f(x)=x2) is very efficient for blind source separation task. It is proved that all stable equilibria of the proposed learning algorithm are desirable solutions. Extensive computer simulation experiments confirmed the validity of the proposed algorithm.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 99
    Digitale Medien
    Digitale Medien
    Springer
    Neural processing letters 7 (1998), S. 211-219 
    ISSN: 1573-773X
    Schlagwort(e): backpropagation ; feature selection ; logical rule extraction ; MLP ; neural networks ; probability density estimation
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract Three neural-based methods for extraction of logical rules from data are presented. These methods facilitate conversion of graded response neural networks into networks performing logical functions. MLP2LN method tries to convert a standard MLP into a network performing logical operations (LN). C-MLP2LN is a constructive algorithm creating such MLP networks. Logical interpretation is assured by adding constraints to the cost function, forcing the weights to ±1 or 0. Skeletal networks emerge ensuring that a minimal number of logical rules are found. In both methods rules covering many training examples are generated before more specific rules covering exceptions. The third method, FSM2LN, is based on the probability density estimation. Several examples of performance of these methods are presented.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 100
    Digitale Medien
    Digitale Medien
    Springer
    Neural processing letters 8 (1998), S. 15-26 
    ISSN: 1573-773X
    Schlagwort(e): neural networks ; constraints satisfaction ; assignment problems ; 0/1 linear programming
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract This paper investigates an industrial assignment problem. It is modelized as a constraint satisfaction problem of large size with linear inequalities and binary variables. A new analog neuron-like network is proposed to find out feasible solutions to problems having several thousands of 0/1 variables. The approach developed in this paper is based on mixed-penalty functions: exterior penalty functions together with interior penalty functions. Starting from a near-binary solution satisfying each linear inequality, the network generates trial solutions located outside or inside the feasible set, in order to minimize an energy function which measures the total binary infeasibility of the system. The performances of the network are demonstrated on real data sets.
    Materialart: Digitale Medien
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
Schließen ⊗
Diese Webseite nutzt Cookies und das Analyse-Tool Matomo. Weitere Informationen finden Sie hier...