ALBERT

All Library Books, journals and Electronic Records Telegrafenberg

X
feed icon rss

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
Filter
  • Articles  (52)
  • Articles: DFG German National Licenses  (52)
  • Neural networks  (52)
  • 1995-1999  (52)
  • Computer Science  (52)
  • Process Engineering, Biotechnology, Nutrition Technology
  • 1
    Electronic Resource
    Electronic Resource
    Committees, collectives and individuals: Expert visual classification by neural network (1997)
    Springer
    Neural computing & applications 5 (1997), S. 99-105 
    Details
    ISSN: 1433-3058
    Keywords: Neural networks ; Taxonomic expertise ; Committee classification
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract It has been established that committee classifiers, in which the outputs of different, individual network classifiers are combined in various ways, can produce better accuracy than the best individual in the committee. We describe results showing that these advantages are obtained when neural networks are applied to a taxonomic problem in marine science: the classification of images of marine phytoplankton. Significant benefits were found when individual networks, trained on different classes of input, having comparable individual performances, were combined. Combining networks of very different accuracy did not improve performance when measured against the best single network, but nor was it reduced. An alternative architecture, which we term a collective machine, in which the different data types are combined in a single network, was found to have significantly better accuracy than the committee machine architectures. The performance gains and resilience to non-discriminatory types of data suggest the techniques have great utility in the development of general purpose, network classifiers.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01501174
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 2
    Electronic Resource
    Electronic Resource
    Representing Probabilistic Rules with Networks of Gaussian Basis Functions (1997)
    Springer
    Machine learning 27 (1997), S. 173-200 
    Details
    ISSN: 0885-6125
    Keywords: Neural networks ; theory refinement ; knowledge-based neural networks ; probability density estimation ; knowledge extraction ; mixture densities ; combining knowledge bases ; Bayesian learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract There is great interest in understanding the intrinsic knowledge neural networks have acquired during training. Most work in this direction is focussed on the multi-layer perceptron architecture. The topic of this paper is networks of Gaussian basis functions which are used extensively as learning systems in neural computation. We show that networks of Gaussian basis functions can be generated from simple probabilistic rules. Also, if appropriate learning rules are used, probabilistic rules can be extracted from trained networks. We present methods for the reduction of network complexity with the goal of obtaining concise and meaningful rules. We show how prior knowledge can be refined or supplemented using data by employing either a Bayesian approach, by a weighted combination of knowledge bases, or by generating artificial training data representing the prior knowledge. We validate our approach using a standard statistical data set.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007381408604
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 3
    Electronic Resource
    Electronic Resource
    Dealing with missing values in neural network-based diagnostic systems (1995)
    Springer
    Neural computing & applications 3 (1995), S. 73-77 
    Details
    ISSN: 1433-3058
    Keywords: Backpropagation ; Classification ; Decision support ; Neural networks ; Thyroid disease
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract Backpropagation neural networks have been applied to prediction and classification problems in many real world situations. However, a drawback of this type of neural network is that it requires a full set of input data, and real world data is seldom complete. We have investigated two ways of dealing with incomplete data — network reduction using multiple neural network classifiers, and value substitution using estimated values from predictor networks — and compared their performance with an induction method. On a thyroid disease database collected in a clinical situation, we found that the network reduction method was superior. We conclude that network reduction can be a useful method for dealing with missing values in diagnostic systems based on backpropagation neural networks.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01421959
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 4
    Electronic Resource
    Electronic Resource
    Automated fuzzy knowledge acquisition with connectionist adaptation (1996)
    Springer
    Neural computing & applications 4 (1996), S. 27-34 
    Details
    ISSN: 1433-3058
    Keywords: Fuzzy logic ; Genetic algorithms ; Knowledge acquisition ; Learning ; Neural networks ; Optimisation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract This paper presents an automated knowledge acquisition architecture for the truck docking problem. The architecture consists of a neural network block, a fuzzy rule generation block and a genetic optimisation block. The neural network block is used to quickly and adaptively learn from trials the driving knowledge. The fuzzy rule generation block then extracts the driving knowledge to form a knowledge rule base. The driving knowledge rule base is further optimised in the genetic optimisation block using a genetic algorithm. Computer simulations are presented to show the effectiveness of the architecture.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413867
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 5
    Electronic Resource
    Electronic Resource
    Neuro-Resistive Grid approach to trainable controllers: A pole balancing example (1997)
    Springer
    Neural computing & applications 5 (1997), S. 33-44 
    Details
    ISSN: 1433-3058
    Keywords: Inverted pendulum problem ; Reinforcement learning ; Learning control ; Nonlinear control ; Neural networks ; Neuro-resistive grid method ; Value map
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract A new neural network approach is described for the task of pole-balancing, considered a benchmark learning control problem. This approach combines Barto, Sutton and Anderson's [1] Associative Search Element (ASE) with a Neuro-Resistive Grid (NRG) [2] acting as Adaptive Critic Element (ACE). The novel feature in NRG is that it provides evaluation of a state based on propagation of the failure information to the neighbours in the grid. NRG is updated only on a failure, and provides ASE with a continuous internal reinforcement signal by comparing the value of the present state to the previous state. The resulting system learns more rapidly and with fewer computations than that of Barto et al.[1]. To establish a uniform basis of comparison of algorithms for pole balancing, both the systems are simulated using benchmark parameters and tests specified in Geva and Sitte [3].
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01414101
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 6
    Electronic Resource
    Electronic Resource
    Neural networks applied to ultrasonic tomographic image reconstruction (1997)
    Springer
    Neural computing & applications 5 (1997), S. 106-123 
    Details
    ISSN: 1433-3058
    Keywords: Image reconstruction ; Neural networks ; Ultrasonic tomography ; Polymer composites
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract A neural network system has been developed which can reconstruct images of defects within fibre reinforced polymer composite samples. This paper discusses the problems associated with the image reconstruction of the ultrasonic data using neural networks, together with various methods adopted to improve the performance of the neural network system, including a modification to the error backpropagation algorithm.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01501175
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 7
    Electronic Resource
    Electronic Resource
    Classification of faults in gearboxes — pre-processing algorithms and neural networks (1997)
    Springer
    Neural computing & applications 5 (1997), S. 160-183 
    Details
    ISSN: 1433-3058
    Keywords: Fault detection ; Gearbox vibration ; Machinery diagnostics ; Neural networks ; Pattern recognition ; Pre-processing algorithms
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract Classical signal processing techniques when combined with pattern classification analysis can provide an automated fault detection procedure for machinery diagnostics. Artificial neural networks have recently been established as a powerful method of pattern recognition. The neural networkbased fault detection approach usually requires preprocessing algorithms which enhance the fault features, reducing their number at the same time. Various timeinvariant and timevariant signal preprocessing algorithms are studied here. These include spectral analysis, time domain averaging, envelope detection, Wigner-Ville distributions and wavelet transforms. A neural network pattern classifier with preprocessing algorithms is applied to experimental data in the form of vibration records taken from a controlled tooth fault in a pair of meshing spur gears. The results show that faults can be detected and classified without errors.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413861
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 8
    Electronic Resource
    Electronic Resource
    Deformation invariant visual object recognition: Experiments with a self-organising neural architecture (1997)
    Springer
    Neural computing & applications 6 (1997), S. 79-90 
    Details
    ISSN: 1433-3058
    Keywords: Computer vision ; Neural networks ; Object classification ; On-line training ; Pattern recognition ; Self-organisation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract A self-organising neural network architecture for grey-scale visual object rcognition is presented. The network is composed of three processing layers with an architecture designed to give deformation tolerance. The processing layers involve feature extraction, sub-pattern detection and classification. Training is generally performed on-line in an unsupervised manner, classes being created when objects are presented that cannot be classified. The results given show the effect of the two discrimination parameters when the network is applied to two very different sets of images, namely hand written numerals and hand gestures images. The sensitivity of the network to the parameters that govern the size of detectable patterns and the areas over which they are detected is also tested. The robustness of the network to the order of image presentation is also demonstrated. The results show that parameter choice is not critical and heuristically chosen parameters provide near optimum performance.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01414005
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 9
    Electronic Resource
    Electronic Resource
    Neural network models for breast cancer prognosis (1998)
    Springer
    Neural computing & applications 7 (1998), S. 367-375 
    Details
    ISSN: 1433-3058
    Keywords: Breast cancer ; Censoring ; Cox regression ; Neural networks ; Prognosis ; Survival
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract Estimating the risk of relapse for breast cancer patients is necessary, since it affects the choice of treatment. This problem involves analysing data of times to relapse of patients and relating them to prognostic variables. Some of the times to relapse will usually be censored.We investigate various ways of using neural network models to extend traditional statistical models in this situation. Such models are better able to model both non-linear effects of prognostic factors and interactions between them, than linear logistic or Cox regression models. With the dataset used in our study, however, the prediction of the risk of relapse is not significantly improved when using a neural network model. Predicting the risk that a patient will relapse within three years, say, is possible from this data, but not when any relapse will happen.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01428127
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 10
    Electronic Resource
    Electronic Resource
    Selective presentation learning for neural network forecasting of stock markets (1996)
    Springer
    Neural computing & applications 4 (1996), S. 143-148 
    Details
    ISSN: 1433-3058
    Keywords: Event-knowledge ; Forecasting ; Neural networks ; Selective presentation learning ; Stockprice prediction ; Stopping criterion
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract This paper proposes a selective presentation learning technique for improving the learnability and predictability of large changes by back-propagation neural networks. Daily stock prices are predicted as a complicated real-world problem, taking non-numerical factors such as political and international events into account. Training data corresponding to large changes of prediction-target time series are presented more often, and network learning is stopped at the point that has the maximal profit. When this technique is applied to daily stock-price prediction, the prediction error on large-change data was reduced by 11%, and the network's ability to make profits through experimental stock-trading was improved by 67% to 81%, in comparison with results obtained using conventional learning techniques.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01414874
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 11
    Electronic Resource
    Electronic Resource
    Predicting returns on Canadian exchange rates with artificial neural networks and EGARCH-M models (1996)
    Springer
    Neural computing & applications 4 (1996), S. 168-174 
    Details
    ISSN: 1433-3058
    Keywords: Backpropagation ; EGARCH-M ; Elman ; Exchange rates ; Neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract This paper investigates the problem of predicting daily returns based on five Canadian exchange rates using artificial neural networks and EGARCH-M models. First, the statistical properties of five daily exchange rate series (US Dollar, German Mark, French Franc, Japanese Yen and British Pound) are analysed. EGARCH-M models on the Generalised Error Distribution (GED) are fitted to the return series, and serve as comparison standards, along with random walk models. Second, backpropagation networks (BPN) using lagged returns as inputs are trained and tested. Estimated volatilities from the EGARCH-M models are used also as inputs to see if performance is affected. The question of spillovers in interrelated markets is investigated with networks of multiple inputs and outputs. In addition, Elman-type recurrent networks are also trained and tested. Comparison of the various methods suggests that, despite their simplicity, neural networks are similar to the EGARCH-M class of nonlinear models, but superior to random walk models, in terms of insample fit and out-of-sample prediction performance.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01414877
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 12
    Electronic Resource
    Electronic Resource
    Neural networks applied to a large biological database to analyse dairy breeding patterns (1996)
    Springer
    Neural computing & applications 4 (1996), S. 237-253 
    Details
    ISSN: 1433-3058
    Keywords: Cascade correlation ; Dairy breeding ; Neural networks ; Linear regression
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract The paper recounts the investigation of a dairy sire prediction capability based on Cascade Correlation neural networks to study influences relating the performance of offspring to their parents. The context of the problem is the artificial insemination breeding program for the Australian dairy industry. The networks are used to screen observed information in the database to relate it to best combinations of dam and sire. The voluminous data is quite noisy and is subject to genetic and environmental influences. The intention is to extract linear and nonlinear relationships from among the input variables without specifying their form. A number of scenarios are employed which recast the data into different forms. In particular, it was discovered that the problem could be restructured and the data supplemented with transformed data to produce succinct input patterns of manageable dimensionality, which allowed for a substantially improved predictive capability. It was then found that reasonable daughter predictions could be obtained of about 10%, as measured by her milk production. Results are compared with those obtained using two alternate neural network methods. Crude statistical methods are employed to evaluate the performance of the neural networks.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413822
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 13
    Electronic Resource
    Electronic Resource
    Application of neural network computing to thermal non-destructive evaluation (1997)
    Springer
    Neural computing & applications 6 (1997), S. 148-157 
    Details
    ISSN: 1433-3058
    Keywords: Bayesan interpretation ; Classification ; Neural networks ; Thermal Non-destructive evaluation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract A methodological study on the use of neural networks for defect characterisation by means of a thermal method is presented. Neural networks are used here as defect classifiers, based on the infrared emission of the target object after heating. In this kind of application, there is a high degree of uncertainty in defect class boundaries due to several factors, such as the noise in the measurement, the uneven heating of the target object and the anisotropies in its thermal conductivity. For this reason, the classical ‘1 of N’ coding scheme during training did not provide satisfactory results. Much better results have instead been obtained using a smoother activation function for the output units during training. The non-destructive evaluation of material using neural networks proved extremely satisfactory, especially when compared to the classical procedures of thermographic analysis.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413826
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 14
    Electronic Resource
    Electronic Resource
    Comparison of neural networks and statistical models to predict gestational age at birth (1997)
    Springer
    Neural computing & applications 6 (1997), S. 158-164 
    Details
    ISSN: 1433-3058
    Keywords: High risk pregnancy ; Logistic regression ; Neural networks ; Pre-term delivery ; Receiver Operating Characteristic curve
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract The aim of this study was to produce models for the prediction of high risk pregnancies, with particular emphasis on pre-term delivery. Neural network and logistic regression models have been developed utilising pregnancy and delivery data spanning a period of seven years. Five input factors were used as explanatory variables: age, number of previous still births, gestational age at first clinical assessment, diabetes and a measure of socio-economic status. There was little difference between average model performance for the two techniques: optimal neural network performance was achieved with a fully connected feed forward network comprising a single hidden layer of three nodes and single output node. This produced a Receiver Operating Characteristic (ROC) curve area of 0.700. The ROC area for logistic regression models was 0.695. The performance of these models reflected weak associations within the data. However, performance is encouraging given the relatively limited number of predictive inputs.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413827
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 15
    Electronic Resource
    Electronic Resource
    Self organising maps for the investigation of clinical data: A case study (1998)
    Springer
    Neural computing & applications 7 (1998), S. 65-70 
    Details
    ISSN: 1433-3058
    Keywords: Data visualisation ; Decision support ; Fracture ; Neural networks ; Osteoporosis ; Self-organising maps
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract The clinical process often involves comparisons of how one set of measurements is related to previous, similar, data and the use of this information to take decisions concerning possible courses of action, often with insufficient data to make meaningful calculations of probabilities. Self-organising maps are useful devices for data visualisation. To illustrate how visualisation with self-organising maps might be used in the clinical process, this paper describes the investigation of an osteoporosis data set using this technique. The data set had previously been used to show that backpropagation neural networks were capable of distinguishing between patients who had suffered a fracture, and those who had not using measured bone mineral density values; illustrating the power of these networks to model relationships in data. However, we had realised that this was somewhat of an academic exercise given that in reality a non-fracture case might be a fracture case waiting to happen. We felt it would be more productive to examine the data itself rather than model an imposed classification. As part of this investigation, the data set was examined using self-organising maps. From the results of the investigation, we conclude that it is possible to create a map, a compressed data representation, using BMD values which may then be partitioned into low and high fracture risk areas. Using such a map may be a useful screening mechanism for detecting people at risk of osteoporotic fracture.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413710
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 16
    Electronic Resource
    Electronic Resource
    A Multi-Output-Layer Perceptron (1996)
    Springer
    Neural computing & applications 4 (1996), S. 10-20 
    Details
    ISSN: 1433-3058
    Keywords: Constructive algorithms ; Multi-outputlayer perceptrons ; Neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract This paper investigates the possibility of improving the classification capability of single-layer and multilayer perceptrons by incorporating additional output layers. This Multi-Output-Layer Perceptron (MOLP) is a new type of constructive network, though the emphasis is on improving pattern separability rather than network efficiency. The MOLP is trained using the standard back-propagation (BP) algorithm. The studies are concentrated on realizations of arbitrary functions which map from an x-dimensional input MOLP, all problems existing in an original n-dimensional space in the hidden layer are transformed to a higher (n +1)-dimensional space, so that the possibility of linear separability is increased. Experimental investigations show that the classification ability of the MOLP is superior to that of an equivalent MLP. In general, this performance increase can be achieved with shorter training times and simpler network architectures.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413865
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 17
    Electronic Resource
    Electronic Resource
    Parallel 1D and 2D vector quantizers using a Kohonen neural network (1996)
    Springer
    Neural computing & applications 4 (1996), S. 64-71 
    Details
    ISSN: 1433-3058
    Keywords: Neural networks ; Vector quantizers ; Fast discrete cosine transform ; Adaptation algorithm ; Loosely coupled architecture ; Parallel processing
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract The process of reconstructing an original image from a compressed one is a difficult problem, since a large number of original images lead to the same compressed image and solutions to the inverse problem cannot be uniquely determined. Vector quantization is a compression technique that maps an input set of k-dimensional vectors into an output set of k-dimensional vectors, such that the selected output vector is closest to the input vector according to a selected distortion measure. In this paper, we show that adaptive 2D vector quantization of a fast discrete cosine transform of images using Kohonen neural networks outperforms other Kohonen vector quantizers in terms of quality (i.e. less distortion). A parallel implementation of the quantizer on a network of SUN Sparcstations is also presented.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413742
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 18
    Electronic Resource
    Electronic Resource
    Neural clustering networks based on global optimisation of prototypes in metric spaces (1997)
    Springer
    Neural computing & applications 5 (1997), S. 2-13 
    Details
    ISSN: 1433-3058
    Keywords: Global optimisation ; Clustering ; Unsupervised learning ; Neural networks ; Random optimisation ; EEG processing
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract The utilisation of clustering algorithms based on the optimisation of prototypes in neural networks is demonstrated for unsupervised learning. Stimulated by common clustering methods of this type (learning vector quantisation [LVQ, GLVQ] and K-means) a globally operating algorithm was developed to cope with known shortcomings of existing tools. This algorithm and K-means (for the common methods) were applied to the problem of clustering EEG patterns being pre-processed. It can be shown that the algorithm based on global random optimisation may find an optimal solution repeatedly, whereas K-means provides different sub-optimal solutions with respect to the quality measure defined as objective function. The results are presented. The performance of the algorithms is discussed.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01414098
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 19
    Electronic Resource
    Electronic Resource
    Neural simulation of acquired and progressive language disorders (1997)
    Springer
    Neural computing & applications 5 (1997), S. 215-223 
    Details
    ISSN: 1433-3058
    Keywords: Neural networks ; Cognitive modelling ; Language disorders ; Multi-network architectures ; Simulation of change ; Self-organisation ; LISA ; Complex systems
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract This paper describes a novel approach to the simulation of language disorders, based upon the notion of a multi-network architecture —a set of autonomous neural networks which have been linked in some manner to perform a complex function that cannot readily be performed by any one network alone. The merits of this approach have been assessed by mapping a neuropsychological model of single-word language processing onto a multi-network architecture. Language disorders may be simulated by damaging, or ‘lesioning’, one or more component networks. Our attempts to simulate two specific language disorders, semantic dementia and deep dysphasia, are described. The relative success of our simulation work is encouraging, and leads us to conclude that a multi-network approach to the simulation of cognitive function and dysfunction offers a valid alternative to the ‘traditional’ single-network based perspective.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01424226
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 20
    Electronic Resource
    Electronic Resource
    Blind source separation with convolutive noise cancellation (1997)
    Springer
    Neural computing & applications 6 (1997), S. 127-141 
    Details
    ISSN: 1433-3058
    Keywords: Adaptive noise cancellation ; Blind separation ; FIR filters ; ICA ; Learning algorithms ; Neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract On-line adaptive learning algorithms for cancellation of additive, convolutive noise from linear mixtures of sources with a simultaneous blind source separation are developed. Associated neural network architectures are proposed. A simple convolutive noise model is assumed, i.e. the unknown additive noise in each channel is a (FIR) filtering version of environmental noise, where some convolutive reference noise is measurable. Two approaches are considered: in the first, the noise is cancelled from the linear mixture of source signals as pre-processing, after that the source signals are separated; in the second, both source separation and additive noise cancellation are performed simultaneously. Both steps consist of adaptive learning processes. By computer simulation experiments, it was found that the first approach is applicable for a large amount of noise, whereas in the second approach, a considerable increase of the convergence speed of the separation process can be achieved. Performance and validity of the proposed approaches are demonstrated by extensive computer simulations.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413824
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 21
    Electronic Resource
    Electronic Resource
    The impact of neural networks in finance (1997)
    Springer
    Neural computing & applications 6 (1997), S. 193-200 
    Details
    ISSN: 1433-3058
    Keywords: Economic modelling ; Finance ; Neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract The financial industry is becoming more and more dependent on advanced computer technologies in order to maintain competitiveness in a global economy. Neural networks represent an exciting technology with a wide scope for potential applications, ranging from routine credit assessment operations to driving of large scale portfolio management strategies. Some of these applications have already resulted in dramatic increases in productivity. This paper brings together, from diverse sources, a collection of current research issues on neural networks in the financial domain. It examines a range of neural network systems related to financial applications from different levels of maturity to fielded products. It discusses the success rate of the neural network systems, and their performance in resolving particular financial problems.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01501506
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 22
    Electronic Resource
    Electronic Resource
    Fuzzy assisted learning in backpropagation neural networks (1997)
    Springer
    Neural computing & applications 6 (1997), S. 238-244 
    Details
    ISSN: 1433-3058
    Keywords: Adaptive algorithms ; Back propagation ; Fuzzy control ; Improved learning ; Neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract This paper reports on studies to overcome difficulties associated with setting the learning rates of backpropagation neural networks by using fuzzy logic. Building on previous research, a fuzzy control system is designed which is capable of dynamically adjusting the individual learning rates of both hidden and output neurons, and the momentum term within a back-propagation network. Results show that the fuzzy controller not only eliminates the effort of configuring a global learning rate, but also increases the rate of convergence in comparison with a conventional backpropagation network. Comparative studies are presented for a number of different network configurations. The paper also presents a brief overview of fuzzy logic and backpropagation learning, highlighting how the two paradigms can enhance each other.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01501510
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 23
    Electronic Resource
    Electronic Resource
    Radial basis function artificial neural networks for the inference process in fuzzy logic based control (1995)
    Springer
    Computing 54 (1995), S. 99-117 
    Details
    ISSN: 1436-5057
    Keywords: Neural networks ; fuzzy logic ; control
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Description / Table of Contents: Zusammenfassung Dieser Artikel illustriert den auf Fuzzy-Logik basierenden Ansatz zur Steuerung eines Systems and diskutiert einige der möglichen Nachteile der üblichen Inferenzmechanismen. Es wurde gezeigt, daß neuronale Netzwerke mit radialen Basisfunktionen für viele Anwendungen sehr effektiv sind und den Vorteil haben, daß das Trainieren des Netzwerkes wegen seiner Struktur ein sehr schneller Prozeß ist. Praktisch wird dies für gewöhnlich durch das Lösen eines linearen Gleichungssystems durchgeführt, ein Schritt für den schnelle und robuste Verfahren verfügbar sind. Es wird gezeigt, daß neuronale Netzwerke mit radialen Basisfunktionen ein Mittel zur Konstruktion einer Inferenzmaschine sind, wobei eine Regel-Basis zur Steuerung von Systemzuständen und Systemänderungen durch Fuzzy-Logik dargestellt wird. Der resultierende Inferenzmechanismus vermeidet das Phänomen der Regelüberlappung, das bei Fuzzy-Logic-Steueralgorithmen auftreten kann. Es ist interessant, daß bei dieser Anwendung von neuronalen Netzwerken mit radialen Basisfunktionen die üblichen Probleme bei der Anzahl und Plazierung der Zentren nicht auftreten. Der Artikel schließt mit einer zusammenfassenden Diskussion und einigen experimentellen Ergebnissen.
    Notes: Abstract This paper illustrates the fuzzy logic based approach to the control of a plant or a system, and discusses some of the possible shortcomings of the usual inference mechanisms. Radial basis function artificial neural networks have been shown to be effective in a number of applications, and have the advantage that network training is a very rapid process due to their structure. In fact, this is usually accomplished by the solution of a system of linear equations, a process for which fast and reliable algorithms are available. Radial basis function networks are shown to provide a means of constructing an ‘inference engine’ capable of handling a rule base in which plant state and control actions are specified in terms of fuzzy sets. The resulting inference mechanism is shown to avoid the phenomena of ‘rule overlap’ which can be a feature of fuzzy control algorithms. It is interesting to note that in this application of radial basis function networks, the usual problems on the number and location of centres do not arise. The paper concludes with a brief discussion of some experimental results achieved.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF02238126
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 24
    Electronic Resource
    Electronic Resource
    Neural net robot controller: Structure and stability proofs (1995)
    Springer
    Journal of intelligent and robotic systems 12 (1995), S. 277-299 
    Details
    ISSN: 1573-0409
    Keywords: Neural networks ; robots ; robust-adaptive control
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract A multilayer neural net (NN) controller for a general serial-link robot arm is developed. The structure of the NN controller is derived using a filtered error approach. It is argued that standard backpropagation tuning, when used for real-time closed-loop control, can yield unbounded NN weights if: (1) the net can not exactly reconstruct a certain required control function, (2) there are bounded unknown disturbances in the robot dynamics, or (3) the robot arm has more than one link (i.e. nonlinear case). On-line weight tuning algorithms including correction terms to backpropagation, plus an added robustifying signal, guarantee tracking as well as bounded weights. The correction terms involve a second-orderforward-propagated wave in the backprop network.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01262965
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 25
    Electronic Resource
    Electronic Resource
    Self-organising neural networks for adaptive control (1996)
    Springer
    Journal of intelligent and robotic systems 15 (1996), S. 153-163 
    Details
    ISSN: 1573-0409
    Keywords: Neural networks ; adaptive control ; self-organising networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract Self-organizing neural networks have been implemented in a wide range of application areas such as speech processing, image processing, optimization and robotics. Recent variations to the basic model proposed by the authors enable it to order state space using a subset of the input vector and to apply a local adaptation procedure that does not rely on a predefined test duration limit. Both these variations have been incorporated into a new feature map architecture that forms an integral part of an Hybrid Learning System (HLS) based on a genetic-based classifier system. Problems are represented within HLS as objects characterized by environmental features. Objects controlled by the system have preset targets set against a subset of their features. The system's objective is to achieve these targets by evolving a behavioural repertoire that efficiently explores and exploits the problem environment. Feature maps encode two types of knowledge within HLS — long-term memory traces of useful regularities within the environment and the classifier performance data calibrated against an object's feature states and targets. Self-organization of these networks constitutes non-genetic-based (experience-driven) learning within HLS. This paper presents a description of the HLS architecture and an analysis of the modified feature map implementing associative memory. Initial results are presented that demonstrate the behaviour of the system on a simple control task.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF00125491
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 26
    Electronic Resource
    Electronic Resource
    Back-propagation neural networks for identification and control of a direct drive robot (1996)
    Springer
    Journal of intelligent and robotic systems 16 (1996), S. 45-64 
    Details
    ISSN: 1573-0409
    Keywords: Neural networks ; back-propagation training method ; parameter identification ; computed-torque method ; direct drive robots
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract A neural approach is proposed to estimate parameters in dynamics of a direct drive robot. Before the estimation, the input-output data for identification are generated in a sequential and term-by-term manner first. Then a two-layer neural network for parameter identification is proposed, in which the back-propagation training method is used to adjust the weights between neurons. The goal is to find the weights that minimize the root-mean-square error between the identification data and output of the network. With the estimated dynamics, existing trajectory-tracking algorithms, such as the well-known computed-torque method, can then be applied to make the robot move along a desired trajectory.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF00309655
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 27
    Electronic Resource
    Electronic Resource
    Diagnostic neural adaptive control of drifting systems (1995)
    Springer
    Journal of intelligent and robotic systems 14 (1995), S. 303-321 
    Details
    ISSN: 1573-0409
    Keywords: Neural networks ; fuzzy logic ; hierarchical control ; redundant robots ; object recognition
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract A hierarchical network of neural network planning and control is employed to successfully accomplish a task such as grasping in a cluttered real world environment. In order for the individual robot joint controllers to follow their specific reference commands, information is shared with other neural network controllers and planners within the hierarchy. Each joint controller is initialized with weights that will acceptably control given a change in any of several crucial parameters across a broad operating range. When increased accuracy is needed as parameters drift, the diagnostic node fuzzy supervisor interprets the controller network's diagnostic outputs and transitions the weights to a closest fit specificchild controller. Future reference commands are in turn influenced by the diagnostic outputs of every robot joint neural network controller. The neural network controller and diagnostics are demonstrated for linear and nonlinear plants.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01258354
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 28
    Electronic Resource
    Electronic Resource
    A neural network based adaptive robot controller (1996)
    Springer
    Journal of intelligent and robotic systems 15 (1996), S. 3-10 
    Details
    ISSN: 1573-0409
    Keywords: Neural networks ; adaptive robot control ; recursive prediction error
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract Neural network based adaptive controllers have been shown to achieve much improved accuracy compared with traditional adaptive controllers when applied to trajectory tracking in robot manipulators. This paper describes a new Recursive Prediction Error technique for estimating network parameters which is more computationally efficient. Results show that this neural controller suppresses disturbances accurately and achieves very small errors between commanded and actual trajectories.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF00435721
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 29
    Electronic Resource
    Electronic Resource
    Artificial neural network based robot control: An overview (1996)
    Springer
    Journal of intelligent and robotic systems 15 (1996), S. 333-365 
    Details
    ISSN: 1573-0409
    Keywords: Neural networks ; robotics ; intelligent control
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract The current thrust of research in robotics is to build robots which can operate in dynamic and/or partially known environments. The ability of learning endows the robot with a form of autonomous intelligence to handle such situations. This paper focuses on the intersection of the fields of robot control and learning methods as represented by artificial neural networks. An in-depth overview of the application of neural networks to the problem of robot control is presented. Some typical neural network architectures are discussed first. The important issues involved in the study of robotics are then highlighted. This paper concentrates on the neural network applications to the motion control of robots involved in both non-contact and contact tasks. The current state of research in this area is surveyed and the strengths and weakness of the present approaches are emphasized. The paper concludes by indentifying areas which need future research work.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF00437601
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 30
    Electronic Resource
    Electronic Resource
    On-line cursive script recognition using time-delay neural networks and hidden Markov models (1995)
    Springer
    Machine vision and applications 8 (1995), S. 215-223 
    Details
    ISSN: 1432-1769
    Keywords: Handwriting recognition ; Neural networks ; Cursive script ; Hidden Markov models ; Dictionary search
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We present a writer-independent system for online handwriting recognition that can handle a variety of writing styles including cursive script and handprinting. The input to our system contains the pen trajectory information, encoded as a time-ordered sequence of feature vectors. A time-delay neural network is used to estimate a posteriori probabilities for characters in a word. A hidden Markov model segments the word in a way that optimizes the global word score, using a dictionary in the process. A geometrical normalization scheme and a fast but efficient dictionary search are also presented. Trained on 20 k words from 59 writers, using a 25 k-word dictionary, our system reached recognition rates of 89% for characters and 80% for words on test data from a disjoint set of writers.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01219589
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 31
    Electronic Resource
    Electronic Resource
    Recognition of hand-written rotated digits by neural networks (1995)
    Springer
    Machine vision and applications 8 (1995), S. 351-357 
    Details
    ISSN: 1432-1769
    Keywords: Neural networks ; Hand-written rotated digits ; Feature selection ; Generalization ; Constructive learning rules
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In this paper, an optical character recognition system for hand-written rotated digits in land registry maps is presented. It is based on a neural network and trained by a constructive learning rule, the Hyperbox Perception Cascade (HPC). The HPC classifier can design complex, possibly nonconvex, disjoint, and bounded decision regions and treat the rejection problems of outliers and unanticipated patterns, which would otherwise tend to be classified positively in an incorrect class. We use “shape features” and a novel approach to select the most promising features to attain a low generalization error. The numerous experiments show that a subset of 24 of the 46 features obtains a good classifier with a high rate of correct classification and a low rate of rejection.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01211497
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 32
    Electronic Resource
    Electronic Resource
    A neuromorphic architecture for cortical multilayer integration of early visual tasks (1995)
    Springer
    Machine vision and applications 8 (1995), S. 305-314 
    Details
    ISSN: 1432-1769
    Keywords: Neural networks ; Cortical architecture ; Primal sketch ; Texture analysis ; VLSI
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract The characteristics and performance of a hierarchical neural architecture, inspired by models of mammalian visual cortex, are considered. The visual pathway from sensory space to the intermediate (cortical) representation is structured in three layers, with intra and interlayer connections through feedforward and recurrent pathways. These interconnections provide a complex perceptual organization that integrates the specific functional tasks performed by each layer. This improves the capabilities of the architecture in feature extraction and segregation, further providing clues on the information content of the intermediate representation (primal sketch). Applications to preattentive vision tasks (edge and contour extractions, texture analysis and boundary completion, and defect detection) are presented with satisfactory results.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01211491
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 33
    Electronic Resource
    Electronic Resource
    Handprinted word recognition on a NIST data set (1995)
    Springer
    Machine vision and applications 8 (1995), S. 31-40 
    Details
    ISSN: 1432-1769
    Keywords: Word recognition ; Character recognition ; Neural networks ; Character segmentation ; Document processing
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract An approach to handprinted word recognition is described. The approach is based on the use of generating multiple possible segmentations of a word image into characters and matching these segmentations to a lexicon of candidate strings. The segmentation process uses a combination of connected component analysis and distance transform-based, connected character splitting. Neural networks are used to assign character confidence values to potential character within word images. Experimental results are provided for both character and word recognition modules on data extracted from the NIST handprinted character database.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01213636
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 34
    Electronic Resource
    Electronic Resource
    Neural structures for visual motion tracking (1995)
    Springer
    Machine vision and applications 8 (1995), S. 275-288 
    Details
    ISSN: 1432-1769
    Keywords: Motion tracking ; Neural networks ; Network ensembles ; Real-time systems
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper addresses visual motion tracking by a connectionist method, and aims at showing how the flexibility and the generalization power of neural networks can enhance a tracking system's adaptiveness and effectiveness. The simple principle of operation widens the range of applicability. A set of tracking structures that exhibit increasing levels of integration and efficiency are described. We also show how multinetwork architectures for estimate averaging may greatly increase tracking stability. The validity of the basic mechanism was assessed on a simple domain; however, a specific difficult testbed made it possible to verify the effectiveness of the method.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01211489
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 35
    Electronic Resource
    Electronic Resource
    Homologue matching applications: Recognition of overlapped chromosomes (1998)
    Springer
    Pattern analysis and applications 1 (1998), S. 206-217 
    Details
    ISSN: 1433-755X
    Keywords: Dynamic programming ; Human chromosomes ; Image processing ; Karyotyping ; Medical imaging ; Neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Automated Giemsa-banded chromosome image research has been largely restricted to classification schemes associated with isolated chromosomes within metaphase spreads. Overlapping chromosomes cause difficulties in the automated chromosome karyotyping process. First, overlapping chromosomes must be recognised and decomposed into the proper chromosome parts. Secondly, the decomposed chromosomes must be classified. The first difficulty is associated with image segmentation. The second area is a pattern recognition problem. Even if chromosomes within overlapping clusters are decomposed properly, classification capability is impaired due to feature distortion in the overlapped regions. In normal human metaphase spreads, chromosomes occur in homologous pairs for the autosomal classes, 1–22, and X chromosome for females. This research presents a homologue matching approach for overlapped chromosome recognition. The undistorted grey level information in isolated chromosomes is used for identifying overlapped chromosomes. An isolated chromosome prototype is obtained using neural networks. Dynamic programming and neural networks are compared for matching the prototype to its overlapped homoloque. The homologue matching method is applied to identifying chromosome 2 in 50 metaphase spreads. Experimental results showed that homologue matching using dynamic programming matching based on the density profile achieved a higher correct recognition rate than homologue matching using three different neural network approaches.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01234768
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 36
    Electronic Resource
    Electronic Resource
    Evaluation of robust control by universal learning networks (1997)
    Springer
    Artificial life and robotics 1 (1997), S. 123-129 
    Details
    ISSN: 1614-7456
    Keywords: Robust control ; Neural networks ; Universal learning networks ; Second-order derivative
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract The characteristics of control system design using a universal learning network (ULN) are such that both the controlled systems and their controller are represented in a unified framework, and that the learning stage of the ULN can be executed by using not only first-order derivatives (gradient) but also the higher order derivatives of the criterion function with respect to parameters. ULNs have the same generalization ability as neural networks. So the ULN controller is able to control the system in a favorable way under an environment which is little different from the environment of the control system at the learning stage. However, stability cannot be sufficiently realized. In this paper, we propose a robust control method using a ULN and second-order derivatives of that ULN. Robust control, as considered here, is defined as follows. Even though the initial values of the node outputs are very different from those at the learning stage, the control system is able to reduce its influence to other node outputs and can control the system as in the case of no variation. In order to realize such robust control, a new term concerning the variation is added to the usual criterion function, and the parameters are adjusted so as to minimize the above-mentioned criterion function using second-order derivatives of the criterion function with respect to the parameters. Finally, it is shown that the ULN controller constructed by the proposed method works effectively in a simulation study of a non-linear crane system.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF02471126
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 37
    Electronic Resource
    Electronic Resource
    Modeling and complexity in neural networks (1999)
    Springer
    Artificial life and robotics 3 (1999), S. 148-154 
    Details
    ISSN: 1614-7456
    Keywords: Chaos ; Neural networks ; Brain ; Complex systems ; Spatio-temporal dynamics
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In this paper, we study nonlinear spatio-temporal dynamics in synchronous and asynchronous chaotic neural networks from the viewpoint of the modeling and complexity of the dynamic brain. First, the possible roles and functions of spatio-temporal neurochaos are considered with a model of synchronous chaotic neural networks composed of a neuron model with a chaotic map. Second, deterministic point-process dynamics with spikes of action potentials is demonstrated with a biologically more plausible model of asynchronous chaotic neural networks. Last, the possibilities of inventing a new brain-type of computing system are discussed on the basis of these models of chaotic neural networks.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF02481131
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 38
    Electronic Resource
    Electronic Resource
    A comparative study for forecasting using neural networks vs genetically identified Box&Jenkins models (1995)
    Springer
    Neural computing & applications 3 (1995), S. 139-148 
    Details
    ISSN: 1433-3058
    Keywords: Comparative study ; Expert systems ; Forecasting ; Genetic algorithm ; Neural networks ; SARIMA models
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract This paper aims to discuss the results and conclusions of an extensive comparative study on the forecasting performance between two different techniques: a genetic expert system in which a genetic algorithm carries out the identification stage embraced in the three- phase Box&Jenkins univariate methodology; and a connectionist approach. At the heart of the former, an expert system rules the identification-estimation-diagnostic checking cyclical process to end up with the predictions provided by the SARIMA model which best fits the data. We will present the connectionist approach as technically equivalent to the latter process and due to its, alas, lack of any conclusive existent algorithm able to identify both the optimal model and architecture for a given problem, the three most common models presently at use and 20 different architectures for each model will be examined. It seems natural that if a comparison is to be made in order to provide a straight answer as to whether or not a connectionist approach outperforms the univariate Box&Jenkins methodology, the benchmark should clearly be the set of time series analysed in the work ‘Time Series Analysis. Forecasting and Control’ by G. E. Box and G. M. Jenkins. Series BJA through to BJG give a total of 1200 plus measures to evaluate and compare the predictive power for different models, architectures, prediction horizons and pre-processing transformations.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01414075
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 39
    Electronic Resource
    Electronic Resource
    A new neural network structure for detection of coronary heart disease (1995)
    Springer
    Neural computing & applications 3 (1995), S. 171-177 
    Details
    ISSN: 1433-3058
    Keywords: Backpropagation ; Coronary heart disease ; Diagnosis ; Neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract We investigate the application of neural networks for the detection of Coronary Heart Disease (CHD). We have used a Neural Network (NN) on data from a self- applied questionnaire to implement a decision system designed to seek out high risk individuals in a large population. A Multi- Layered Perceptron (MLP) was trained with risk factors to distinguish CHD. We also describe a modification to the architecture of the neural network in which an extra layer of neurons is added at the input. We present possible interpretations of the weights of these neurons, and show how they can be used as a selection criteria for which questions to use as inputs. The technique is compared against other statistical methods. We go on to demonstrate the system's capability for detecting both the symptomatic and asymptomatic patient.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01414079
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 40
    Electronic Resource
    Electronic Resource
    A neural network simulation method of aphasic naming errors: Properties and behaviour (1995)
    Springer
    Neural computing & applications 3 (1995), S. 192-201 
    Details
    ISSN: 1433-3058
    Keywords: Aphasia ; Computer linguistics ; Lingual naming errors ; Neural networks ; Psycholinguistics ; Simulation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract Aphasia is a language disorder caused by brain damage. Naming errors which are common in aphasia are applied to reveal the type and the effects of a disorder. Naming in this research field refers to psycholinguistic tests where a subject is asked to say the name of an object presented as a picture to him or her. We have earlier presented a simulation model on the basis of neural networks [1,2]. The model is further developed here, and its properties and behaviour are described in the present paper. The simulation model includes a bounded set of Finnish words in their base lingual form. The principle of activation spreading is used to process naming errors with the method to simulate actual aphasic errors. All computation in the model is executed with words as text or with textual components of words, although the system processes naming errors, i.e. human speech.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01414644
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 41
    Electronic Resource
    Electronic Resource
    Assessment of sheet-metal bending requirements using neural networks (1996)
    Springer
    Neural computing & applications 4 (1996), S. 35-43 
    Details
    ISSN: 1433-3058
    Keywords: Automation ; Bending ; Forming ; Modelling ; Neural networks ; Sheet-metal ; Springback system
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract The springback behaviour of a sheet-metal is dependent on the properties of the metal and the bending conditions, namely the thickness of the sheet-metal, geometry of the tooling and the amount of force used for bending. Sheet-metal component manufacturing often requires near zero springback angle to obtain the correct shape of the product. An attempt has been made to model the non-linear relation between properties of the metal, the springback angle, geometry of the tooling and the bending force applied. Multilayer perceptron neural networks with a backpropagation learning algorithm were used to model the bending process. One set of data from bending experiments in a laboratory environment was used to train the networks. The networks were tested with the remaining set of experimental results. Then, the neural networks were used to predict the forces required for a number of bending experiments to achieve a zero springback angle. Validation of the neural network predictions was performed by trying to apply the predicted amounts of bending force in the physical experiments. The springback angles achieved were within ±1 degree, which is an acceptable range for the work. The research clearly demonstrates the applicability of neural networks to modelling the sheet-metal bending process.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413868
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 42
    Electronic Resource
    Electronic Resource
    Patenting neural networks-an introduction (1996)
    Springer
    Neural computing & applications 4 (1996), S. 58-62 
    Details
    ISSN: 1433-3058
    Keywords: Copyright ; Neural networks ; Patents
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract Two well-known former neural computation researchers explain the legal protection available for neural networks in Europe, and in particular the applicability of patent law to the unique concepts underlying neural research1. The result is an introductory guide for all groups whose projects are approaching, or have taken, the leap from the drawing board, and who wish to make commercial use of their results.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413870
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 43
    Electronic Resource
    Electronic Resource
    A field trial using Artificial Neural Networks to predict psychiatric in-patient Length-of-stay (1997)
    Springer
    Neural computing & applications 5 (1997), S. 184-193 
    Details
    ISSN: 1433-3058
    Keywords: Neural networks ; Length-of-stay ; Psychiatry ; Resource utilization ; Back propagation ; Field study
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract Demands for health care reform will increase service utilization, much of which will fall on a system of expanded primary care providers, many of whom will not be specialists in psychiatry. These providers will need tools to augment their decision-making process. In this paper, we explore the use of Artificial Neural Networks (ANNs) in three different field sites to predict inpatient psychiatric Length-Of-Stay (LOS). This study describes the development and implementation of a runtime system in three different psychiatric facilities. Data was collected at these respective sites using the runtime system, and then this data was used to retrain the networks to determine if site-specific data would improve accuracy of prediction of LOS. The results indicate that ANNs trained with state hospital data could accurately predict LOS in two different community hospital psychiatric units. When the respective ANNs were retrained with approximately 10% new data from these specific hospitals, rates of improvement ranged from 3% to 15%. Our findings demonstrate that an ANN can adapt to different treatment settings and, when retrained, significantly improve prediction of LOS. Prediction rates by the ANN after retraining are comparable to results of a clinical team.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413862
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 44
    Electronic Resource
    Electronic Resource
    Feed-forward neural networks and topographic mappings for exploratory data analysis (1996)
    Springer
    Neural computing & applications 4 (1996), S. 83-95 
    Details
    ISSN: 1433-3058
    Keywords: Neural networks ; Topographic mappings ; Data analysis ; Feature Extraction ; Sammon mapping ; Multidimensional scaling
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract A recent novel approach to the visualisation and analysis of datasets, and one which is particularly applicable to those of a high dimension, is discussed in the context of real applications. A feed-forward neural network is utilised to effect a topographic, structure-preserving, dimension-reducing transformation of the data, with an additional facility to incorporate different degrees of associated subjective information. The properties of this transformation are illustrated on synthetic and real datasets, including the 1992 UK Research Assessment Exercise for funding in higher education. The method is compared and contrasted to established techniques for feature extraction, and related to topographic mappings, the Sammon projection and the statistical field of multidimensional scaling.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01413744
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 45
    Electronic Resource
    Electronic Resource
    A PDP constructive algorithm for system modelling (1996)
    Springer
    Neural computing & applications 4 (1996), S. 175-182 
    Details
    ISSN: 1433-3058
    Keywords: Neural networks ; Constructive algorithm ; System modelling ; Interpretation ; Cross-validation ; Hybrid networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract A new constructive algorithm is presented for building neural networks that learn to reproduce output temporal sequences based on one or several input sequences. This algorithm builds a network for the task of system modelling, dealing with continuous variables in the discrete time domain. The constructive scheme makes it user independent. The network's structure consists of an ordinary set and a classification set, so it is a hybrid network like that of Stokbro et al. [6], but with a binary classification. The networks can easily be interpreted, so the learned representation can be transferred to a human engineer, unlike many other network models. This allows for a better understanding of the system structure than just its simulation. This constructive algorithm limits the network complexity automatically, hence preserving extrapolation capabilities. Examples with real data from three totally different sources show good performance and allow for a promising line of research.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01414878
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 46
    Electronic Resource
    Electronic Resource
    Temperature analysis of Coherent Anti-Stokes Raman spectra using a neural network approach (1997)
    Springer
    Neural computing & applications 5 (1997), S. 248-257 
    Details
    ISSN: 1433-3058
    Keywords: Neural networks ; CARS ; Spectroscopy ; Combustors
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract A neural network trained with clustered data has been applied to the extraction of temperature from vibrational Coherent Anti-Stokes Raman (CARS) spectra of nitrogen. CARS is a non-intrusive thermometry technique applied in practical combustors in industry. The advantages of clustering of training data over training with unprocessed calculated spectra is described. The method is applied to CARS data from an isothermal furnace and a liquid kerosene fuelled aeroengine combustor sector rig. Resulting temperatures have been compared with values extracted from the data using conventional least squares fitting and, where possible, mean temperatures measured by pyrometer and blackbody cavity probe. The main advantage of the neural network method is speed, with the potential for online temperature extraction at the spectral acquisition rate of 10 Hz using standard PC hardware.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01424230
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 47
    Electronic Resource
    Electronic Resource
    Genetic design of real-time neural network controllers (1997)
    Springer
    Neural computing & applications 6 (1997), S. 12-18 
    Details
    ISSN: 1433-3058
    Keywords: Flow systems ; Genetic algorithms ; Neural networks ; Real-time control ; Reinforcement learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract The use of genetic algorithms to design neural networks for real-time control of flows in sewerage networks is discussed. In many control applications, standard supervised learning techniques (such as back-propagation) cannot be used through lack of training data. Reinforcement learning techniques, such as genetic algorithms, are a computationally-expensive but viable alternative if a simulator is available for the system in question. The paper briefly describes why genetic algorithms and neural networks were selected, then reports the results of a feasibility study. This demonstrates that the approach does indeed have merits. The implications of high computational cost are discussed, in terms of scaling up to significantly complex problems.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01670149
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 48
    Electronic Resource
    Electronic Resource
    The prediction of protein secondary structure with a Cascade Correlation Learning Architecture of neural networks (1997)
    Springer
    Neural computing & applications 6 (1997), S. 57-62 
    Details
    ISSN: 1433-3058
    Keywords: Cascade correlation learning algorithm ; Neural networks ; Pattern recognition ; Predictive methods ; Protein secondary structure prediction
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract A Cascade Correlation Learning Architecture (CCLA) of neural networks is tested on the task of predicting the secondary structure of proteins. The results are compared with those obtained with Neural Networks (NN) trained with the back-propagation algorithm (BPNN) and generated with genetic algorithms. CCLA proceeds towards the global minimum of the error function more efficiently than BPNN. However, only a slight improvement in the average efficiency value is noticeable (61.82% as compared with 61.61% obtained with BPNN). The values of the three correlation coefficients for the discriminated secondary structures are also rather similar (Ct8,C α ,C β and Ccoil are 0.36, 0.29 and 0.36 with CCLA, and 0.36, 0.31 and 0.35 with BPNN). This indicates that the efficiency of the prediction does not depend upon the training algorithm, and confirms our previous observation that when single sequences are used as input code to the network system, different NN architectures can perform similarly.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01670152
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 49
    Electronic Resource
    Electronic Resource
    Global feature space neural network for active computer vision (1998)
    Springer
    Neural computing & applications 7 (1998), S. 195-215 
    Details
    ISSN: 1433-3058
    Keywords: Active vision ; Classification ; Neural networks ; Recognition ; Representation ; Pose estimation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract We advance new active computer vision algorithms based on the Feature space Trajectory (FST) representations of objects and a neural network processor for computation of distances in global feature space. Our algorithms classify rigid objects and estimate their pose from intensity images. They also indicate how to automatically reposition the sensor if the class or pose of an object is ambiguous from a given viewpoint and they incorporate data from multiple object views in the final object classification. An FST in a global eigenfeature space is used to represent 3D distorted views of an object. Assuming that an observed feature vector consists of Gaussian noise added to a point on the FST, we derive a probability density function for the observation conditioned on the class and pose of the object. Bayesian estimation and hypothesis testing theory are then used to derive approximations to the maximum a posterioriprobability pose estimate and the minimum probability of error classifier. Confidence measures for the class and pose estimates, derived using Bayes theory, determine when additional observations are required, as well as where the sensor should be positioned to provide the most useful information.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01414882
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 50
    Electronic Resource
    Electronic Resource
    Neural network controller for a multivariable model of submarine dynamics (1998)
    Springer
    Neural computing & applications 7 (1998), S. 295-308 
    Details
    ISSN: 1433-3058
    Keywords: Adaptive ; Backpropagation ; Multivariable ; Neural networks ; Optimal control ; Submarine
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract Recently, there have been many attempts to use neural networks as a feedback controller. However, most of the reported cases seek to control Single-Input Single-Output (SISO) systems using some sort of adaptive strategy. In this paper, we demonstrate that neural networks can be used for the control of complex multivariable, rather than simply SISO, systems. A modified direct control scheme using a neural network architecture is used with backpropagation as the adaptive algorithm. The proposed algorithm is designed for Multi-Input Multi-Output (MIMO) systems, and is similar to that proposed by Saerens and Soquet [1] and Goldenthal and Farrell [2] for (SISO) systems, and differs only in the form of the gradient approximation. As an example of the application of this approach, we investigate the control of the dynamics of a submarine vehicle with four inputs and four outputs, in which the differential stern, bow and rudder control surfaces are dynamically coordinated to cause the submarine to follow commanded changes in roll, yaw rate, depth rate and pitch attitude. Results obtained using this scheme are compared with those obtained using optimal linear quadratic control.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01428121
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 51
    Electronic Resource
    Electronic Resource
    Detection of Lung Injury with Conventional and Neural Network-Based Analysis of Continuous Data (1998)
    Springer
    Journal of clinical monitoring and computing 14 (1998), S. 433-440 
    Details
    ISSN: 1573-2614
    Keywords: Neural networks ; monitoring ; artificial ventilation ; oleic acid ; respiratory failure ; lung mechanics
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Medicine
    Notes: Abstract Objective. To test if analysis of pressure and flow waveform patterns with an artificial intelligence neural network could distinguish between normal and injured lungs. Methods. Acute lung injury was induced in ten healthy anesthetized, mechanically ventilated dogs with repeated injections of oleic acid, until arterial blood oxyhemoglobin saturation reached 85% breathing room air. Airway pressure, esophageal pressure, airway flow, and arterial and mixed venous saturation signals were stored at 2 min intervals. Hemodynamic and blood gas data were collected every 10 min. Back-propagation neural networks were trained with normalized airway pressure and flow waveforms from normal and fully injured lungs. Results. The networks scored lung injury on a continuous scale from +1 (normal) to −1 (injured). Network scores unequivocally distinguished between normal and fully injured lungs and suggested a gradual transition from normal to injury pattern. However, the response of the network was slow compared to compliance, resistance and venous admixture. Conclusions. Normal and fully injured lungs display distinct flow and pressure waveform patterns which are independent of changes in calculated pulmonary mechanics variables. These patterns can be recognized by a neural network. Further research is needed to determine the full potential of automated pattern recognition for lung monitoring.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009938725385
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 52
    Electronic Resource
    Electronic Resource
    Upgrading automation for nuclear fuel in-core management: From the symbolic generation of configurations, to the neural adaptation of heuristics (1997)
    Springer
    Engineering with computers 13 (1997), S. 1-19 
    Details
    ISSN: 1435-5663
    Keywords: Allocation ; Design ; Downtime ; Expert systems ; Machine learning ; Neural networks ; Nuclear engineering ; in-core fuel management ; Refueling ; Reload
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics , Technology
    Notes: Abstract FUELCON is an expert system in nuclear engineering. Its task is optimized refueling-design, which is crucial to keep down operation costs at a plant. FUELCON proposes sets of alternative configurations of fuel-allocation; the fuel is positioned in a grid representing the core of a reactor. The practitioner of in-core fuel management uses FUELCON to generate a reasonably good configuration for the situation at hand. The domain expert, on the other hand, resorts to the system to test heuristics and discover new ones, for the task described above. Expert use involves a manual phase of revising the ruleset, based on performance during previous iterations in the same session. This paper is concerned with a new phase: the design of a neural component to carry out the revision automatically. Such an automated revision considers previous performance of the system and uses it for adaptation and learning better rules. The neural component is based on a particular schema for a symbolic to recurrent-analogue bridge, called NIPPL, and on the reinforcement learning of neural networks for the adaptation.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01201857
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...