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  (9)
  • neural network  (8)
  • taxonomy
  • Springer  (9)
  • American Meteorological Society
  • 1995-1999  (9)
  • 1990-1994
  • 1985-1989
  • 1965-1969
  • 1955-1959
  • 1950-1954
  • 1999  (9)
  • Computer Science  (9)
  • 1
    Electronic Resource
    Electronic Resource
    Recurrence and transience properties of some neural networks: an approach via fluid limit models (1999)
    Springer
    Queueing systems 32 (1999), S. 99-130 
    Details
    ISSN: 1572-9443
    Keywords: neural network ; inhibition ; stability ; Markov process ; fluid limit ; Harris-recurrence ; transience
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract The subject of the paper is the stability analysis of some neural networks consisting of a finite number of interacting neurons. Following the approach of Dai [5] we use the fluid limit model of the network to derive a sufficient condition for positive Harris-recurrence of the associated Markov process. This improves the main result in Karpelevich et al. [11] and, at the same time, sheds some new light on it. We further derive two different conditions that are sufficient for transience of the state process and illustrate our results by classifying some examples according to positive recurrence or transience.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1019135020138
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 2
    Electronic Resource
    Electronic Resource
    A Neurocomputational Approach to Abduction (1999)
    Springer
    Minds and machines 9 (1999), S. 257-265 
    Details
    ISSN: 1572-8641
    Keywords: Abduction ; control ; neural network ; perceptual judgment ; prototype ; prototype activation ; reduction ; theory-ladenness ; vector completion
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Philosophy
    Notes: Abstract Recent developments in the cognitive sciences and artificial intelligence suggest ways of answering the most serious challenge to Peirce's notion of abduction. Either there is no such logical process as abduction or, if abduction is a form of inference, it is essentially unconscious and therefore beyond rational control so that it lacks any normative significance. Peirce himself anticipates and attempts to answer this challenge. Peirce argues that abduction is both a source of creative insight and a form of logical inference subject to a degree of conscious control. In this paper I shall sketch a developing account of abduction that is suggested by the work of Paul Churchland, Paul Thagard, Chris Eliasmith, William Wimsatt, Owen Flanagan, and others. I shall argue that a credible account of abduction will require that we approach the phenomenon from both higher and lower levels as represented by these approaches.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008282804997
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 3
    Electronic Resource
    Electronic Resource
    Two examples of decision support in the law (1999)
    Springer
    Artificial intelligence and law 7 (1999), S. 303-321 
    Details
    ISSN: 1572-8382
    Keywords: decision support ; expert system ; fuzzy logic ; fuzzy ranking method ; insurance ; neural network ; traffic cases
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Law
    Notes: Abstract There are several systems which provide computer support to legal decisions. Perhaps the most significant ones, besides various computerised systems for administration, are information retrieval systems that locate statutes and documents. Other research projects, however, deal with legislation and adjudication, making it possible to use information techniques in making legal decisions. I wish to describe two decision-support programs and to link them to some theoretical findings of my former researches. What connects those programs is that they give some new information for decisions on the basis of previous similar legal cases; both describe cases with the help of criteria and use diverse artificial intelligence methods for different types or criteria. The first of the two programs aims to support decisions of insurance specialists by assessing the measure of the compensation for immaterial damage. The result is given by the combination of a neural network, based upon previous judicial cases, and an expert system. The neural network gives the first assessment for the sum of compensation while the expert system refines the network's output. The other program can be used by judges and lawyers in the course of preparing a decision. Studying cases of road accidents, we find that fuzzy logic methods can help to approximate decisions actually given by judges. In this way, the process of decision making by courts and lawyers receives an additional piece of information, obtained by comparing the seriousness of the actual case with that of previous cases.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008384601583
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 4
    Electronic Resource
    Electronic Resource
    Neural Control of the Movements of a Wheelchair (1999)
    Springer
    Journal of intelligent and robotic systems 25 (1999), S. 213-226 
    Details
    ISSN: 1573-0409
    Keywords: intelligent control ; neural network ; backpropagation ; Lyapunow stability ; wheelchair
    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 This paper studies the problem of controlling the movements of a handicapped person's motorized wheelchair from a practical point of view. The control system implemented has been divided into two levels: the “low level”, consisting of an electronic system which directly controls the drivers of the chair's motors, with a classic PID (proportional-integral-derivative) control loop. The aim of this level is to ensure that the speeds of each one of the wheels is similar to the input speed of these control boards. The second control level (“high level”), implemented by means of neural techniques, ensures that the linear and angular speeds of the wheelchair are those indicated by a trajectory generator. A new recurrent model is used as the neural network, for which the stability conditions of the complete control system are obtained and various practical tests are carried out, which show the correct performance of the actual system implemented.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008068322312
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 5
    Electronic Resource
    Electronic Resource
    On Model-Based Evolutionary Computation (1999)
    Springer
    Soft computing 3 (1999), S. 76-82 
    Details
    ISSN: 1433-7479
    Keywords: Key words: Fitness models ; genetic algorithm ; neural network ; NK model
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract  Traditional evolutionary computing techniques use an explicit fitness function – mathematical or simulated – to derive a solution to a problem from a population of individuals, over a number of generations. In this paper an approach which allows such techniques to be used on problems in which evaluations are costly, which cannot be expressed formally, or which are difficult to simulate, is examined. A neural network is trained using example individuals with the explicit fitness and the resulting model of the fitness function is then used by the evolutionary algorithm to find a solution. It is shown that the approach is effective over a small range of function types in comparison to the traditional approach when limited training data is available. An iterative step is then added whereby after a number of generations the current best individual in a population is evaluated directly on the explicit fitness function. The individual and its “real” fitness are then added to the training data and the neural network is re-trained to improve its approximation of the fitness function. It is shown that in this way the performance of the model-based architecture is greatly improved on more rugged/complex landscapes without a large increase in the amount of training data required.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/s005000050055
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 6
    Electronic Resource
    Electronic Resource
    A Chaotic Annealing Neural Network with Gain Sharpening and Its Application to the 0/1 Knapsack Problem (1999)
    Springer
    Neural processing letters 9 (1999), S. 243-247 
    Details
    ISSN: 1573-773X
    Keywords: knapsack problem ; chaotic annealing ; neural network
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In this article we present a modified transiently chaotic neural network model and then use it to solve the 0/1 knapsack problem. During the chaotic searching the gain of the neurons is gradually sharpened, this strategy can accelerate the convergence of the network to a binary state and keep the satisfaction of the constraints. The simulation demonstrates that the approach is efficient both in approximating the global solution and the number of iterations.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1018603904290
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 7
    Electronic Resource
    Electronic Resource
    System Thoughts in Manufacturing (1999)
    Springer
    Journal of systems integration 9 (1999), S. 167-185 
    Details
    ISSN: 1573-8787
    Keywords: flexibility ; complexity ; systems approach ; taxonomy
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In this paper we present a taxonomy of manufacturing problems, labeled in a general sense as Design, Production, or Distribution problems. One or more basic systems concepts, such as complexity and adaptation, attach themselves to each such problems. By combining the hierarchical Design—Production—Distribution idea with system concepts, we establish the fact that there is, indeed, a significant systems component to most problems of modern manufacturing.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008422627181
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 8
    Electronic Resource
    Electronic Resource
    Computational Rules for Chemotaxis in the Nematode C. elegans (1999)
    Springer
    Journal of computational neuroscience 6 (1999), S. 263-277 
    Details
    ISSN: 1573-6873
    Keywords: orientation ; neural network ; control ; rule extraction ; linearization
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Medicine , Physics
    Notes: Abstract We derive a linear neural network model of the chemotaxis control circuit in the nematode Caenorhabditis elegans and demonstrate that this model is capable of producing nematodelike chemotaxis. By expanding the analytic solution for the network output in time-derivatives of the network input, we extract simple computational rules that reveal how the model network controls chemotaxis. Based on these rules we find that optimized linear networks typically control chemotaxis by computing the first time-derivative of the chemical concentration and modulating the body turning rate in response to this derivative. We argue that this is consistent with behavioral studies and a plausible mechanism for at least one component of chemotaxis in real nematodes.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008857906763
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 9
    Electronic Resource
    Electronic Resource
    Nonlinear Model-Based Predictive Control of Non-Depolarizing Muscle Relaxants using Neural Networks (1999)
    Springer
    Journal of clinical monitoring and computing 15 (1999), S. 271-278 
    Details
    ISSN: 1573-2614
    Keywords: Muscle relaxants ; closed-loop control ; neural network ; model-based predictive control ; mivacurium
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Medicine
    Notes: Abstract Neuromuscular blockade can be relatively easily measured in the clinical setting. Consequently, closed-loop control can be exercised by measuring the neuromuscular activity, calculating the dose of drug necessary to achieve a predefined degree of neuromuscular blockade and finally directing an infusion pump. Recently introduced short-acting blocking agents like mivacurium provide benefits for the clinical routine due to a small onset time and half life. In order to provide a stable blockade for different groups of patients a fast and highly adaptable control unit is needed. Furthermore its development should not imply costly investigations for determining a pharmacological model. The fulfilling of these requirements yield a self-adapting model-based predictive control system. The application of artificial neural networks allows an appropriate adjustment of specific parameters without the knowledge of inner pharmacodynamic processes. In a clinical study the EMG module within a Datex AS/3 monitor was used to measure the blockade and a Grasepy 3500 infusion pump for i.v. administration of mivacurium to 35 patients (ASA I-III). The performance of the novel system (mean of the T1 error: −0.32 ± 1.7) compares favourably with closed-loop controllers demonstrated in the past. These promising results and the easy adaption to other blocking agents encourage to apply this technology even for delivering hypnotic drugs.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009915105434
    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...