Cantitate/Preț
Produs
Total produse
Vezi coșul
Artificial Neural Networks: International Workshop IWANN '91, Granada, Spain, September 17-19, 1991. Proceedings de Alberto Prieto

Artificial Neural Networks: International Workshop IWANN '91, Granada, Spain, September 17-19, 1991. Proceedings: Lecture Notes in Computer Science, cartea 540

Editat de Alberto Prieto
en Limba Engleză Paperback – 28 aug 1991
Artificial neural networks are massively parallelinterconnected networks ofsimple elements which areintended to interact with the objects of the real world inthe same way as biological nervous systems do. Interest inthese networks is due to the opinion that they are able toperform tasks like image and speech recognition that haveonly been implemented in limited ways by traditionalcomputing methods.This book includes invited lectures and the fullcontributions to the International Workshop onArtificialNeural Networks held in Granada, Spain, September 17-19,1991. The workshop was sponsored by the IEEE ComputerSociety, the Spanish Association for Computing andAutomatics, and the University of Granada. The contributionswere selected by an international program committee; theauthors of the papers come from 12 countries. The book isorganized in six sections, covering: - Neural networktheories and neural models - Biological perspectives -Neural network architectures and algorithms - Softwaredevelopments and tools - Hardware implementations -Applications.
Citește tot Restrânge

Din seria Lecture Notes in Computer Science

Preț: 34560 lei

Preț vechi: 43200 lei
-20%

Puncte Express: 518
Preț estimativ în valută:
6110€ • 7284$ • 5299£

Carte tipărită la comandă

Livrare economică 16-30 martie

 Adaugă în coș

Wish list
Gift list
Am citit!
Adaugă în listă

Specificații

ISBN-13: 9783540545378
ISBN-10: 3540545379
Pagini: 496
Ilustrații: XIV, 486 p.
Dimensiuni: 216 x 279 x 26 mm
Greutate: 1.16 kg
Ediția:1991
Editura: Springer Berlin, Heidelberg
Colecția Springer
Seria Lecture Notes in Computer Science

Locul publicării:Berlin, Heidelberg, Germany

Public țintă

Research

Cuprins

Cooperative computing and neural networks.- Neural Net's theory — The specifications of a computational model of memory and information processing in decision-making.- Chaotic neural networks and associative memory.- Nonequilibrium model of neural networks.- A modified algorithm for self-organizing maps based on the Schrödinger equation.- Neural network modelling by means of networks of finite automata.- Adaptive optimization of neural algorithms.- Neural networks with hysteresis type of nonlinearity exhibit global optimization property.- Stability measurement criterion for neural networks of competitive learning.- On the power of networks of majority functions.- Using quadratic perceptrons to reduce interconnection density in multilayer neural networks.- Always trying to write an equation for the brain.- Transformation of control signals for saccadic eye movements.- On the semantics of morphogenesys in photoreceptors.- Implementing a "psychophysical" pattern classifier in a decrementing network.- Contributions of Neural Net's Theory to the understanding of Psychopathological productions in Schizophrenia.- Backpropagation growing networks: Towards local minima elimination.- Methods for encoding in multilayer feed-forward neural networks.- Learning algorithm for feed-forward neural networks with discrete synapses.- Synthesis of adaptive memories with neural networks.- Minimally disturbing learning.- Fuzzy-neunet: A non standard neural network.- Decrementing hamming and Bayesian neural networks: Analog implementations and relative performance.- Dynamic thresholds and attractor neural networks.- Use of genetic algorithms in neural networks definition.- Simulated evolution of modular networks.- Computational experiments with Boltzmann Machines.- An adaptive resonancetheory architecture for the automatic recognition of on-line handwritten symbols of a mathematical editor.- An experimental design advisor and neural network analysis package.- Extending an object oriented concurrent logic language for neural network simulations.- Application and implementation of neural networks in microelectronics.- Cmos implementation of a cellular neural network with dynamically alterable cloning templates.- Systolic implementation of hopfield networks of arbitrary size.- Vlsi fully connected neural networks for the implementation of other topologies.- Backpropagation multilayer perceptron: A modular implementation.- Toroidal neural network processor: Multiple learning algorithm support.- Cmos implementation of synapse matrices with programmable analog weights.- Analog VLSI synapse matrix with enhanced stochastic computations.- Cmos continuous BAM with on chip learning.- An integrated circuit for artificial neural networks.- An application of neural networks to natural scene segmentation.- An approach to isolated word recognition using multilayer perceptrons.- The use of multilayer perceptrons in isolated word recognition.- Continuous speech recognition with the connectionist viterbi training procedure: A summary of recent work.- Recurrent neural networks for speech recognition.- A speech recognition system that integrates neural nets and HMM.- Comparison of neural networks and conventional techniques for automatic recognition of a multilingual speech database.- Optimization problems on concurrent testing solved by neural networks.- Application of high-order hopfield neural networks to the solution of diophantine equations.- Self-organizing feature maps and their application to digital coding of information.- Neural networks as error correcting systems in digital communications.- Application of vector quantization algorithms to protein classification and secondary structure computation.- Application of the LVQ neural method to a stellar catalogue.- Neural network design for mobile robot control following a contour.- A supervisory technique to apply neural networks in control.- Autonomous controller tuning by using a neural network.- Neural networks for water demand time series forecasting.- Using artificial neural networks to aid decision making processes.- Data analysis: How to compare Kohonen neural networks to other techniques?.