Neural networks : EURASIP Workshop 1990, Sesimbra, Portugal, February 15{u2013}17, 1990 : proceedings

"The EURASIP workshop contributions collected in this volume have an interdisciplinary character. The authors include psychologists, biologists, engineers and mathematicians as well as computer scientists. The volume starts with two invited papers, by George Cybenko and by Eric Baum, on the formal study of the capabilities of neural networks. The following papers are organized into parts dealing with theory and algorithms, speech processing, image processing, and implementation. The workshop was sponsored by the European Association for Signal Processing without restriction on the origin of participants."--Publisher's website When are k-nearest neighbor and back propagation accurate for feasible sized sets of examples?....Pages 1-25 Complexity theory of neural networks and classification problems....Pages 26-44 Generalization performance of overtrained back-propagation networks....Pages 45-55 Stability of the random neural network model....Pages 56-68 Temporal pattern recognition using EBPS....Pages 69-80 Markovian spatial properties of a random field describing a stochastic neural network: Sequential or parallel implementation?....Pages 81-89 Chaos in neural networks....Pages 90-99 The “moving targets” training algorithm....Pages 100-109 Acceleration techniques for the backpropagation algorithm....Pages 110-119 Rule-injection hints as a means of improving network performance and learning time....Pages 120-129 Inversion in time....Pages 130-140 Cellular neural networks: Dynamic properties and adaptive learning algorithm....Pages 141-150 Improved simulated annealing, Boltzmann machine, and attributed graph matching....Pages 151-160 Artificial dendritic learning....Pages 161-174 A neural net model of human short-term memory development....Pages 175-185 Large vocabulary speech recognition using neural-fuzzy and concept networks....Pages 186-196 Speech feature extraction using neural networks....Pages 197-204 Neural network based continuous speech recognition by combining self organizing feature maps and Hidden Markov Modeling....Pages 205-214 Ultra-small implementation of a neural halftoning technique....Pages 215-224 Application of self-organising networks to signal processing....Pages 225-232 A study of neural network applications to signal processing....Pages 233-242 Simulation machine and integrated implementation of neural networks....Pages 243-266 VLSI implementation of an associative memory based on distributed storage of information....Pages 267-276