Wolfgang Kinzel
Published 1997-04-11Version 1
The cooperative behaviour of interacting neurons and synapses is studied using models and methods from statistical physics. The competition between training error and entropy may lead to discontinuous properties of the neural network. This is demonstrated for a few examples: Perceptron, associative memory, learning from examples, generalization, multilayer networks, structure recognition, Bayesian estimate, on-line training, noise estimation and time series generation.
Comments: Plenary talk for MINERVA workshop on mesoscopics, fractals and neural networks, Eilat, March 1997 Postscript File
Neural Networks, Game Theory and Time Series Generation
Retrieval dynamics of neural networks for sparsely coded sequential patterns
Stochastic learning in a neural network with adapting synapses
