Phase Transitions of Neural Networks
Disordered Systems and Neural Networks
2017-02-08 v1 q-bio
Abstract
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.
Keywords
Cite
@article{arxiv.cond-mat/9704098,
title = {Phase Transitions of Neural Networks},
author = {Wolfgang Kinzel},
journal= {arXiv preprint arXiv:cond-mat/9704098},
year = {2017}
}
Comments
Plenary talk for MINERVA workshop on mesoscopics, fractals and neural networks, Eilat, March 1997 Postscript File