Energy functional and fixed points of a neural network
Disordered Systems and Neural Networks
2012-03-24 v1
Abstract
A dynamic system, which is used in the neural network theory, Ising spin glasses and factor analysis, has been investigated. The properties of the connection matrix, which guarantee the coincidence of the set of the fixed points of the dynamic system with the set of the local minima of the energy functional, have been determined. The influence of the connection matrix diagonal elements on the structure of the fixed points set has been investigated.
Keywords
Cite
@article{arxiv.cond-mat/9706280,
title = {Energy functional and fixed points of a neural network},
author = {Leonid B. Litinskii},
journal= {arXiv preprint arXiv:cond-mat/9706280},
year = {2012}
}
Comments
LaTex, 7 pages, e-mail: [email protected]