Dynamics of Interacting Neural Networks

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

The dynamics of interacting perceptrons is solved analytically. For a directed flow of information the system runs into a state which has a higher symmetry than the topology of the model. A symmetry breaking phase transition is found with increasing learning rate. In addition it is shown that a system of interacting perceptrons which is trained on the history of its minority decisions develops a good strategy for the problem of adaptive competition known as the Bar Problem or Minority Game.
9 pages, 3 figures; typos corrected, content reorganized

Keywords

Disordered Systems and Neural Networks

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/29366

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/cond-mat/9906058
 http://arxiv.org/abs/cond-mat/9906058

Collections

arXiv