Threshold Noise as a Source of Volatility in Random Synchronous Asymmetric Neural Networks

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We study the diversity of complex spatio-temporal patterns of random synchronous asymmetric neural networks (RSANNs). Specifically, we investigate the impact of noisy thresholds on network performance and find that there is a narrow and interesting region of noise parameters where RSANNs display specific features of behavior desired for rapidly `thinking' systems: accessibility to a large set of distinct, complex patterns.
17 pages, 11 figures, submitted to Neural Computation

Keywords

Disordered Systems and Neural Networks, Adaptation and Self-Organizing Systems, Biological Physics, Neurons and Cognition

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/27957

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/cond-mat/9712132
 http://arxiv.org/abs/cond-mat/9712132

Collections

arXiv