Threshold Noise as a Source of Volatility in Random Synchronous Asymmetric Neural Networks
Disordered Systems and Neural Networks
2007-05-23 v1 adap-org
Adaptation and Self-Organizing Systems
Biological Physics
Neurons and Cognition
Abstract
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.
Keywords
Cite
@article{arxiv.cond-mat/9712132,
title = {Threshold Noise as a Source of Volatility in Random Synchronous Asymmetric Neural Networks},
author = {Henrik Bohr and Patrick McGuire and Chris Pershing and Johann Rafelski},
journal= {arXiv preprint arXiv:cond-mat/9712132},
year = {2007}
}
Comments
17 pages, 11 figures, submitted to Neural Computation