Stability of the replica symmetric solution for the information conveyed by by a neural network
Disordered Systems and Neural Networks
2009-10-30 v2 q-bio
Abstract
The information that a pattern of firing in the output layer of a feedforward network of threshold-linear neurons conveys about the network's inputs is considered. A replica-symmetric solution is found to be stable for all but small amounts of noise. The region of instability depends on the contribution of the threshold and the sparseness: for distributed pattern distributions, the unstable region extends to higher noise variances than for very sparse distributions, for which it is almost nonexistant.
Keywords
Cite
@article{arxiv.cond-mat/9709219,
title = {Stability of the replica symmetric solution for the information conveyed by by a neural network},
author = {Simon Schultz and Alessandro Treves},
journal= {arXiv preprint arXiv:cond-mat/9709219},
year = {2009}
}
Comments
19 pages, LaTeX, 5 figures. Also available at http://www.mrc-bbc.ox.ac.uk/~schultz/papers.html . Submitted to Phys. Rev. E Minor changes