Stability of the replica-symmetric solution for the information conveyed by a neural network

Publisher Website
Google Scholar
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 nonexistent.

This publication has 12 references indexed in Scilit: