NEURAL NETWORKS AS OPTIMAL INFORMATION PROCESSORS

1 October 1994

journal article
Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics C

Vol. 5 (5) , 855-862
https://doi.org/10.1142/s0129183194000994

Abstract

We explore the properties of a feed-forward neural network whose couplings are chosen in such a way as to maximize the input-output mutual information, in the case in which the input-output channel is affected by noise.

Keywords

MUTUAL INFORMATION
FEED FORWARD NEURAL NETWORK
NEURAL NETWORKS
NEURAL NETWORK
INFORMATION THEORY
SIGNAL ANALYSIS
INPUT OUTPUT

This publication has 0 references indexed in Scilit: