A Local Learning Rule that Enables Information Maximization for Arbitrary Input Distributions

        This note presents a local learning rule that enables a network to maximize the mutual information between input and output vectors. The network's output units may be nonlinear, and the distribution of input vectors is arbitrary. The local algorithm also serves to compute the inverse C-1 of an arbitrary square connection weight matrix.

By: Ralph Linsker

Published in: RC20575 in 1996

This Research Report is not available electronically. Please request a copy from the contact listed below. IBM employees should contact ITIRC for a copy.

Questions about this service can be mailed to reports@us.ibm.com .