A Local Learning Rule That Enables Information Maximization for Arbitrary Input Distributions
Author:
- 1 November 1997
- journal article
- Published by MIT Press in Neural Computation
- Vol. 9 (8) , 1661-1665
Abstract
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.Keywords
This publication has 4 references indexed in Scilit:
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995
- Local Synaptic Learning Rules Suffice to Maximize Mutual Information in a Linear NetworkNeural Computation, 1992
- Could information theory provide an ecological theory of sensory processing?Network: Computation in Neural Systems, 1992
- How to Generate Ordered Maps by Maximizing the Mutual Information between Input and Output SignalsNeural Computation, 1989