论文信息 - A Local Learning Rule That Enables Information Maximization for Arbitrary Input Distributions

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 C1 of an arbitrary square connection weight matrix.

Ralph Linsker | R. Linsker

[1] Ralph Linsker,et al. How to Generate Ordered Maps by Maximizing the Mutual Information between Input and Output Signals , 1989, Neural Computation.

[2] Ralph Linsker,et al. Local Synaptic Learning Rules Suffice to Maximize Mutual Information in a Linear Network , 1992, Neural Computation.

[3] Ralph Linsker,et al. Self-organization in a perceptual network , 1988, Computer.

[4] Ralph Linsker,et al. An Application of the Principle of Maximum Information Preservation to Linear Systems , 1988, NIPS.

[5] Andrzej Cichocki,et al. A New Learning Algorithm for Blind Signal Separation , 1995, NIPS.

[6] Terrence J. Sejnowski,et al. An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.