Notes on Bell-Sejnowski PDF-matching neuron

Authors:
Simone Fiori
Affiliations:
Faculty of Engineering, University of Perugia, Loc. Pentima bassa, 21, I-05100 Terni, Italy
Venue:
Neural Computation
Year:
2002

Citing 2
Cited 1

An information-maximization approach to blind separation and blind deconvolution

Neural Computation
Blind signal processing by the adaptive activation function neurons

Neural Networks

Closed-form expressions of some stochastic adapting equations for nonlinear adaptive activation function neurons

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article investigates the behavior of a single-input, single-unit neuron model of the Bell-Sejnowski class, which learn through the maximum-entropy principle, in order to understand its probability density function matching ability.