The Fisher Information as a Neural Guiding Principle for Independent Component Analysis

The Fisher Information as a Neural Guiding Principle for Independent Component Analysis

The Fisher information constitutes a natural measure for the sensitivity of a probability distribution with respect to a set of parameters. An implementation of the stationarity principle for synaptic learning in terms of the Fisher information results in a Hebbian self-limiting learning rule for sy...

Full description

Bibliographic Details
Main Authors: Rodrigo Echeveste, Samuel Eckmann, Claudius Gros
Format: Article
Language:English
Published: MDPI AG 2015-06-01
Series:Entropy
Subjects:
Fisher information
guiding principle
excess kurtosis
objective functions
synaptic plasticity
Hebbian learning
independent component analysis
Online Access:http://www.mdpi.com/1099-4300/17/6/3838

Internet

http://www.mdpi.com/1099-4300/17/6/3838

Similar Items