Improved local learning rule for information maximization and related applications

DOI10.1016/J.NEUNET.2005.01.002MaRDI QIDQ557628zbMATH OpenOpenAlexFDO

Authors Ralph Linsker

Publication date 30 June 2005

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2005.01.002

zbMATH Keywords

Hebbian learningCovariance matrixInfomaxMutual informationSensory processing

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Independent component analysis by general nonlinear Hebbian-like learning rules
• Coherent infomax as a computational goal for neural systems
• Nonlinear feedforward networks with stochastic outputs: infomax implies redundancy reduction
• From neural learning to independent components
• Multiple timescale online learning rules for information maximization with energetic constraints

Cites work

• scientific article; zbMATH DE number 1569102 (Why is no real title available?)
• Updating the Inverse of a Matrix

Cited in

(9)

• Constrained information maximization by free energy minimization
• Information estimators for weighted observations
• Simplified information maximization for improving generalization performance in multilayered neural networks
• Neural network learning of optimal Kalman prediction and control
• An information global minimization algorithm using the local improvement technique
• Fast search local extremum for maximal information coefficient (MIC)
• Similarity interaction in information-theoretic self-organizing maps
• On the Use of Neuro-fuzzy Techniques for Analyzing Experimental Surface Electromyographic Data
• Self-enhancement learning: target-creating learning and its application to self-organizing maps

This page was built for publication: Improved local learning rule for information maximization and related applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q557628)