Nonlinear feedforward networks with stochastic outputs: infomax implies redundancy reduction

DOI10.1088/0954-898X/9/2/004zbMATH Open0908.68150OpenAlexW4231105908MaRDI QIDQ4211331FDOQ4211331

Authors: Jean-Pierre Nadal, Nicolas J.-B. Brunel, Néstor Parga 

Publication date: 16 September 1998

Full work available at URL: https://doi.org/10.1088/0954-898x/9/2/004

Recommendations

• Maximization of mutual information in a linear noisy network: a detailed study
• Nonlinear neurons in the low-noise limit: a factorial code maximizes information transfer
• About the maximum information and maximum likelihood principles.

zbMATH Keywords

feedforward neural network

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cited In (6)

• Remarks on Invariance in the Primary Visual Systems of Mammals
• Redundancy reduction with information-preserving nonlinear maps
• Improved local learning rule for information maximization and related applications
• About the maximum information and maximum likelihood principles.
• Title not available (Why is that?)
• Quantifying Neurotransmission Reliability Through Metrics-Based Information Analysis

This page was built for publication: Nonlinear feedforward networks with stochastic outputs: infomax implies redundancy reduction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4211331)