Multiple Timescale Online Learning Rules for Information Maximization with Energetic Constraints

DOI10.1162/neco_a_01182zbMath1471.92041OpenAlexW2921409828WikidataQ92441352 ScholiaQ92441352MaRDI QIDQ5154156

Shinung Ching, Peng Yi

Publication date: 1 October 2021

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/neco_a_01182

zbMATH Keywords

neural networkslearningadaptationinfomax paradigm

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Memory and learning in psychology (91E40)

Cites Work

• Unnamed Item
• Unnamed Item
• Natural image statistics. A probabilistic approach to early computational vision.
• Metabolically Efficient Information Processing
• Computational rationality: A converging paradigm for intelligence in brains, minds, and machines
• Recurrent Infomax Generates Cell Assemblies, Neuronal Avalanches, and Simple Cell-Like Selectivity
• Toward a unified theory of efficient, predictive, and sparse coding
• Information-Theoretic Bounds and Approximations in Neural Population Coding
• Mutual Information, Fisher Information, and Efficient Coding
• Recurrent Information Optimization with Local, Metaplastic Synaptic Dynamics

This page was built for publication: Multiple Timescale Online Learning Rules for Information Maximization with Energetic Constraints