Multiple timescale online learning rules for information maximization with energetic constraints

DOI10.1162/NECO_A_01182MaRDI QIDQ5154156zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Peng Yi, Shinung Ching

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

adaptationinfomax paradigmlearningneural networks

Mathematics Subject Classification ID

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

Recommendations

• On the Maximization of Information Flow Between Spiking Neurons
• Learning spatiotemporally encoded pattern transformations in structured spiking neural networks
• Predictive Coding and the Slowness Principle: An Information-Theoretic Approach
• Spiking Neurons Can Learn to Solve Information Bottleneck Problems and Extract Independent Components
• Efficient Neural Codes That Minimize L_p Reconstruction Error

Cites work

• Computational rationality: A converging paradigm for intelligence in brains, minds, and machines
• scientific article; zbMATH DE number 3148887 (Why is no real title available?)
• scientific article; zbMATH DE number 5284813 (Why is no real title available?)
• Information-theoretic bounds and approximations in neural population coding
• Metabolically efficient information processing
• Mutual information, Fisher information, and efficient coding
• Natural image statistics. A probabilistic approach to early computational vision.
• Recurrent Infomax Generates Cell Assemblies, Neuronal Avalanches, and Simple Cell-Like Selectivity
• Recurrent information optimization with local, metaplastic synaptic dynamics
• Toward a unified theory of efficient, predictive, and sparse coding

Cited in

(3)

• Reverse-engineering neural networks to characterize their cost functions
• Predictive Coding and the Slowness Principle: An Information-Theoretic Approach
• Improved local learning rule for information maximization and related applications

This page was built for publication: Multiple timescale online learning rules for information maximization with energetic constraints

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5154156)