Adaptive balancing of exploration and exploitation around the edge of chaos in internal-chaos-based learning

DOI10.1016/J.NEUNET.2020.08.002MaRDI QIDQ2057742zbMATH OpenOpenAlexWikidataFDO

Authors Toshitaka Matsuki, Katsunari Shibata

Publication date 7 December 2021

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2020.08.002

zbMATH Keywords

chaotic neural networkedge of chaosexploration-exploitation dilemmareservoir computingreward-modulated Hebbian learning

Mathematics Subject Classification ID

Strange attractors, chaotic dynamics of systems with hyperbolic behavior (37D45) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Learning, exploration and chaotic policies
• scientific article; zbMATH DE number 14852
• Adaptive intelligence learning for nonlinear chaotic systems
• Adaptive functional systems: learning with chaos
• Chaotic exploration and learning of locomotion behaviors

Cites work

• Edge of chaos and prediction of computational performance for neural circuit models
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• The criticality hypothesis: how local cortical networks might optimize information processing

Cited in

(4)

• Learning, exploration and chaotic policies
• CHAOTIC EXPLORATION EFFECTS ON REINFORCEMENT LEARNING IN SHORTCUT MAZE TASK
• Sensitivity -- local index to control chaoticity or gradient globally
• Learning performance of cerebellar circuit depends on diversity and chaoticity of spiking patterns in granule cells: a simulation study

Describes a project that uses

Uses Software

• ImageNet
• AlexNet

This page was built for publication: Adaptive balancing of exploration and exploitation around the edge of chaos in internal-chaos-based learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2057742)