Statistical physics of learning in high-dimensional chaotic systems

DOI10.1088/1742-5468/AD082DMaRDI QIDQ6611431zbMATH OpenFDO

Authors Samantha J. Fournier, Pierfrancesco Urbani

Publication date 26 September 2024

Published in Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1088/1742-5468/AD082D

zbMATH Keywords

learning theoryneuronal networksspin glasses

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Recommendations

• The Road to Chaos by Time-Asymmetric Hebbian Learning in Recurrent Neural Networks
• scientific article; zbMATH DE number 1304847
• “FORCE” learning in recurrent neural networks as data assimilation
• scientific article; zbMATH DE number 1843140
• Chaoticity generated by a learning model

Cites work

• Disordered high-dimensional optimal control
• Exit probabilities and optimal stochastic control
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• The effective noise of stochastic gradient descent

Cited in

(2)

• High-dimensional dynamical systems: co-existence of attractors, phase transitions, maximal Lyapunov exponent and response to periodic drive
• Chaos in high-dimensional dynamical systems with tunable non-reciprocity

This page was built for publication: Statistical physics of learning in high-dimensional chaotic systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6611431)