‘Place-cell’ emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space

DOI10.1088/1751-8121/ab7d00OpenAlexW3104390546WikidataQ113091417 ScholiaQ113091417MaRDI QIDQ5061428

J. Tubiana, Moshir Harsh, Simona Cocco, Remi Monasson

Publication date: 12 January 2023

Published in: Journal of Physics A: Mathematical and Theoretical (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.12942

zbMATH Keywords

learningmachine learningreceptive fieldrestricted Boltzmann machine

Mathematics Subject Classification ID

Quantum theory (81-XX) Statistical mechanics, structure of matter (82-XX)

Related Items (2)

Equilibrium and non-equilibrium regimes in the learning of restricted Boltzmann machines* ⋮ An introduction to machine learning: a perspective from statistical physics

Cites Work

• Dynamics of pattern formation in lateral-inhibition type neural fields
• Mathematical biology. Vol. 2: Spatial models and biomedical applications.
• Thermodynamics of restricted Boltzmann machines and related learning dynamics
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Flat Minima
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• Could information theory provide an ecological theory of sensory processing?
• Optimal unsupervised learning
• The space of interactions in neural network models
• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES

This page was built for publication: ‘Place-cell’ emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space