Statistical mechanics of unsupervised feature learning in a restricted Boltzmann machine with binary synapses

DOI10.1088/1742-5468/AA6DDCzbMath1457.82323arXiv1612.01717OpenAlexW3104798141MaRDI QIDQ3303061

Haiping Huang

Publication date: 11 August 2020

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

Full work available at URL: https://arxiv.org/abs/1612.01717

Mathematics Subject Classification ID

Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Related Items (11)

Analyticity of the energy in an Ising spin glass with correlated disorder ⋮ Minimal model of permutation symmetry in unsupervised learning ⋮ Mean-field inference methods for neural networks ⋮ The emergence of a concept in shallow neural networks ⋮ Hopfield model with planted patterns: a teacher-student self-supervised learning model ⋮ Role of zero synapses in unsupervised feature learning ⋮ Non-convex multi-species Hopfield models ⋮ Thermodynamics of restricted Boltzmann machines and related learning dynamics ⋮ Learning a restricted Boltzmann machine using biased Monte Carlo sampling ⋮ Parallel learning by multitasking neural networks ⋮ Gaussian-spherical restricted Boltzmann machines

Uses Software

• darch
• Omniglot
• BinaryConnect

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• An iterative construction of solutions of the TAP equations for the Sherrington-Kirkpatrick model
• Human-level concept learning through probabilistic program induction
• Reducing the Dimensionality of Data with Neural Networks
• Constructing Free-Energy Approximations and Generalized Belief Propagation Algorithms
• Information, Physics, and Computation
• Statistical Physics of Spin Glasses and Information Processing
• Spin-glass theory for pedestrians
• A Fast Learning Algorithm for Deep Belief Nets

This page was built for publication: Statistical mechanics of unsupervised feature learning in a restricted Boltzmann machine with binary synapses