On the equivalence of Hopfield networks and Boltzmann machines

DOI10.1016/j.neunet.2012.06.003zbMath1258.68112arXiv1105.2790OpenAlexW2125150881WikidataQ45960406 ScholiaQ45960406MaRDI QIDQ1941600

Alberto Bernacchia, Pierluigi Contucci, Adriano Barra, Enrica Santucci

Publication date: 13 March 2013

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1105.2790

zbMATH Keywords

statistical mechanicsHopfield networksBoltzmann machines

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Lattice systems (Ising, dimer, Potts, etc.) and systems on graphs arising in equilibrium statistical mechanics (82B20)

Related Items (29)

Anergy in self-directed B lymphocytes: a statistical mechanics perspective ⋮ A transport equation approach for deep neural networks with quenched random weights ⋮ On the Marchenko–Pastur law in analog bipartite spin-glasses ⋮ Minimal model of permutation symmetry in unsupervised learning ⋮ Interpolating between boolean and extremely high noisy patterns through minimal dense associative memories ⋮ Statistical physics and representations in real and artificial neural networks ⋮ Neural networks retrieving Boolean patterns in a sea of Gaussian ones ⋮ A multivariate extension of mutual information for growing neural networks ⋮ Generalized pinning synchronization of delayed Cohen-Grossberg neural networks with discontinuous activations ⋮ A new mechanical approach to handle generalized Hopfield neural networks ⋮ Dynamics of neural networks over undirected graphs ⋮ Interacting dreaming neural networks ⋮ Thermodynamics of bidirectional associative memories ⋮ The emergence of a concept in shallow neural networks ⋮ On the effective initialisation for restricted Boltzmann machines via duality with Hopfield model ⋮ Hopfield model with planted patterns: a teacher-student self-supervised learning model ⋮ Annealing and replica-symmetry in deep Boltzmann machines ⋮ An introduction to machine learning: a perspective from statistical physics ⋮ Multitasking attractor networks with neuronal threshold noise ⋮ Dreaming neural networks: rigorous results ⋮ Non-convex multi-species Hopfield models ⋮ Thermodynamics of restricted Boltzmann machines and related learning dynamics ⋮ Storing, learning and retrieving biased patterns ⋮ Multi-species mean field spin glasses. Rigorous results ⋮ Mittag-Leffler stability of fractional-order neural networks in the presence of generalized piecewise constant arguments ⋮ Learning Compositional Representations of Interacting Systems with Restricted Boltzmann Machines: Comparative Study of Lattice Proteins ⋮ Learning and retrieval operational modes for three-layer restricted Boltzmann machines ⋮ Free energies of Boltzmann machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit ⋮ Replica symmetry breaking in neural networks: a few steps toward rigorous results

Uses Software

• darch

Cites Work

• Unnamed Item
• The mean field Ising model trough interpolating techniques
• Mathematical aspects of spin classes and neural networks
• On the stability of the quenched state in mean-field spin-glass models
• Reducing the Dimensionality of Data with Neural Networks
• Learning Deep Architectures for AI
• Introduction to Theoretical Neurobiology
• Self-Consistent Method for Density Estimation
• Neural networks and physical systems with emergent collective computational abilities.
• About a solvable mean field model of a Gaussian spin glass
• The replica symmetric approximation of the analogical neural network

This page was built for publication: On the equivalence of Hopfield networks and Boltzmann machines