Learning and retrieval operational modes for three-layer restricted Boltzmann machines

DOI10.1007/s10955-021-02841-yOpenAlexW3209333113MaRDI QIDQ2060007

Elena Agliari, Giulia Sebastiani

Publication date: 13 December 2021

Published in: Journal of Statistical Physics (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/11573/1586700

zbMATH Keywords

disordered systemsHopfield modelBoltzmann machine

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Time-dependent statistical mechanics (dynamic and nonequilibrium) (82Cxx) Applications of statistical mechanics to specific types of physical systems (82Dxx)

Related Items

A transport equation approach for deep neural networks with quenched random weights

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Training restricted Boltzmann machines: an introduction
• Neural networks retrieving Boolean patterns in a sea of Gaussian ones
• On the equivalence of Hopfield networks and Boltzmann machines
• Generalized Guerra's interpolation schemes for dense associative neural networks
• Non-convex multi-species Hopfield models
• Deep Boltzmann machines: rigorous results at arbitrary depth
• Storing, learning and retrieving biased patterns
• Universality in Sherrington-Kirkpatrick's spin glass model
• Universality in bipartite mean field spin glasses
• Modeling Brain Function
• Free energies of Boltzmann machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit
• A transport equation approach for deep neural networks with quenched random weights
• Dreaming neural networks: rigorous results
• Statistical Mechanics of Disordered Systems
• On the effective initialisation for restricted Boltzmann machines via duality with Hopfield model