Thermodynamics of bidirectional associative memories

DOI10.1088/1751-8121/accc60arXiv2211.09694OpenAlexW4365597485MaRDI QIDQ6046084

Giovanni Catania, Adriano Barra, B. Seoane, Aurélien Decelle

Publication date: 15 May 2023

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

Full work available at URL: https://arxiv.org/abs/2211.09694

zbMATH Keywords

neural networksassociative memoryHopfield modelrestricted Boltzmann machinesspin-glasses

Mathematics Subject Classification ID

Biology and other natural sciences (92-XX) Statistical mechanics, structure of matter (82-XX)

Cites Work

• Unnamed Item
• Parallel retrieval of correlated patterns: from Hopfield networks to Boltzmann machines
• The mean field Ising model trough interpolating techniques
• Neural networks retrieving Boolean patterns in a sea of Gaussian ones
• On the equivalence of Hopfield networks and Boltzmann machines
• Thermodynamics of restricted Boltzmann machines and related learning dynamics
• Deep Boltzmann machines: rigorous results at arbitrary depth
• Annealing and replica-symmetry in deep Boltzmann machines
• Macroscopic limit of a bipartite Curie-Weiss model: a dynamical approach
• The adaptive interpolation method: a simple scheme to prove replica formulas in Bayesian inference
• Universality in Sherrington-Kirkpatrick's spin glass model
• Replica symmetry breaking in dense Hebbian neural networks
• Universality in bipartite mean field spin glasses
• Reducing the Dimensionality of Data with Neural Networks
• Training Products of Experts by Minimizing Contrastive Divergence
• Analogue neural networks on correlated random graphs
• Bipartite Mean Field Spin Systems. Existence and Solution
• A spherical Hopfield model
• The Little–Hopfield model on a sparse random graph
• Analytic solution of attractor neural networks on scale-free graphs
• The adaptive interpolation method for proving replica formulas. Applications to the Curie–Weiss and Wigner spike models
• A quantitative analysis of a generalized Hopfield model that stores and retrieves mismatched memory patterns
• Replica symmetry breaking in neural networks: a few steps toward rigorous results
• On the effective initialisation for restricted Boltzmann machines via duality with Hopfield model

This page was built for publication: Thermodynamics of bidirectional associative memories