Hopfield model with planted patterns: a teacher-student self-supervised learning model

DOI10.1016/j.amc.2023.128253arXiv2304.13710OpenAlexW4385438032MaRDI QIDQ6096393

Luca Camanzi, Daniele Tantari, Francesco Alemanno, Gianluca Manzan

Publication date: 12 September 2023

Published in: Applied Mathematics and Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2304.13710

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Equilibrium statistical mechanics (82Bxx) Time-dependent statistical mechanics (dynamic and nonequilibrium) (82Cxx)

Cites Work

• Unnamed Item
• Legendre duality of spherical and Gaussian spin glasses
• Non-convex multipartite ferromagnets
• Anergy in self-directed B lymphocytes: a statistical mechanics perspective
• Entropy, large deviations, and statistical mechanics.
• On the storage capacity of Hopfield models with correlated patterns
• Hierarchical neural networks perform both serial and parallel processing
• Neural networks retrieving Boolean patterns in a sea of Gaussian ones
• Overlap synchronisation in multipartite random energy models
• On the equivalence of Hopfield networks and Boltzmann machines
• Non-convex multi-species Hopfield models
• Deep Boltzmann machines: rigorous results at arbitrary depth
• A remark on the spherical bipartite spin glass
• Annealing and replica-symmetry in deep Boltzmann machines
• The solution of the deep Boltzmann machine on the Nishimori line
• Storing, learning and retrieving biased patterns
• Multi-species mean field spin glasses. Rigorous results
• The adaptive interpolation method: a simple scheme to prove replica formulas in Bayesian inference
• The multi-species mean-field spin-glass on the Nishimori line
• Effect of spatial correlations on Hopfield neural network and dense associative memories
• Data quality for the inverse lsing problem
• Immune networks: multi-tasking capabilities at medium load
• Immune networks: multitasking capabilities near saturation
• Metastable states in the hierarchical Dyson model drive parallel processing in the hierarchical Hopfield network
• Statistical mechanics of unsupervised feature learning in a restricted Boltzmann machine with binary synapses
• Information, Physics, and Computation
• The Nishimori line and Bayesian statistics
• Modified pseudo-inverse neural networks storing correlated patterns
• Hebbian learning, its correlation catastrophe, and unlearning
• High storage capacity in the Hopfield model with auto-interactions—stability analysis
• Statistical Physics of Spin Glasses and Information Processing
• Mismatching as a tool to enhance algorithmic performances of Monte Carlo methods for the planted clique model
• Minimal model of permutation symmetry in unsupervised learning
• Legendre equivalences of spherical Boltzmann machines
• Neural networks and physical systems with emergent collective computational abilities.
• About a solvable mean field model of a Gaussian spin glass
• The free energy in a multi-species Sherrington-Kirkpatrick model