Dense Hebbian neural networks: a replica symmetric picture of unsupervised learning

DOI10.1016/j.physa.2023.129143arXiv2211.14067MaRDI QIDQ6054639

Elena Agliari, Adriano Barra, Francesco Alemanno, Linda Albanese, Daniele Lotito, Andrea Alessandrelli, Dino Pedreschi, Fosca Giannotti

Publication date: 28 September 2023

Published in: Physica A (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2211.14067

zbMATH Keywords

spin glassesHebbian learningcost and loss functions

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• Free energy and complexity of spherical bipartite models
• The mean field Ising model trough interpolating techniques
• Neural networks retrieving Boolean patterns in a sea of Gaussian ones
• The complexity of spherical \(p\)-spin models: a second moment approach
• The spin-glass phase-transition in the Hopfield model with \(p\)-spin interactions
• Broken replica symmetry bounds in the mean field spin glass model
• Generalized Guerra's interpolation schemes for dense associative neural networks
• Deep Boltzmann machines: rigorous results at arbitrary depth
• The solution of the deep Boltzmann machine on the Nishimori line
• The extremal process of critical points of the pure \(p\)-spin spherical spin Glass model
• Universality in Sherrington-Kirkpatrick's spin glass model
• Replica symmetry breaking in dense Hebbian neural networks
• Universality in bipartite mean field spin glasses
• Modeling Brain Function
• Random Matrices and Complexity of Spin Glasses
• A transport equation approach for deep neural networks with quenched random weights
• The adaptive interpolation method for proving replica formulas. Applications to the Curie–Weiss and Wigner spike models
• Neural networks and physical systems with emergent collective computational abilities.
• Replica symmetry breaking in neural networks: a few steps toward rigorous results
• Nonlinear PDEs approach to statistical mechanics of dense associative memories
• On Gaussian spin glass with P-wise interactions

This page was built for publication: Dense Hebbian neural networks: a replica symmetric picture of unsupervised learning