On a model of associative memory with huge storage capacity

DOI10.1007/S10955-017-1806-YzbMath1382.82037arXiv1702.01929OpenAlexW3102889924MaRDI QIDQ2410291

Franck Vermet, Sven Upgang, Judith Heusel, Mete Demircigil, Matthias Loewe

Publication date: 17 October 2017

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

Full work available at URL: https://arxiv.org/abs/1702.01929

zbMATH Keywords

neural networksassociative memoryHopfield modelexponential interaction

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Related Items (2)

Index structures for fast similarity search for binary vectors ⋮ Quaternion-valued recurrent projection neural networks on unit quaternions

Cites Work

• Unnamed Item
• Unnamed Item
• Lower bounds on the restitution error in the Hopfield model
• On the storage capacity of Hopfield models with correlated patterns
• Rigorous results for the Hopfield model with many patterns
• The spin-glass phase-transition in the Hopfield model with \(p\)-spin interactions
• The capacity of \(q\)-state Potts neural networks with parallel retrieval dynamics
• The storage capacity of the Hopfield model and moderate deviations
• The capacity of the Hopfield associative memory
• Sharp upper bounds on perfect retrieval in the Hopfield model
• Neural networks and physical systems with emergent collective computational abilities.

This page was built for publication: On a model of associative memory with huge storage capacity