Modified pseudo-inverse neural networks storing correlated patterns

DOI10.1088/0305-4470/25/10/013zbMath0753.92002OpenAlexW2071930128MaRDI QIDQ4020951

No author found.

Publication date: 17 January 1993

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

Full work available at URL: https://doi.org/10.1088/0305-4470/25/10/013

zbMATH Keywords

Hamiltonianthresholdmaximal capacityaverage neural activityHebb learning ruleHopfield model limitpseudo-inverse model limitreplica-symmetric thermodynamic calculationsstrongly correlated patternssymmetric couplings

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) 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)

Hopfield model with planted patterns: a teacher-student self-supervised learning model ⋮ The free energy of a class of Hopfield models

This page was built for publication: Modified pseudo-inverse neural networks storing correlated patterns