Physical Review Letters · 1987 · 262 citations · 14 references
ComputingComputer ScienceMachine LearningPattern FormationSynaptic PlasticityLearning In Neural SystemsNeural ModelingNeural NetworksNeuronal DynamicsLearning RulesNeural Network ModelingPatterns
Two simple storing prescriptions are presented for neural network models of N two-state neurons. These rules are local and allow the embedding of correlated patterns without errors in a network of spin-glass type. Starting from an arbitrary configuration of synaptic bonds, up to N patterns can be stored by successive modification of the synaptic efficacies. Proofs for the convergence are given. Extensions of these rules are possible.
14
Solvable Model of a Spin-Glass
David C. Sherrington, Scott Kirkpatrick · Physical Review Letters · 1975 · 4.3K citations
Donald Greenspan, Brice Carnahan, H. Luther et al. · Mathematics of Computation · 1970 · 3.5K citations