Storing Infinite Numbers of Patterns in a Spin-Glass Model of Neural Networks
- 30 September 1985
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 55 (14), 1530-1533
- https://doi.org/10.1103/physrevlett.55.1530
Abstract
The Hopfield model for a neural network is studied in the limit when the number of stored patterns increases with the size of the network, as . It is shown that, despite its spin-glass features, the model exhibits associative memory for , . This is a result of the existence at low temperature of dynamically stable degenerate states, each of which is almost fully correlated with one of the patterns. These states become ground states at . The phase diagram of this rich spin-glass is described.
This publication has 14 references indexed in Scilit:
- Spin-glass models of neural networksPhysical Review A, 1985
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences of the United States of America, 1984
- Collective properties of neural networks: A statistical physics approachBiological Cybernetics, 1984
- Dynamic behavior of nonlinear networksPhysical Review A, 1983
- ‘Unlearning’ has a stabilizing effect in collective memoriesNature, 1983
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences of the United States of America, 1982
- Infinite-ranged models of spin-glassesPhysical Review B, 1978
- Analytic study of the memory storage capacity of a neural networkMathematical Biosciences, 1978
- Solvable spin systems with random interactionsPhysics Letters A, 1976
- The existence of persistent states in the brainMathematical Biosciences, 1974