Information storage and retrieval in spin-glass like neural networks
- 1 January 1985
- journal article
- Published by EDP Sciences in Journal de Physique Lettres
- Vol. 46 (8) , 359-365
- https://doi.org/10.1051/jphyslet:01985004608035900
Abstract
The link between the structure of a neural network and its attractor states is investigated, with a view to designing associative memories based on such networks. It is shown that, for any preassigned set of states to be memorized, the parameters of the network can be completely calculated in most cases so as to guaranteee the stability of these states. The spin glass formulation of the neural network problem leads to particularly simple results which, in some cases, allow an analytical evaluation of the attractivity of the memorized statesKeywords
This publication has 10 references indexed in Scilit:
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984
- Adaptation and Self-Repair in Parallel Computing StructuresPhysical Review Letters, 1984
- Dynamics of self-organization in complex adaptive networksJournal of Statistical Physics, 1984
- Collective properties of neural networks: A statistical physics approachBiological Cybernetics, 1984
- An application of physical methods to the computer aided design of electronic circuitsJournal de Physique Lettres, 1984
- Order Parameter for Spin-GlassesPhysical Review Letters, 1983
- Optimization by Simulated AnnealingScience, 1983
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- A theory for the acquisition and loss of neuron specificity in visual cortexBiological Cybernetics, 1979
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1943