Designing asymmetric neural networks with associative memory
Author:
- 27 December 2004
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 70 (6) , 066137
Abstract
A strategy for designing asymmetric neural networks of associative memory with controllable degree of symmetry and controllable basins of attraction is presented. It is shown that the performance of the networks depends on the degree of the symmetry, and by adjusting the degree of the symmetry the spurious memories or unwanted attractors can be suppressed completely.Keywords
This publication has 23 references indexed in Scilit:
- Complex Adaptive Systems2005
- Associative memory in an analog iterated-map neural networkPhysical Review A, 1990
- Associative recall of memory without errorsPhysical Review A, 1987
- Temporal Association in Asymmetric Neural NetworksPhysical Review Letters, 1986
- Storing Infinite Numbers of Patterns in a Spin-Glass Model of Neural NetworksPhysical Review Letters, 1985
- Spin-glass models of neural networksPhysical Review A, 1985
- Information storage and retrieval in spin-glass like neural networksJournal de Physique Lettres, 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
- ‘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