Associative memories via artificial neural networks
- 1 April 1990
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Magazine
- Vol. 10 (3) , 6-17
- https://doi.org/10.1109/37.55118
Abstract
Several design techniques that can be used for continuous-time and discrete-time neural networks to realize associative memories are presented. Associative memory is discussed, and neural network models are presented. Some stability concepts are outlined. The applicability of these techniques is demonstrated by means of specific examples that illustrate strengths and weaknesses.Keywords
This publication has 23 references indexed in Scilit:
- A synthesis procedure for Hopfield's continuous-time associative memoryIEEE Transactions on Circuits and Systems, 1990
- Analysis and synthesis of a class of neural networks: linear systems operating on a closed hypercubeIEEE Transactions on Circuits and Systems, 1989
- Analysis and synthesis of a class of neural networks: variable structure systems with infinite grainIEEE Transactions on Circuits and Systems, 1989
- Qualitative analysis of neural networksIEEE Transactions on Circuits and Systems, 1989
- Cellular neural networks: theoryIEEE Transactions on Circuits and Systems, 1988
- Qualitative analysis and synthesis of a class of neural networksIEEE Transactions on Circuits and Systems, 1988
- Collective computational properties of neural networks: New learning mechanismsPhysical Review A, 1986
- Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuitIEEE Transactions on Circuits and Systems, 1986
- Information storage and retrieval in spin-glass like neural networksJournal de Physique Lettres, 1985
- ‘Unlearning’ has a stabilizing effect in collective memoriesNature, 1983