A memory which forgets
- 11 July 1986
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 19 (10) , L617-L620
- https://doi.org/10.1088/0305-4470/19/10/011
Abstract
The model of Hopfield for a neural network with associative memory is modified by the introduction of a maximum value for the synaptic strength; in this way old patterns are automatically forgotten and the memory recalls only the most recent ones. If the parameters are correctly chosen, the memory never goes into the state of total confusion, characteristic of the Hopfield model.Keywords
This publication has 2 references indexed in Scilit:
- Learning and pattern recognition in spin glass modelsZeitschrift für Physik B Condensed Matter, 1985
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982