Neural networks have proved to be useful models of associative memories. After a brief review of the standard Hopfield model we discuss how to introduce some realistic features such as categorization of the stored information and asymmetric synapsis.
On the behavior of some associative neural networks
β Scribed by R. Braham; J. O. Hamblen
- Publisher
- Springer-Verlag
- Year
- 1988
- Tongue
- English
- Weight
- 666 KB
- Volume
- 60
- Category
- Article
- ISSN
- 0340-1200
No coin nor oath required. For personal study only.
β¦ Synopsis
Since Hopfield published his work on an associative memory model, a large number of works have studied the model from several angles and showed in particular its weaknesses, and presented ways to overcome them. Most of the proposed solutions seem to us however not biologically plausible. In this paper we present a simple statistical analysis of two networks similar to the Hopfield net, and show that the usage of positive feedback enhances the net recognizing capability without jeopardizing the stability. We also describe a layered parallel network composed of modules, each module being a modified Hopfield net. We finally present computer simulation results to support our analytical findings. The most important principles of this network are supported by data from the world of neurobiology.
π SIMILAR VOLUMES
Synapses are essential elements for computation and information storage in both real and artificial neural systems. An artificial synapse needs to remember its past dynamical history, store a continuous set of states, and be "plastic" according to the pre-synaptic and post-synaptic neuronal activity
The results of a computer study of the continuous-time version of macrodynamical system of equations governing the recalling process of associative memory neural networks are presented. The comparative analysis of two models of associative memory network--recurrent (autoassociative) and layered (fee