Analysis and design of associative memories based on recurrent neural networks with linear saturation activation functions and time-varying delays

Zhigang Zeng, Jun Wang

Research output: Contribution to journalArticlepeer-review

57 Citations (Scopus)

Abstract

In this letter, some sufficient conditions are obtained to guarantee recurrent neural networks with linear saturation activation functions, and time-varying delays have multiequilibria located in the saturation region and the boundaries of the saturation region. These results on pattern characterization are used to analyze and design autoassociative memories, which are directly based on the parameters of the neural networks. Moreover, a formula for the numbers of spurious equilibria is also derived. Four design procedures for recurrent neural networks with linear saturation activation functions and time-varying delays are developed based on stability results. Two of these procedures allow the neural network to be capable of learning and forgetting. Finally, simulation results demonstrate the validity and characteristics of the proposed approach.

Original languageEnglish
Pages (from-to)2149-2182
Number of pages34
JournalNeural computation
Volume19
Issue number8
DOIs
Publication statusPublished - Aug 2007
Externally publishedYes

Fingerprint

Dive into the research topics of 'Analysis and design of associative memories based on recurrent neural networks with linear saturation activation functions and time-varying delays'. Together they form a unique fingerprint.

Cite this