Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Analysis and Design of Associative Memories Based on Recurrent Neural Networks with Linear Saturation Activation Functions and Time-Varying Delays

Analysis and Design of Associative Memories Based on Recurrent Neural Networks with Linear... 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. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neural Computation MIT Press

Analysis and Design of Associative Memories Based on Recurrent Neural Networks with Linear Saturation Activation Functions and Time-Varying Delays

Neural Computation , Volume 19 (8) – Aug 1, 2007

Loading next page...
 
/lp/mit-press/analysis-and-design-of-associative-memories-based-on-recurrent-neural-xSITWj60AT

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
MIT Press
Copyright
© 2007 Massachusetts Institute of Technology
Subject
Letters
ISSN
0899-7667
eISSN
1530-888X
DOI
10.1162/neco.2007.19.8.2149
pmid
17571941
Publisher site
See Article on Publisher Site

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.

Journal

Neural ComputationMIT Press

Published: Aug 1, 2007

There are no references for this article.