A new strategy for designing bidirectional associative memories

Authors:
Gengsheng Zheng;Sidney Nascimento Givigi;Weiyu Zheng
Affiliations:
Gengsheng Zheng, School of Computer Science and Technology, Wuhan University, Wuhan, Hubei, China;Sidney Nascimento Givigi Junior, Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada;Weiyu Zheng, Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
Year:
2005

Citing 1
Cited 7

Bidirectional associative memories

IEEE Transactions on Systems, Man and Cybernetics

Alpha---Beta bidirectional associative memories: theory and applications

Neural Processing Letters
Object recognition and tracking with maximum likelihood bidirectional associative memory networks

Neurocomputing
Optimum associative neural network utilizing maximum likelihood

Neurocomputing
From Bidirectional Associative Memory to a noise-tolerant, robust Protein Processor Associative Memory

Artificial Intelligence
Complexity of alpha-beta bidirectional associative memories

MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence
A new model of BAM: alpha-beta bidirectional associative memories

ISCIS'06 Proceedings of the 21st international conference on Computer and Information Sciences
Bidirectional associative memories: Different approaches

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

A comprehensive strategy for bidirectional associative memories (BAMs) is presented, which enhances storage capacity greatly. The design strategy combines the dummy augmentation encoding method with optimal gradient descent algorithm. The proposed method increases the storage capacity performance of BAM to its upper limit compared with original Kosko method and optimal gradient descent algorithm. Computer simulations and comparison are given based on three methods to demonstrate the performance improvement of the proposed strategy.