Dynamical Associative Memory: The Properties of the New Weighted Chaotic Adachi Neural Network

Guangchun LUO  Jinsheng REN  Ke QIN  

IEICE TRANSACTIONS on Information and Systems   Vol.E95-D   No.8   pp.2158-2162
Publication Date: 2012/08/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E95.D.2158
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Biocybernetics, Neurocomputing
chaotic neural networks,  chaotic pattern recognition,  dynamical associative memory,  Adachi Neural Network,  

Full Text: PDF>>
Buy this Article

A new training algorithm for the chaotic Adachi Neural Network (AdNN) is investigated. The classical training algorithm for the AdNN and it's variants is usually a “one-shot” learning, for example, the Outer Product Rule (OPR) is the most used. Although the OPR is effective for conventional neural networks, its effectiveness and adequateness for Chaotic Neural Networks (CNNs) have not been discussed formally. As a complementary and tentative work in this field, we modified the AdNN's weights by enforcing an unsupervised Hebbian rule. Experimental analysis shows that the new weighted AdNN yields even stronger dynamical associative memory and pattern recognition phenomena for different settings than the primitive AdNN.