For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
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
Publication Date: 2012/08/01
Online ISSN: 1745-1361
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>>
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.