Fully-Connected Neural Network Model of Associative Memory as a Test Function of Evolutionary Computations

Akira IMADA  Keijiro ARAKI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E82-D   No.1   pp.318-325
Publication Date: 1999/01/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Bio-Cybernetics and Neurocomputing
Keyword: 
genetic algorithm,  test function,  fully-connected neural network model of associative memory,  

Full Text: PDF>>
Buy this Article




Summary: 
We apply some variants of evolutionary computations to the fully-connected neural network model of associative memory. Among others, when we regard it as a parameter optimization problem, we notice that the model has some favorable properties as a test function of evolutionary computations. So far, many functions have been proposed for comparative study. However, as Whitley and his colleagues suggested, many of the existing common test functions have some problems in comparing and evaluating evolutionary computations. In this paper, we focus on the possibilities of using the fully-connected neural network model as a test function of evolutionary computations.