A Genetic Algorithm Creates New Attractors in an Associative Memory Network by Pruning Synapses Adaptively

Akira IMADA  Keijiro ARAKI  

IEICE TRANSACTIONS on Information and Systems   Vol.E81-D   No.11   pp.1290-1297
Publication Date: 1998/11/25
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Bio-Cybernetics and Neurocomputing
genetic algorithm,  fully connected neural network model of associative memory,  storage capacity,   synaptic symmetry and dilution,  

Full Text: PDF>>
Buy this Article

We apply evolutionary algorithms to neural network model of associative memory. In the model, some of the appropriate configurations of the synaptic weights allow the network to store a number of patterns as an associative memory. For example, the so-called Hebbian rule prescribes one such configuration. However, if the number of patterns to be stored exceeds a critical amount (over-loaded), the ability to store patterns collapses more or less. Or, synaptic weights chosen at random do not have such an ability. In this paper, we describe a genetic algorithm which successfully evolves both the random synapses and over-loaded Hebbian synapses to function as associative memory by adaptively pruning some of the synaptic connections. Although many authors have shown that the model is robust against pruning a fraction of synaptic connections, improvement of performance by pruning has not been explored, as far as we know.