Summary
International Technical Conference on Circuits/Systems, Computers and Communications
2008
Session Number:C7
Session:
Number:C7-2
Statistical Properties and Memory Capacities of Chaos Associative Memory
Masahiro Nakagawa,
pp.-
Publication Date:2008/7/7
Online ISSN:2188-5079
Summary:
In this report we shall propose a chaos dynamic memory model applied to the chaotic autoassociation memory. The present artificial neuron model is properly characterized in terms of a timedependent sinusoidal activation function to involve a transient chaotic dynamics as well as the energy steepest descent strategy. It is elucidated that the present neural network has a remarkable retrieval ability beyond the conventional models with such a monotonous activation function as sigmoidal one. This advantage is found to result from the property of the analogue periodic mapping accompanied with a chaotic behaviour of the neurons as well as the symmetry of the dynamic equation.