Statistical Properties and Memory Capacities of Chaos Associative Memory
Masahiro Marshall Nakagawa · ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications · 2008
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.