Chaos Synergetic Neural Network
Masahiro Marshall Nakagawa · Journal of the Physical Society of Japan · 1995
In this paper we shall put forward a novel chaos synergetic neural network and investigate the dynamic properties in a memory retrieval mode. The present artificial neuron model is characterized by a sinusoidal activation function as well as competitive connections between synergetic neurons. It is elucidated that the present neural network has an ability of the dynamic memory retrievals beyond the conventional chaotic model with such a monotonic mapping as a sigmoid function. This advantage is considered to result from the nonmonotonic property of the analogue periodic mapping which may be accompanied with a chaotic behaviour of the neurons and the synergetic connections. It is also found that the present analogue neural network may be reduced to the previously proposed synergetic neural network if one assumes an identity mapping in the feedback loop instead of the nonlinear periodic one.