AN ANALYSIS ON MINIMUM SEARCHING PRINCIPLE OF CHAOTIC NEURAL-NETWORK

This article analyzes dynamics of the chaotic neural network and minim um searching principle of this network. First it is indicated that the dynamics of the chaotic neural network is described like a gradient d escent, and the chaotic neural network can roughly find out a local mi nimum point of a quadratic function using its attractor. Secondly It i s guaranteed that the vertex corresponding a local minimum point deriv ed from the chaotic neural network has a lower value of the objective function. Then it is confirmed that the chaotic neural network can esc ape an invalid local minimum and find out a reasonable one.