Controlling Chaos in a Neural Network Based on the Orbit Space Compression
基于轨道空间压缩的混沌神经网络控制

In this paper, a controlling chaos method of the orbit space compression is proposed for a Chaotic Neural Network(CNN). The computer simulation of the chaotic behaviors of the CNN proves that each pattern can be controlled using the orbit space compression. Starting from any initial state the CNN can converge in a stored pattern or its inverse pattern, which has the smallest Hamming distance with the initial state. The controlling method of the orbit space compression shows clear physical meaning and can be easily carried out.