混沌在Hopfield联想记忆网络中的应用

The Application of Chaos in Hopfield Associative Memory Networks

将混沌应用到Hofield联想记忆网络中,利用混沌的遍历性和随机性等独特的性质,可以使待联想模式跳出伪模式的吸引域,而到达存储模式的吸引域内,从而解决了Hopfield网络在噪信比较高的情况下,联想成功率较低的问题。仿真结果证明了该方法的有效性。

A new algorithm is proposed in this paper,in which chaos is applied in associative memory.Using the ergod-icity and randomicity of chaos,the algorithm could make the inputting pattern get away from the attraction domain of fault pattern,and arrive at the one of storage pattern,which solves the problem that the success rate of associative memory is low when noise-signal ratio is high.The simulation results prove the validity of the algorithm.