基于神经网络的混沌信号源的设计及同步

该文应用具有全局最优的BP改进算法和神经网络的强大学习能力、逼近任意非线性能力和权值调整的灵活性来优化混沌信号源的设计,采用非线性负反馈实现了神经网络混沌信号源之间的同步。计算机仿真结果表明:由于该模型充分利用了逼近任意非线性能力和网络权值调整的灵活性,比单一混沌映射能产生更多的、具有良好相关性能的混沌信号,且易于同步。

Chaotic signal source design and synchronization based on neural networks

Chaotic signal source design based ori neural networks trainecl by modified back propagation algorithm and synchronizatiori by nonlinear feedback method liave been proposed iii this paper. This neural network source can very easily getierate mauy chaotic signals by changing synaptic weights of neural networks. Nonlinear feedback term is used to synchronize chaotic signal sources designed by neural networks. Experimental results show tliat these chaotic sonrces can generate much niore signal than other chaotic sources designed by the single chaotic map, aud are very easily synchronized by the saine nonlinear feedback inethod.