摘要
利用进化策略建立产生混沌序列的优化感知器模型。该模型产生的混沌序列更换调整容易。计算机仿真结果表明 :该模型比BP算法训练的多层感知器模型能更好地重构的混沌吸引子。
A generating chaotic series model, Multi-layer perceptrons(MLP) trained by evolutionary strategy(ES) , is presented in this paper. Changing the output chao tic series generated by this model is very easy. Experimental results show that this ES-trained MLP model can be generated a chaotic series whose attractor can be reconstructed better than that generated by the BP-trained MLP model.
出处
《电讯技术》
北大核心
2000年第5期15-18,共4页
Telecommunication Engineering
