摘要
本文以布拉格声光双稳混池系统之系统辨识为例，研究了利用前向神经网络对混沌光学系统进行快速系统辨识的可能性，其计算机仿真实验结果表明，由静态BP算法训练的三层前向种经网络，在混优催化算法的支持下可克服BP算法训练时间沉长的缺点，在较少的训练次数内即已成为一良好的混沌光学系统辨识器，因而可用来高效率地处理混沌光学时间序列以进行混沌光学系统的动力学重构。
The feasibility of identifying the chaotic optical system via BP NN suppotted by chaos speed-up alsorithm is raised and demonstrted in this paper with taking the identification of the Bragg acoustooptic bistub1e & chaotic system as example. The resu1t of the computer simu1ation shows that, the three layer foreward NN, if trained with the BP algorithm supported by the chaos speed-up a1gorithm, is indeed a fine identifier with less training iterations than usual, thus it could be used tO reconstruct the dynamics of the chaotic optica1 system fromits output series high efficiently.
出处
《长春光学精密机械学院学报》
1995年第4期6-12,共7页
Journal of Changchun Institute of Optics and Fine Mechanics
