Analysis of stationary dynamic neural networks on the basis of statistical linearizatoin method

被引:0
作者
Ptitchkin, VA [1 ]
机构
[1] Belarussian State Univ Informat & Radioelect, Minsk 220027, BELARUS
来源
8TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING, VOLS 1-3, PROCEEDING | 2001年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The approximate methods are proposed for determination of statistical moments of order 2 on the output of finite-memory dynamic neural networks and recurrent neural networks on the basis of similar characteristics of steady-state input process. The paper examines special features of application of statistical linearization method for analysis of the above-mentioned neural networks included in the closed-loop control contour.
引用
收藏
页码:1544 / 1549
页数:6
相关论文
共 6 条
  • [1] PTITCHKIN V, 1999, P INT C NEUR NETW AR, P40
  • [2] PTITCHKIN VA, 2001, NEUROCOMPUTERS DESIG
  • [3] PTITCHKIN VA, 2000, ANAL NEURONET TRANSF, V1, P30
  • [4] PTITCHKIN VA, 2000, ANAL MULTILAYER NEUR
  • [5] Pugachev VS., 1960, Theory of Random Functions: And Its Application to Control Problems
  • [6] TEREKHOV VA, 1999, NEURAL NET CONTROL S