The Robustness of Combination of Sigmoid Function Wavelet Neural Network

被引:0
作者
Xia, Hou [1 ,2 ]
Hu ShouSong [2 ]
Hai, Liu Guo [1 ]
机构
[1] Jiangsu Univ, Sch Elect & Informat Engn, Zhenjiang 212013, Peoples R China
[2] Nanjing Univ Aeronaut & Astronaut, Coll Automat Engn, Nanjing, Jiangsu, Peoples R China
来源
2008 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-11 | 2008年
关键词
Wavelet Neural Network; Faint Perturbation; Sensitive Disturbance; Sensitivity; Robustness;
D O I
10.1109/CCDC.2008.4597979
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The disturbing sensitivity and robustness of combination of sigmoid function wavelet neural network are discussed by making use of probability statistics and symbolic logic. If the faint perturbation appears, the robust invariability condition of wavelet neural network is obtained, and if the sensitive disturbance appears, the sensitivity formula and robustness formula are given. It is proved theoretically that to a certain extent, the more hidden wavelet nerve cells, the less robustness of wavelet neural network Consequently, it validates analytically the intuitionistic hypothesis of the relationship between hidden layer wavelet nerve cells number and the robustness of wavelet neural network.
引用
收藏
页码:3494 / +
页数:2
相关论文
共 16 条
[1]   FPE-based criteria to dimension feedforward neural topologies [J].
Alippi, C .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1999, 46 (08) :962-973
[2]  
AMARI S, 1995, COMPUTATIONAL INTELL, P71
[3]  
Bishop CM., 1995, Neural networks for pattern recognition
[4]  
DAzzo J.J., 2003, Linear Control System Analysis and Design with MATLAB, VFifth
[5]   Fast robust correlation [J].
Fitch, AJ ;
Kadyrov, A ;
Christmas, WJ ;
Kittler, J .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2005, 14 (08) :1063-1073
[6]   Robust adaptive tracking for time-varying uncertain nonlinear systems with unknown control coefficients [J].
Ge, SS ;
Wang, J .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2003, 48 (08) :1463-1469
[7]   Wavelet neural network approach for fault diagnosis of analogue circuits [J].
He, Y ;
Tan, Y ;
Sun, Y .
IEE PROCEEDINGS-CIRCUITS DEVICES AND SYSTEMS, 2004, 151 (04) :379-384
[8]  
JIAN NC, 2005, ICNN B 05 INT C NEUR, P781
[9]  
KREINOVICH V, 1994, IEEE WORLD C COMP IN, V1, P299
[10]  
LARSEN J, 1992, P IEEE SP WORKSH, P29