Training RBF network to tolerate single node fault

被引：8
作者：
Ho, Kevin [2 ]
Leung, Chi-sing [3 ]
Sum, John [1 ]
机构：
[1] Natl Chung Hsing Univ, Inst Technol Management, Taichung 40227, Taiwan
[2] Providence Univ, Dept Comp Sci & Commun Engn, Shalu, Taiwan
[3] City Univ Hong Kong, Dept Elect Engn, Kln, Hong Kong, Peoples R China
来源：
NEUROCOMPUTING | 2011年 / 74卷 / 06期
关键词：
Fault tolerant neural networks; RBF; Single node fault; FEEDFORWARD NEURAL-NETWORKS; OPTIMAL INTERPOLATIVE NETS; REGRESSION ESTIMATION; LEARNING ALGORITHM;
D O I：
10.1016/j.neucom.2010.12.005
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, an objective function for training a radial basis function (RBF) network to handle single node open fault is presented. Based on the definition of this objective function, we propose a training method in which the computational complexity is the same as that of the least mean squares (LMS) method. Simulation results indicate that our method could greatly improve the fault tolerance of RBF networks, as compared with the one trained by LMS method. Moreover, even if the tuning parameter is misspecified, the performance deviation is not significant. (C) 2011 Elsevier By. All rights reserved.
引用
收藏
页码：1046 / 1052
页数：7
相关论文
共 21 条
[1]  
Bolt G., 1992, THESIS U YORK UK
[2]   A novel learning algorithm which improves the partial fault tolerance of multilayer neural networks [J].
Cavalieri, S ;
Mirabella, O .
NEURAL NETWORKS, 1999, 12 (01) :91-106
[3]   Local regularization assisted orthogonal least squares regression [J].
Chen, S .
NEUROCOMPUTING, 2006, 69 (4-6) :559-585
[4]   Multiple model regression estimation [J].
Cherkassky, V ;
Ma, YQ .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (04) :785-798
[5]  
CHIU C, 1994, P IEEE INT C NEURAL, V1, P333
[6]   Synthesis of fault-tolerant feedforward neural networks using minimax optimization [J].
Deodhare, D ;
Vidyasagar, M ;
Keerthi, SS .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (05) :891-900
[7]   DETERMINING AND IMPROVING THE FAULT-TOLERANCE OF MULTILAYER PERCEPTRONS IN A PATTERN-RECOGNITION APPLICATION [J].
EMMERSON, MD ;
DAMPER, RI .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (05) :788-793
[8]  
HAMMADI NC, 1997, LEICE T INFORM SYSTE, P21
[9]  
Kamiura N, 2000, IEICE T INF SYST, VE83D, P1931
[10]   MAXIMALLY FAULT TOLERANT NEURAL NETWORKS [J].
NETI, C ;
SCHNEIDER, MH ;
YOUNG, ED .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (01) :14-23
123