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
[11]   Synthesis of fault tolerant neural networks [J].
Phatak, DS ;
Tchernev, E .
PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, :1475-1480
[12]   COMPLETE AND PARTIAL FAULT-TOLERANCE OF FEEDFORWARD NEURAL NETS [J].
PHATAK, DS ;
KOREN, I .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (02) :446-456
[13]  
Sequin C.H., 1991, Neural Networks, V4, P111
[14]  
SHER BY, 1999, P NATL SCI COUNC REP, V23, P599
[15]   FAULT-TOLERANT TRAINING FOR OPTIMAL INTERPOLATIVE NETS [J].
SIMON, D ;
ELSHERIEF, H .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (06) :1531-1535
[16]   Distributed fault tolerance in optimal interpolative nets [J].
Simon, D .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (06) :1348-1357
[17]   On Objective Function, Regularizer, and Prediction Error of a Learning Algorithm for Dealing With Multiplicative Weight Noise [J].
Sum, John Pui-Fai ;
Leung, Chi-Sing ;
Ho, Kevin I. -J. .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2009, 20 (01) :124-138
[18]  
Vapnik V, 1997, ADV NEUR IN, V9, P281
[19]   LMS learning algorithms: Misconceptions and new results on convergence [J].
Wang, ZQ ;
Manry, MT ;
Schiano, JL .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (01) :47-56
[20]   Evolving fault-tolerant neural networks [J].
Zhou, ZH ;
Chen, SF .
NEURAL COMPUTING & APPLICATIONS, 2003, 11 (3-4) :156-160
123