A Regularizer Approach for RBF Networks Under the Concurrent Weight Failure Situation
Authors:
- 28 March 2016
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 28 (6) , 1360-1372
Abstract
Many existing results on fault-tolerant algorithms focus on the single fault source situation, where a trained network is affected by one kind of weight failure. In fact, a trained network may be affected by multiple kinds of weight failure. This paper first studies how the open weight fault and the multiplicative weight noise degrade the performance of radial basis function (RBF) networks. Afterward, we define the objective function for training fault-tolerant RBF networks. Based on the objective function, we then develop two learning algorithms, one batch mode and one online mode. Besides, the convergent conditions of our online algorithm are investigated. Finally, we develop a formula to estimate the test set error of faulty networks trained from our approach. This formula helps us to optimize some tuning parameters, such as RBF width.Keywords
Funding Information
- City University of Hong Kong (7004233)
This publication has 50 references indexed in Scilit:
- Multilayer Perceptrons Which Are Tolerant to Multiple Faults and Learnings to Realize Them2014
- Classification in the Presence of Label Noise: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2013
- An FPGA-based multiple-weight-and-neuron-fault tolerant digital multilayer perceptronNeurocomputing, 2013
- Noise-enhanced clustering and competitive learning algorithmsNeural Networks, 2013
- Synthesis of fault tolerant neural networks2003
- Regularization parameter estimation for feedforward neural networksIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2003
- A novel learning algorithm which improves the partial fault tolerance of multilayer neural networksNeural Networks, 1999
- Synthesis of fault-tolerant feedforward neural networks using minimax optimizationIEEE Transactions on Neural Networks, 1998
- Fault-tolerant training for optimal interpolative netsIEEE Transactions on Neural Networks, 1995
- Maximally fault-tolerant neural networks and nonlinear programming1990