IEEE Transactions on Neural Networks and Learning Systems · 2016 · 41 citations · 42 references
ComputingComputer EngineeringComputer ScienceFault ToleranceFault-tolerant SystemsMachine LearningFault DetectionNetwork Fault ToleranceNetwork RobustnessFault Tolerant AlgorithmsFault-tolerant Machine LearningFault-tolerant NetworksMultiplicative NoiseObjective Function FormulationRadial Basis Function NetworksTuning
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.
42
UCI Machine Learning Repository
Arthur Asuncion · Medical Entomology and Zoology · 2007 · 24.4K citations