On the objective function and learning algorithm for concurrent open node fault

Authors:
Chi Sing Leung;Pui Fai Sum;Kai-Tat Ng
Affiliations:
Dept. of Electronic Engineering, City University of Hong Kong, Hong Kong;Institute of Technology Management, National Chung Hsing University, Taiwan;Dept. of Electronic Engineering, City University of Hong Kong, Hong Kong
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part III
Year:
2012

Citing 6
Cited 0

Neural networks and dynamical systems

International Journal of Approximate Reasoning - Special issue on fuzzy logic and neural networks for pattern recognition and control
Obtaining Fault Tolerant Multilayer Perceptrons Using an Explicit Regularization

Neural Processing Letters
Convergence and objective functions of some fault/noise-injection-based online learning algorithms for RBF networks

IEEE Transactions on Neural Networks
The Impact of Arithmetic Representation on Implementing MLP-BP on FPGAs: A Study

IEEE Transactions on Neural Networks
A Fault-Tolerant Regularizer for RBF Networks

IEEE Transactions on Neural Networks
Complete and partial fault tolerance of feedforward neural nets

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper studies the performance of faulty RBF networks when stuck-at-zero node fault and stuck-at-one node fault happen. An objective function for training fault tolerant RBF networks for node fault is first derived. A training learning algorithm for faulty RBF networks is then presented. Finally, a mean prediction error formula which can estimate the test set error of faulty networks is derived. Simulation experiments are then performed to verify our theoretical result.