Generalization error of faulty MLPs with weight decay regularizer

Authors:
Chi Sing Leung;John Sum;Shue Kwan Mak
Affiliations:
Department of Electronic Engineering, City University of Hong Kong, Hong Kong;Institute of Technology Management, National Chung Hsing University, Taiwan;Department of Electronic Engineering, City University of Hong Kong, Hong Kong
Venue:
ICONIP'10 Proceedings of the 17th international conference on Neural information processing: models and applications - Volume Part II
Year:
2010

Citing 7
Cited 0

A Quantitative Study of Fault Tolerance, Noise Immunity, and Generalization Ability of MLPs

Neural Computation
Behavioral Fault Model for Neural Networks

ICCET '09 Proceedings of the 2009 International Conference on Computer Engineering and Technology - Volume 02
Local regularization assisted orthogonal least squares regression

Neurocomputing
On the regularization of forgetting recursive least square

IEEE Transactions on Neural Networks
Two regularizers for recursive least squared algorithms in feedforward multilayered neural networks

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	0.01

Visualization

Abstract

Weight decay is a simple regularization method to improve the generalization ability of multilayered perceptrons (MLPs). Besides, the weight decay method can also improve the fault tolerance of MLPs. However, most existing generalization error results of using the weight decay method focus on fault-free MLPs only. For faulty MLPs, using a test set to study the generalization ability is not practice because there are huge number of possible faulty networks for a trained network. This paper develops a prediction error formula for predicting the performance of faulty MLPs. Our prediction error results allows us to select an appropriate model for MLPs under open node fault situation.