A study of the effect of noise injection on the training of artificial neural networks

Authors:
Yulei Jiang;Richard M. Zur;Lorenzo L. Pesce;Karen Drukker
Affiliations:
Department of Radiology, the University of Chicago, Chicago, IL;Department of Radiology, the University of Chicago, Chicago, IL;Department of Radiology, the University of Chicago, Chicago, IL;Department of Radiology, the University of Chicago, Chicago, IL
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 5
Cited 1

Creating artificial neural networks that generalize

Neural Networks
”Proper” binormal ROC curves: theory and maximum-likelihood estimation

Journal of Mathematical Psychology
Neural Network Modelling with Input Uncertainty: Theory and Application

Journal of VLSI Signal Processing Systems
Comparison of Non-Parametric Methods for Assessing Classifier Performance in Terms of ROC Parameters

AIPR '04 Proceedings of the 33rd Applied Imagery Pattern Recognition Workshop
The effects of adding noise during backpropagation training on a generalization performance

Neural Computation

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

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We studied the effect of noise injection in overcoming the problem of overtraining in the training of artificial neural networks (ANNs) in comparison with other common approaches for overcoming this problem such as early stopping of the ANN training process and weight decay (which is similar to Bayesian artificial neural networks). We found from simulation studies and studies of a computer-aided diagnosis application that noise injection is effective in overcoming overtraining and is as effective as, or even more effective than, early stopping and weight decay.