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

Yulei Jiang*, Richard M. Zur, Lorenzo L. Pesce, Karen Drukker

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

30 Scopus citations

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.

Original languageEnglish (US)
Title of host publication2009 International Joint Conference on Neural Networks, IJCNN 2009
Pages1428-1432
Number of pages5
DOIs
StatePublished - 2009
Event2009 International Joint Conference on Neural Networks, IJCNN 2009 - Atlanta, GA, United States
Duration: Jun 14 2009Jun 19 2009

Publication series

NameProceedings of the International Joint Conference on Neural Networks

Other

Other2009 International Joint Conference on Neural Networks, IJCNN 2009
Country/TerritoryUnited States
CityAtlanta, GA
Period6/14/096/19/09

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'A study of the effect of noise injection on the training of artificial neural networks'. Together they form a unique fingerprint.

Cite this