TY - GEN
T1 - A study of the effect of noise injection on the training of artificial neural networks
AU - Jiang, Yulei
AU - Zur, Richard M.
AU - Pesce, Lorenzo L.
AU - Drukker, Karen
PY - 2009
Y1 - 2009
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=70449408530&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70449408530&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2009.5178981
DO - 10.1109/IJCNN.2009.5178981
M3 - Conference contribution
AN - SCOPUS:70449408530
SN - 9781424435531
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 1428
EP - 1432
BT - 2009 International Joint Conference on Neural Networks, IJCNN 2009
T2 - 2009 International Joint Conference on Neural Networks, IJCNN 2009
Y2 - 14 June 2009 through 19 June 2009
ER -