Title | ||
---|---|---|
A study of the effect of noise injection on the training of artificial neural networks |
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. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/IJCNN.2009.5178981 | IJCNN |
Keywords | Field | DocType |
simulation study,overcoming overtraining,computer-aided diagnosis application,noise injection,artificial neural network,common approach,ann training process,weight decay,histograms,learning artificial intelligence,radiology,artificial neural networks,sampling methods,kernel,application software,noise,bayesian methods,data handling,cancer | Kernel (linear algebra),Overtraining,Early stopping,Automatic voltage control,Computer science,Weight decay,Artificial intelligence,Artificial neural network,Group method of data handling,Machine learning,Bayesian probability | Conference |
ISSN | Citations | PageRank |
1098-7576 | 6 | 0.56 |
References | Authors | |
8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yulei Jiang | 1 | 80 | 8.90 |
Richard M. Zur | 2 | 6 | 0.56 |
Lorenzo L. Pesce | 3 | 27 | 3.77 |
Karen Drukker | 4 | 46 | 11.96 |