Evaluation of the Noise Injection in High Dimensions
Yoshihiro Mitani, Yoshihiko Hamamoto, Shingo Tomita · 1996
The noise injection into the training samples has been shown to lead to improvement of the generalization ability of artificial neural network(ANN) classifiers. In this paper, we investigate the positive effect of the noise injection on the generalization ability of ANN classifiers in high dimensions. We further show that the noise injection technique is very useful in situations where the true Bayes error is small. 1