ANN Classifiers The noise injection into the training samples has been shown to lead to improvement of the gener- alization ability of artificial neural network(ANN) classifiers. In this paper, we investigate the posi- tive effect of the noise injection on the generaliza- tion ability of ANN classifiers in high dimensions. We further show that the noise injection technique is very useful in situations where the true Bayes er- ror is small. We will consider ANN classifiers with one hidden layer. The input neurons correspond to the com- ponents of the pattern vector to be classified. The hidden layer has m neurons. The output neurons correspond to the pattern class labels. For simplic- ity we will focus on the two-class problem. Hence, the number of output neurons is 2. Each neuron of one layer except the output layer is fully con- nected to that of the only next layer. The back- propagation(BP) algorithm (ll) was used to train the ANN classifiers. Initial weights of a network were distributed uniformly in -0.5 to 0.5. Learning was terminated when the mean-squared error over a training set dropped below a specified threshold, or when the mean-squared error was unchanged. Here, the maximum number of iterations was set to 10000. The rate of convergence is considerably affected by the learning rate c. From preliminary experiments, we used c = 0.1.
[1]
Geoffrey E. Hinton,et al.
Experiments on Learning by Back Propagation.
,
1986
.
[2]
Yves Grandvalet,et al.
Comments on "Noise injection into inputs in back propagation learning"
,
1995,
IEEE Trans. Syst. Man Cybern..
[3]
Geoffrey E. Hinton,et al.
Learning internal representations by error propagation
,
1986
.
[4]
John Van Ness,et al.
On the dominance of non-parametric Bayes rule discriminant algorithms in high dimensions
,
1980,
Pattern Recognit..
[5]
Petri Koistinen,et al.
Using additive noise in back-propagation training
,
1992,
IEEE Trans. Neural Networks.
[6]
R.J.F. Dow,et al.
Neural net pruning-why and how
,
1988,
IEEE 1988 International Conference on Neural Networks.
[7]
Kiyotoshi Matsuoka,et al.
Noise injection into inputs in back-propagation learning
,
1992,
IEEE Trans. Syst. Man Cybern..
[8]
Christopher M. Bishop,et al.
Current address: Microsoft Research,
,
2022
.
[9]
Anil K. Jain,et al.
Small sample size problems in designing artificial neural networks
,
1991
.
[10]
S. Raudys,et al.
Why do multilayer perceptrons have favorable small sample properties
,
1994
.