Stability of Neural Networks for Slightly Perturbed Training Data Sets
Indrias Berhane, Cidambi Srinivasan · Communication in Statistics- Theory and Methods · 2004
In learning models of artificial neural networks, that randomness comes from the distribution of the training data. We show individual observations do not affect excessively for a neutral network modeling, provided that it has adequate nodes on the hidden layer and proves that the empirical error of a neural network with p number of weights converges to the expected error when where m is the size of the perturbed training data.