Training Data Selection Method for Generalization by Multilayer Neural Networks

摘要

A training data selection method is proposed for multilayer neural networks (MLNNs). This method selects a small number of the training data, which guarantee both gen- eralization and fast training of the MLNNs applied to pattern classification. The generalization will be satisfied using the data locate close to the boundary of the pattern classes. However, if these data are only used in the training, convergence is slow. This phenomenon is analyzed in this paper. Therefore, in the proposed method, the MLNN is first trained using some number of the data, which are randomly selected (Step 1).