Training data selection method for generalization by multilayer neural networks

スポンサーリンク

概要

• 論文の詳細を見る

• 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 generalization 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). The data, for which the output error is relatively large, are selected. Furthermore, they are paired with the nearest data belong to the different class. The newly selected data are further paired with the nearest data. Finally, pairs of the data, which locate close to the boundary, can be found. Using these pairs of the data, the MLNNs are further trained (Step 2). Since, there are some variations to combine Steps 1 and 2, the proposed method can be applied to both off-line and on-line training. The proposed method can reduce the number of the training data, at the same time, can hasten the training. Usefulness is confirmed through computer simulation.

• 一般社団法人電子情報通信学会の論文
• 1998-03-25

著者

• Hara Kazuyuki

  The Department Of Computer Science Gunma Polytechnic College

• Nakayama Kenji

  The Department Of Electrical And Computer Engineering Faculty Of Engineering Kanazawa University

関連論文

• Alternative learning algorithm for stereophonic acoustic echo canceller without Pre-Processing
• A cascade form predictor of neural and FIR filters and its minimum size estimation based on nonlinearity analysis of time series
• Training data selection method for generalization by multilayer neural networks

スポンサーリンク