A training data selection in on-line training for multilayer neural networks

Author

Hara, Kazuyuki ; Nakayama, Kenji ; Karaf, A.A.M.

Author_Institution

Gunma Polytech. Coll., Japan

Volume

3

fYear

1998

fDate

4-9 May 1998

Firstpage

2247

Abstract

In this paper, a training data selection method for multilayer neural networks (MLNNs) in online training is proposed. Purpose of the reduction in training data is reducing the computation complexity of the training and saving the memory to store the data without losing generalization performance. This method uses a pairing method, which selects the nearest neighbor data by finding the nearest data in the different classes. The network is trained by the selected data. Since the selected data located along data class boundary, the trained network can guarantee generalization performance. Efficiency of this method for the online training is evaluated by computer simulation

Keywords

computational complexity; generalisation (artificial intelligence); learning (artificial intelligence); multilayer perceptrons; MLNN; computation complexity; computational efficiency; data class boundary; generalization; multilayer neural networks; nearest neighbor data; online training; pairing method; training data selection; Computer simulation; Data mining; Intelligent networks; Multi-layer neural network; Network address translation; Neural networks; Nonhomogeneous media; Pattern classification; Supervised learning; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on

Conference_Location

Anchorage, AK

ISSN

1098-7576

Print_ISBN

0-7803-4859-1

Type

conf

DOI

10.1109/IJCNN.1998.687210

Filename

687210