Selective Presentation of Training Set to Back-Propagation Neural Networks

DOI Web Site Web Site 2 Citations 15 References Open Access

Bibliographic Information

Other Title
  • バックプロパゲーション・ニューラルネットへの学習セットの選択的提示法
  • バックプロパゲーション ニューラル ネット エ ノ ガクシュウ セット ノ セ

Search this article

Description

We investigate how training patterns should be presented to a back-propagation neural network (BPNN) so as to train the BPNN with a small deviation of training patterns and to improve the BPNN's learning speed. First, we explain the problem with a conventional learning technique, in which all training patterns are presented to a BPNN equally. Then, we propose a selective presentation of training set to a BPNN. In a proposed technique, using several criterion values for both the mean summed squared error and individual summed squared errors, we detect poorly-trained patterns and present them more often. The effectiveness of the proposed technique is confirmed by evaluation experiments using mesh patterns extracted from handwritten digits and two-dimensional Gaussian distribution data.

Journal

Citations (2)*help

See more

References(15)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top