書誌事項
- タイトル別名
-
- Selective Presentation of Training Set to Back-Propagation Neural Networks
- 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
この論文をさがす
抄録
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.
収録刊行物
-
- 電気学会論文誌C(電子・情報・システム部門誌)
-
電気学会論文誌C(電子・情報・システム部門誌) 117 (9), 1281-1290, 1997
一般社団法人 電気学会
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1390282679583662208
-
- NII論文ID
- 130006842949
- 10009866165
- 10002811482
-
- NII書誌ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL書誌ID
- 4284311
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可