-
- 小原 和博
- NTT
書誌事項
- タイトル別名
-
- Performance Verification Method on Modification Techniques of Desired Outputs for 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 キョウシ シンゴウ シュウセ
この論文をさがす
抄録
We proposed ways to improve pattern recognition ability by combining several small back-propagation neural networks (BPNNs) [1]. We found that modifying the desired outputs according to the similarity of the input patterns (i.e., increasing desired outputs to similar classes) increases the BPNN outputs for similar classes, thus improving the generalization ability of the modular-net architecture. We evaluated the learning technique using two subfeatures extracted from handwritten digits [1]. This paper proposes a performance-verification method and presents experimental results applying learning techniques to the proposed verification-problems: 4-class, 10-class, and 20-class classification problems using 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) 118 (11), 1617-1622, 1998
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
- 1390001204607032832
-
- NII論文ID
- 130006842997
- 10002815469
-
- NII書誌ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL書誌ID
- 4588425
-
- 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