Modifying Desired Outputs to Improve Pattern Recognition by Combining Subfeature-Input Neural Networks
-
- Kohara Kazuhiro
- NTT
-
- Nakamura Yukihiro
- Kyoto University
書誌事項
- タイトル別名
-
- Modifying Desired Outputs to Improve Pa
この論文をさがす
抄録
We have investigated ways to improve pattern recognition ability by combining several small back-propagation neural networks (BPNNs) into a modular-net architecture. In this architecture several subfeatures are extracted from patterns, each subfeature is input into a separate BPNN, and the output vectors from the BPNNs are combined to obtain the recognition results. Using two subfeatures extracted from handwritten digits, we investigated how best to obtain the desired outputs for similar patterns in order to improve the generalization ability of the modular-net architecture. We found that the conventional all-or-nothing desired-output approach, “1” for the correct class and “0” for the other classes, prevents the BPNN outputs for similar classes from becoming sufficiently large, preventing the combined output for the correct class for patterns in which both subfeatures are very similar to those of the other classes from becoming maximal. We also 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, which help maximize the combined output for the correct class, thus improving the generalization ability of the modular-net architecture. The effectiveness of our approach was shown by several experiments using two subfeatures extracted from handwritten digits.
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 (6), 805-813, 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
- 1390001204608063872
-
- NII論文ID
- 130006843818
- 10002810606
-
- NII書誌ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL書誌ID
- 4216210
-
- 本文言語コード
- en
-
- 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