書誌事項
- タイトル別名
-
- An ANN Learning Algorithm Based on Hierarchical Clustering of Training Data
- カイソウテキ モンダイ ブンカツ ニヨル ニューラル ネットワーク ガクシュウ
この論文をさがす
抄録
We propose a new ANN learning algorithm based on hierarchical clustering of training data. The proposed algorithm first constructs a tree of sub-learning problems by hiearchically clustering given learning patterns in a bottom-up manner and decides a corresponding network structure. The proposed algorithm trains the whole network giving teacher signals of the original learning problem to the output units, and trains sub-networks giving teacher signals of the divided sub-learning problems to the hidden units simultaneously. The hidden units which learn sub-learning problems become feature detectors, which promote the learning of the original learning problem. We demonstrate the advantages of our learning algorithm by solving N-bits parity problems, a non-liner function approximation, iris classification problem, and two-spirals problem. Experimen-tal results show that our learning algorithm obtains better solutions than the standard back-propagation algorithms and one of constructive algorithms in terms of the learning speed and the convergence rate.
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 (3), 326-332, 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
- 1390001204607422592
-
- NII論文ID
- 130006843388
- 10004161457
- 10002813236
-
- NII書誌ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL書誌ID
- 4423997
-
- 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