An ANN Learning Algorithm Based on Hierarchical Clustering of Training Data
-
- Uno Tatsuya
- Chiba University
-
- Koakutsu Seiichi
- Chiba University
-
- Hirata Hironori
- Chiba University
Bibliographic Information
- Other Title
-
- 階層的問題分割によるニューラルネットワーク学習法
- 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
Search this article
Abstract
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.
Journal
-
- IEEJ Transactions on Electronics, Information and Systems
-
IEEJ Transactions on Electronics, Information and Systems 118 (3), 326-332, 1998
The Institute of Electrical Engineers of Japan
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390001204607422592
-
- NII Article ID
- 130006843388
- 10004161457
- 10002813236
-
- NII Book ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL BIB ID
- 4423997
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed