A Study for Keeping Generalization Ability of Multilayered Neural Networks using Evolution Strategies
-
- Ogawa Satoru
- Tokyo Metropolitan University
-
- Watanebe Takao
- Tokyo Metropolitan University
-
- Yasuda Keiichiro
- Tokyo Metropolitan University
-
- Yokoyama Ryuichi
- Tokyo Metropolitan University
Bibliographic Information
- Other Title
-
- 進化戦略の適用による階層型ネットワークの汎化能力向上に関する研究
- シンカ センリャク ノ テキヨウ ニヨル カイソウガタ ネットワーク ノ ハン
Search this article
Abstract
This paper proposes a new algorithm for advancing the generalization ability of multilayer neural networks. The proposed algorithm, based on regularization theory, is a method for determining the regularization parameter, on condition that the training data is shown additionally. It is not a method that solves a problem for all training data again when additional training data is shown, but rather a method that adjusts the regularization parameter to fit additional training data. The characteristics of this algorithm are (1) the prediction error for the additional data is used in evaluating to determine the regularization parameter, (2) Evolution strategies (ES) that is multipoint search method is used for the determination problem of regularization parameter. The evaluation of the regularization parameter varies according to the data added. This study simulated an additional learning problem to examine the performance of the proposed method. And the simulation results are presented in this paper.
Journal
-
- IEEJ Transactions on Electronics, Information and Systems
-
IEEJ Transactions on Electronics, Information and Systems 117 (2), 143-149, 1997
The Institute of Electrical Engineers of Japan
- Tweet
Details 詳細情報について
-
- CRID
- 1390282679584426496
-
- NII Article ID
- 130006843615
- 10002809323
-
- NII Book ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL BIB ID
- 4128398
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed