A New Method Based on Determining Error Surface for Designing Three Layer Neural Networks
-
- LU Baiquan
- Graduate School of Information Science and Electrical Engineering, Kyushu University
-
- MURATA Junichi
- Graduate School of Information Science and Electrical Engineering, Kyushu University
-
- HIRASAWA Kotaro
- Graduate School of Information Science and Electrical Engineering, Kyushu University
抄録
A method is proposed for designing three layer neural networks that gives relevant network structures which assure global minimization of learning errors for small training sets and small learning errors for big training sets both irrespective of the initial values. A condition on network structure is considered to achieve the above purpose, and a number of possible structures are provided together with their learning algorithms. Also, the generalization abilities of the network structures are discussed to guide the choice of structures in practice. All of the proposed structures for small training sets have zero errors after learning by a gradient-based algorithm and thus solve the local minima problem. The difference between them is in the level of locality and generalization abilities. For a big training set, first, the structure with zero learning errors for part of training data is obtained, then all of training data are used to train the network of the given structure, which improves the generalization abilities. Numerical examples are provided that support the present approach.
収録刊行物
-
- 計測自動制御学会論文集
-
計測自動制御学会論文集 36 (7), 589-598, 2000
公益社団法人 計測自動制御学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390282679478353024
-
- NII論文ID
- 130003791634
-
- ISSN
- 18838189
- 04534654
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可