Emergent Neural Network and Application to Moving Obstacles Avoidance
-
- Naito Hirohisa
- Fujitsu Lab. Ltd.
-
- Uchida Kenko
- University of Waseda
Bibliographic Information
- Other Title
-
- 進化型ニューラルネットワークと移動障害物回避問題への応用
- シンカガタ ニューラル ネットワーク ト イドウ ショウガイブツ カイヒ モン
Search this article
Abstract
This paper proposes a new construction method of neural networks. The construction method consists of two fundamental ideas, which are a parallel selection-style evaluation and rules evolution.<br>This paper first explains these two ideas and combines these two ideas into one design method for neural networks. The neural network constructed by this proposed method is called emergent neural network.<br>An emergent neural network is applied to moving obstacles avoidance problem and its performance is demonstrated.
Journal
-
- IEEJ Transactions on Electronics, Information and Systems
-
IEEJ Transactions on Electronics, Information and Systems 117 (6), 768-776, 1997
The Institute of Electrical Engineers of Japan
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282679584770048
-
- NII Article ID
- 130006843814
- 10000121840
- 10002810556
-
- NII Book ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL BIB ID
- 4216205
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed