|
Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >
複合的人工ニューラルネットワーク : 教師なし学習を用いた動的制御における選択型ニューラルネットワークアンサンブル
| Title: | 複合的人工ニューラルネットワーク : 教師なし学習を用いた動的制御における選択型ニューラルネットワークアンサンブル |
| Other Titles: | Composite Artificial Neural Network : Selection-type Neural Network Ensembles in Dynamic System Control by Unsupervised Learning |
| Authors: | 大江, 亮介1 Browse this author | | 鈴木, 育男2 Browse this author →KAKEN DB | | 山本, 雅人3 Browse this author →KAKEN DB | | 古川, 正志4 Browse this author →KAKEN DB |
| Authors(alt): | OOE, Ryosuke1 | | SUZUKI, Ikuo2 | | YAMAMOTO, Masahito3 | | FURUKAWA, Masashi4 |
| Keywords: | artificial neural networks | | evolving artificial neural networks | | unsupervised learning | | neural network ensembles | | composite artificial neural network | | physical engine | | particle swarm optimization |
| Issue Date: | 2013 |
| Publisher: | 公益社団法人 精密工学会 |
| Journal Title: | 精密工学会誌 |
| Volume: | 79 |
| Issue: | 6 |
| Start Page: | 552 |
| End Page: | 558 |
| Publisher DOI: | 10.2493/jjspe.79.552 |
| Abstract: | This paper describes a novel method of combining artificial neural networks (ANNs), the composite artificial neural network (CANN), to improve performance of evolving ANNs (EANNs) in dynamic system control problems. Methods of combining ANNs by majority voting or averaging are not effective in controlling dynamic systems by EANNs. Unsupervised learning of EANNs is mathematically described, and then it is shown that the reason for ineffectiveness depends on the mechanism of evaluating ANNs indirectly by states. To avoid this problem, the CANN selects the suitable ANN by a high-level ANN to combine some ANNs. In numerical experiments, a flapping flight model is controlled by a common EANN and the CANN. The model motion is calculated by physical engine PhysX, and a common EANN and the CANN are optimized by the particle swarm optimization (PSO) respectively. The experiments show that the average evaluation of the CANN is 6.46% higher than that of a common EANN for the same computational time. |
| Type: | article |
| URI: | http://hdl.handle.net/2115/64600 |
| Appears in Collections: | 情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
Submitter: 山本 雅人
|
