HUSCAP logo Hokkaido Univ. logo

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

Files in This Item:
79_552.pdf10.8 MBPDFView/Open
Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/64600

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

Export metadata:

OAI-PMH ( junii2 , jpcoar )

MathJax is now OFF:


 

 - Hokkaido University