Presentation 2003/3/10
Interactive Learning of Motions Based on H_∞-Learning : In the case of two-dimentional trajectories
Kiyoshi NISIYAMA, Koushi OCHISAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The interactive learning of motions will be very important for extracting their skills from craftsmen. However, the conventional learnings including the back-propagation (BP) are unsuitable to the interactive learning because the teaching data always has a considerably large degree of uncertainty in training. This paper shows by computer simulations that the H_∞-learning, which has been proposedby one of authors, is effective for such an interactive learning of motions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) motion learning / interactive learning / robust learning / H_∞-learning / H_2-learning / TDNN
Paper # NC2002-144
Date of Issue

Conference Information
Committee NC
Conference Date 2003/3/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Interactive Learning of Motions Based on H_∞-Learning : In the case of two-dimentional trajectories
Sub Title (in English)
Keyword(1) motion learning
Keyword(2) interactive learning
Keyword(3) robust learning
Keyword(4) H_∞-learning
Keyword(5) H_2-learning
Keyword(6) TDNN
1st Author's Name Kiyoshi NISIYAMA
1st Author's Affiliation Department of Computer and Information Science, Iwate University()
2nd Author's Name Koushi OCHISAI
2nd Author's Affiliation Department of Computer and Information Science, Iwate University
Date 2003/3/10
Paper # NC2002-144
Volume (vol) vol.102
Number (no) 729
Page pp.pp.-
#Pages 8
Date of Issue