Presentation 2000/2/3
Adaptive Incremental Projection Learning
Yoshiharu Suga, Hidemitsu Ogawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When a target function has changed after the learning was finished, the learning result becomes wrong obviously. Then, we have to learn the new target function by using new training examples. It is called re-learning. However, if the change is partial, we can learn more effectively than re-learning. In this paper, we give an incremental learning method which utilizes not only new training examples but also the former learning result to provide better generalization ability than re-learning. The proposed method is successfully applied to the problem of learning the sensorimotor maps of a robot arm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) projection learning / re-learning / incremental learning / generalization ability / sensorimotor maps
Paper # NC99-82
Date of Issue

Conference Information
Committee NC
Conference Date 2000/2/3(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) Adaptive Incremental Projection Learning
Sub Title (in English)
Keyword(1) projection learning
Keyword(2) re-learning
Keyword(3) incremental learning
Keyword(4) generalization ability
Keyword(5) sensorimotor maps
1st Author's Name Yoshiharu Suga
1st Author's Affiliation Department of Computer Science, Graduate School of Infomation Science and Engineering, Tokyo Institute of Technology.()
2nd Author's Name Hidemitsu Ogawa
2nd Author's Affiliation Department of Computer Science, Graduate School of Infomation Science and Engineering, Tokyo Institute of Technology.
Date 2000/2/3
Paper # NC99-82
Volume (vol) vol.99
Number (no) 612
Page pp.pp.-
#Pages 8
Date of Issue