Presentation 2002/11/4
A Forward-propagation Rule for Learning Inverse Models based on Adaptive Filter Theory
Yoshihiro OHAMA, Naohiro FUKUMURA, Yoji UNO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Human motor control consists of feedback control and feedforward control. When a feedforward controller controls a dynamical system to follow planned trajectories, the feedforward controller can be regarded as an inverse model about the dynamical system. Thus, the motor control must contain such suitable inverse models trained in some schemes. We have proposed a Forward-propagation learning scheme to acquire neural inverse models of controlled objects. In this report, we develop this scheme in a framework of adaptive filter theory and confirm by computer simulation that the proposed scheme can acquire suitable inverse models.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Forward-propagation rule / inverse model / layered neural network / adaptive filter / system identification / RLS algorithms
Paper # NC2002-69
Date of Issue

Conference Information
Committee NC
Conference Date 2002/11/4(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) A Forward-propagation Rule for Learning Inverse Models based on Adaptive Filter Theory
Sub Title (in English)
Keyword(1) Forward-propagation rule
Keyword(2) inverse model
Keyword(3) layered neural network
Keyword(4) adaptive filter
Keyword(5) system identification
Keyword(6) RLS algorithms
1st Author's Name Yoshihiro OHAMA
1st Author's Affiliation Department of Information and Computer Sciences, Toyohashi University of Technology()
2nd Author's Name Naohiro FUKUMURA
2nd Author's Affiliation Department of Information and Computer Sciences, Toyohashi University of Technology
3rd Author's Name Yoji UNO
3rd Author's Affiliation Department of Information and Computer Sciences, Toyohashi University of Technology
Date 2002/11/4
Paper # NC2002-69
Volume (vol) vol.102
Number (no) 430
Page pp.pp.-
#Pages 6
Date of Issue