Presentation 2003/11/14
Robotic Control by Volterra Netwerk
Yoshikazu FUJISUE, Eiichi INOHIRA, Hirokazu YOKOI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the conventional feedback error learning method, a hierarchical neural network by using a learning threshold element has been employed. However, a hierarchical neural network by using a learning threshold element cannot achieve the performance of processing a time series signal and controlling a system as much as we expected. The reason is that this neural network has low ability of processing a time series signal. We apply a hierarchical neural network by using volterra element, which has high ability of processing a time series signal. We embed the feed back error learning method into a control system of a robot, and verify the effectiveness of a volterra network by comparing the error in case of using the conventional hierarchical neural network.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Feedback error learning method / Volterra netwerk / Robot
Paper # NC2003-78
Date of Issue

Conference Information
Committee NC
Conference Date 2003/11/14(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) Robotic Control by Volterra Netwerk
Sub Title (in English)
Keyword(1) Feedback error learning method
Keyword(2) Volterra netwerk
Keyword(3) Robot
1st Author's Name Yoshikazu FUJISUE
1st Author's Affiliation Kyusyu Institute of Technology Graduate School of Life Science and Systems Engineering()
2nd Author's Name Eiichi INOHIRA
2nd Author's Affiliation Kyusyu Institute of Technology Graduate School of Life Science and Systems Engineering
3rd Author's Name Hirokazu YOKOI
3rd Author's Affiliation Kyusyu Institute of Technology Graduate School of Life Science and Systems Engineering
Date 2003/11/14
Paper # NC2003-78
Volume (vol) vol.103
Number (no) 465
Page pp.pp.-
#Pages 5
Date of Issue