Presentation 2004/5/21
Mode-utilizing developmental learning based on coherent neural networks
Akira HIROSE, Yasufumi ASANO, Toshihiko HAMANO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose the mode-utilizing developmental learning with which a system learns similar or advanced tasks incrementally by using its cumulative skill with mode parameters. We construct such a system based on the coherent neural network theory by choosing the carrier frequency as the mode-selecting key. We assume two tasks to ride a bicycle. The first is to ride as long as the system can before it falls. The second is an advanced one, i.e., to ride as far as possible. The mode key is found adjusted self-organizingly in the developmental learning. It is demonstrated that the learning is performed efficiently to exhibit a successful ride for a long distance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) brain-like computing / behavioral modulation / complex-valued neural networks / sensorimotor system
Paper # NC2004-3
Date of Issue

Conference Information
Committee NC
Conference Date 2004/5/21(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) Mode-utilizing developmental learning based on coherent neural networks
Sub Title (in English)
Keyword(1) brain-like computing
Keyword(2) behavioral modulation
Keyword(3) complex-valued neural networks
Keyword(4) sensorimotor system
1st Author's Name Akira HIROSE
1st Author's Affiliation Department of Electronic Engineering, The University of Tokyo()
2nd Author's Name Yasufumi ASANO
2nd Author's Affiliation Department of Electronic Engineering, The University of Tokyo
3rd Author's Name Toshihiko HAMANO
3rd Author's Affiliation Department of Frontier Informatics, The University of Tokyo
Date 2004/5/21
Paper # NC2004-3
Volume (vol) vol.104
Number (no) 99
Page pp.pp.-
#Pages 6
Date of Issue