Presentation 1994/10/13
Complex Back-Propagation with Local Feedback
Makoto Kinouchi, Masafumi Hagiwara,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) To deal with temporal patterns is very important and difficult problem for applications of neural networks.In this paper,we propose local feedback multilayered networks,a paticular class of reccurent networks,using 'complex neuron'.Complex number can express time by the phase component.We derive simple learning algorithm based on the back-propagation to deal with temporal patterns.It is shown in some computer simulations that the proposed complex networks have better ability than the conventional real networks.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) temporal patterns / recurrent networks / local feedback / complex number / back-propagation
Paper # NC94-40
Date of Issue

Conference Information
Committee NC
Conference Date 1994/10/13(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) Complex Back-Propagation with Local Feedback
Sub Title (in English)
Keyword(1) temporal patterns
Keyword(2) recurrent networks
Keyword(3) local feedback
Keyword(4) complex number
Keyword(5) back-propagation
1st Author's Name Makoto Kinouchi
1st Author's Affiliation Department of Electorical Engineering,Faculty of Science and Technology,Keio University()
2nd Author's Name Masafumi Hagiwara
2nd Author's Affiliation Department of Electorical Engineering,Faculty of Science and Technology,Keio University
Date 1994/10/13
Paper # NC94-40
Volume (vol) vol.94
Number (no) 272
Page pp.pp.-
#Pages 8
Date of Issue