Presentation 2003/10/14
BackPropagation with ID Model
Jun FUKUHARA, Yoshihiro HAYAKAWA, Koji NAKAJIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Inverse Delayed model used in our research shows the negative resistance effect and the bistable output potential, and we are interested in their influence to the network behavior. In order to investigate the learning of the network composed of ID neurons in this report, we apply Back Propagation to ID model. Then, we discuss what influence the above ID neuron's characters have on the input-output behavior and leaning dynamics.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) negative resistance / inverse function / learning / Back Propagation
Paper # NLP2003-92
Date of Issue

Conference Information
Committee NLP
Conference Date 2003/10/14(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 Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) BackPropagation with ID Model
Sub Title (in English)
Keyword(1) negative resistance
Keyword(2) inverse function
Keyword(3) learning
Keyword(4) Back Propagation
1st Author's Name Jun FUKUHARA
1st Author's Affiliation Laboratory for Electronic Intelligent Systems, Reseach Institute of Electrical Communication, Tohoku University()
2nd Author's Name Yoshihiro HAYAKAWA
2nd Author's Affiliation Laboratory for Electronic Intelligent Systems, Reseach Institute of Electrical Communication, Tohoku University
3rd Author's Name Koji NAKAJIMA
3rd Author's Affiliation Laboratory for Electronic Intelligent Systems, Reseach Institute of Electrical Communication, Tohoku University
Date 2003/10/14
Paper # NLP2003-92
Volume (vol) vol.103
Number (no) 375
Page pp.pp.-
#Pages 6
Date of Issue