Presentation 1996/7/24
Characteristics of Various Auto-regressive neural networks
H. Kasahara, M. nakajoh, T. Kamiyama, M. Sekiguchi, T. Furuya, T. Satake, T. Tanaka, T. Higuchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Neuron models with autoregressive models (ARN) have been proposed. Neural net which consists of ARNs (ARN net) has an ability of spatio temporal pattern processing. We selected four types of ARN. and compared the characteristics of the ARN neural nets. The nets lerned four problems (growth estimation, abc trajectry, flip flop) by the Backpropagation algorithm. The characteristics of ARN net depend on the place of AR model within a neuron model.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Layerd neural network / Auto-regressive model / Backpropagation
Paper # NC96-37
Date of Issue

Conference Information
Committee NC
Conference Date 1996/7/24(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) Characteristics of Various Auto-regressive neural networks
Sub Title (in English)
Keyword(1) Layerd neural network
Keyword(2) Auto-regressive model
Keyword(3) Backpropagation
1st Author's Name H. Kasahara
1st Author's Affiliation Faculty of Science,Toho University()
2nd Author's Name M. nakajoh
2nd Author's Affiliation Faculty of Science,Toho University
3rd Author's Name T. Kamiyama
3rd Author's Affiliation Faculty of Science,Toho University
4th Author's Name M. Sekiguchi
4th Author's Affiliation Faculty of Science,Toho University
5th Author's Name T. Furuya
5th Author's Affiliation Faculty of Science,Toho University
6th Author's Name T. Satake
6th Author's Affiliation University of Tsukuba
7th Author's Name T. Tanaka
7th Author's Affiliation Electrotechnical Laboratory
8th Author's Name T. Higuchi
8th Author's Affiliation Electrotechnical Laboratory
Date 1996/7/24
Paper # NC96-37
Volume (vol) vol.96
Number (no) 178
Page pp.pp.-
#Pages 8
Date of Issue