Presentation 1996/10/28
Layerd Neural network with Feedback constructed by AutoRegressive Neuron(ARN)
M. NAKAJOH, T. FURUYA, H. KASAHARA, T. HIGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose an AutoRegressive Neuron (ARN) which has an autoregressive (AR) model between the neuron's input and the sigmoid function and can use BackPropergation (BP) learning. By using ARNs, we construct layered neural nets (LN), Jordan's nets (JN) and Elman's nets (EN), and then make them learn verious temporal data sequences. The simulation results have shown that the proposed ARN can improve the temporal data processing ability of JN and EN greatly.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Layerd neural network / Autoregressive model / Jordan's net / Elman's nets / Temporal process
Paper # NC96-44
Date of Issue

Conference Information
Committee NC
Conference Date 1996/10/28(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) Layerd Neural network with Feedback constructed by AutoRegressive Neuron(ARN)
Sub Title (in English)
Keyword(1) Layerd neural network
Keyword(2) Autoregressive model
Keyword(3) Jordan's net
Keyword(4) Elman's nets
Keyword(5) Temporal process
1st Author's Name M. NAKAJOH
1st Author's Affiliation Toho University()
2nd Author's Name T. FURUYA
2nd Author's Affiliation Toho University
3rd Author's Name H. KASAHARA
3rd Author's Affiliation Toho University
4th Author's Name T. HIGUCHI
4th Author's Affiliation Electrotechnical Laboratory
Date 1996/10/28
Paper # NC96-44
Volume (vol) vol.96
Number (no) 331
Page pp.pp.-
#Pages 8
Date of Issue