Presentation 2003/11/14
Nerve Field Dynamics of Neural Network with Cyclic Connections
Shinya SUENAGA, Yoshihiro HAYAKAWA, Koji NAKAJIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We analyse a dynamics of neural network with cyclic and antisymmetric connections. Particularly the focus points of this analyse are many kinds of limitcycles. In this paper, two different apporoximation methods which replaces original tanh type activation function with a high gain limit function and with a linear function are used. Although periods of limitcycles relate to some parameters of this type neural network, the detailed relation can be obtained by means of these methods. Futhermore, we discuss the detailed relations between characteristics of the network and the limit cycle.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Limit Cycle / Cyclic Connections / Neural Network
Paper # NLP2003-107
Date of Issue

Conference Information
Committee NLP
Conference Date 2003/11/14(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) Nerve Field Dynamics of Neural Network with Cyclic Connections
Sub Title (in English)
Keyword(1) Limit Cycle
Keyword(2) Cyclic Connections
Keyword(3) Neural Network
1st Author's Name Shinya SUENAGA
1st Author's Affiliation Laboratory for Electronic Intelligent Systems, Research Institute of Electrical Communication, Tohoku University()
2nd Author's Name Yoshihiro HAYAKAWA
2nd Author's Affiliation Laboratory for Electronic Intelligent Systems, Research Institute of Electrical Communication, Tohoku University
3rd Author's Name Koji NAKAJIMA
3rd Author's Affiliation Laboratory for Electronic Intelligent Systems, Research Institute of Electrical Communication, Tohoku University
Date 2003/11/14
Paper # NLP2003-107
Volume (vol) vol.103
Number (no) 463
Page pp.pp.-
#Pages 6
Date of Issue