Presentation 1997/2/6
Dynamics of Linear Networks with Plural Spatio-Temporal Input Patterns
Ryoichi Wada, Arata Okuyama, Kazutoshi Gohara,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Dynamics of neural networks with spatio-temporal input patterns can be analyzed by the Excited Attractor Model. When all Poincare maps associated with inputs are contractive transformation, the state of the network changes not on the continuous space but on the discrete fractal-like invariant set. This paper verifies it for linear networks of which Poincare maps can be determinded analytically.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Excited Attractor / Hyper Cylindrical Phase Space, Poincare Section / IFS / Contraction MaP / Fractal Transition / Linear Dynamics
Paper # NLP96-139,NC96-93
Date of Issue

Conference Information
Committee NC
Conference Date 1997/2/6(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) Dynamics of Linear Networks with Plural Spatio-Temporal Input Patterns
Sub Title (in English)
Keyword(1) Excited Attractor
Keyword(2) Hyper Cylindrical Phase Space, Poincare Section
Keyword(3) IFS
Keyword(4) Contraction MaP
Keyword(5) Fractal Transition
Keyword(6) Linear Dynamics
1st Author's Name Ryoichi Wada
1st Author's Affiliation Faculty of Engineering, Hokkaido University()
2nd Author's Name Arata Okuyama
2nd Author's Affiliation Faculty of Engineering, Hokkaido University
3rd Author's Name Kazutoshi Gohara
3rd Author's Affiliation Faculty of Engineering, Hokkaido University
Date 1997/2/6
Paper # NLP96-139,NC96-93
Volume (vol) vol.96
Number (no) 511
Page pp.pp.-
#Pages 8
Date of Issue