Presentation 1997/3/17
Dynamics of recurrent complex-valued neural networks
Hirofumi ONISHI, Akira HIROSE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Complex-valued neural networks are to be fundamental to realize quantum neural devices and coherent optical neural networks in the future. In this paper, dynamics of recurrent complex-valued neural networks are numerically analyzed. The conclusions are as follows : 1)A 'drift' phenomenon is synchronously induced. 2)Trajectory instability is caused by the drift, although it is usually suppressed. 3)The networks are very sensitive to external input-signals, resulting in a phase lock.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Recurrent complex-valued neural networks / Drift / Lyapunov spectrum / Phase lock
Paper # NC96-123
Date of Issue

Conference Information
Committee NC
Conference Date 1997/3/17(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 recurrent complex-valued neural networks
Sub Title (in English)
Keyword(1) Recurrent complex-valued neural networks
Keyword(2) Drift
Keyword(3) Lyapunov spectrum
Keyword(4) Phase lock
1st Author's Name Hirofumi ONISHI
1st Author's Affiliation Research Center for Advanced Science and Technology (RCAST), University of Tokyo()
2nd Author's Name Akira HIROSE
2nd Author's Affiliation Research Center for Advanced Science and Technology (RCAST), University of Tokyo
Date 1997/3/17
Paper # NC96-123
Volume (vol) vol.96
Number (no) 583
Page pp.pp.-
#Pages 8
Date of Issue