Presentation 1999/9/22
The Self-Feedback Controlled Chaotic Neural Network and its Application to the Multi-Layer Channel Routing
Masaya OHTA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The chaotic neural network has a characteristic of escape from a local minimal point of the energy function, so that it can find a global minimal point easier than by the Hopfield model. However it is sometime difficult to escape by the chaotic behavior. To overcome it, the self-feedback controlled Chaotic Neural Network is proposed. The proposed system can perceive to be caught in a local minimal point and escape from it by reinforcing its own self-feedback connection autonomously. To confirm the effectiveness of the proposed system, it is applied to the multi-layer channel routing problem. It is confirmed from experimental results that although an iteration steps to get the optimal solution increases, a frequency to get the optimal solution is vastly improved.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) chaos / neural network / negative self-feedback / multi-layer channel routing problem / local minimum
Paper # NLP99-101
Date of Issue

Conference Information
Committee NLP
Conference Date 1999/9/22(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) The Self-Feedback Controlled Chaotic Neural Network and its Application to the Multi-Layer Channel Routing
Sub Title (in English)
Keyword(1) chaos
Keyword(2) neural network
Keyword(3) negative self-feedback
Keyword(4) multi-layer channel routing problem
Keyword(5) local minimum
1st Author's Name Masaya OHTA
1st Author's Affiliation Osaka Electro-Communication University()
Date 1999/9/22
Paper # NLP99-101
Volume (vol) vol.99
Number (no) 324
Page pp.pp.-
#Pages 8
Date of Issue