Presentation 1999/5/20
Dynamics of Quantized Hopfield Networks with Fluctuation
Satoshi Matsuda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Quantized Hopfield networks with fluctuation can obtain good solutions to integer optimization problems more quickly than conventional binary or continuous networks. However, their basic dynamics is not clear, for example, we are unaware of the ralationship between the fluctuation width and the solutions obtained by the networks. In this paper we first clarify the relationship between the dynamics of the hysteresis binary networks and the quantized networks, and then, by taking Hitchcock problems as examples of integer optimization, we theoretically show the stability and instability conditions of the feasible and infeasible solutions in terms of the values of fluctuation width. Simulation results illus- trate this theoretical concludings.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hopfield network / integer programming / quantized neuron / fluctuation / hysteresis / stability
Paper # NC99-4
Date of Issue

Conference Information
Committee NC
Conference Date 1999/5/20(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 Quantized Hopfield Networks with Fluctuation
Sub Title (in English)
Keyword(1) Hopfield network
Keyword(2) integer programming
Keyword(3) quantized neuron
Keyword(4) fluctuation
Keyword(5) hysteresis
Keyword(6) stability
1st Author's Name Satoshi Matsuda
1st Author's Affiliation Computer and Communication Research Center, Tokyo Electric Power Company()
Date 1999/5/20
Paper # NC99-4
Volume (vol) vol.99
Number (no) 58
Page pp.pp.-
#Pages 8
Date of Issue