Presentation 1995/5/22
Some combinatorial optimization problems always solvable by Hopfield neural networks and their applications and limitations
Satoshi Matsuda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Many trials to solve the combinatorial optimization problems by Hopfield neural networks have been made extensively, however, it is, of course, not guaranteed to get always optimal solutions. Then it is interesting of what kind of combinatorial optimization problems the optimal solutions can always be obtained by Hopfield neural networks. In this paper, by the theory of the asymptotical stability and unstability of solutions and nonsolutions made by the author, it is shown that the optimal solutions of n-rook problems, which have a similarity to crossbar switching and a practical significance, can always be obtained by Hopfield neural networks. But it is also shown that optimal solutions of "inverse n-rook problem", which is more precise model of crossbar, can not always be obtained.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hopfield neural network / n-rook problem / crossbar switching
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 1995/5/22(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Some combinatorial optimization problems always solvable by Hopfield neural networks and their applications and limitations
Sub Title (in English)
Keyword(1) Hopfield neural network
Keyword(2) n-rook problem
Keyword(3) crossbar switching
1st Author's Name Satoshi Matsuda
1st Author's Affiliation Computer and Communication Research Center, Tokyo Electric Power Company()
Date 1995/5/22
Paper #
Volume (vol) vol.95
Number (no) 57
Page pp.pp.-
#Pages 8
Date of Issue