Theoretical characterizations of possibilities and impossibilities of Hopfield neural networks in solving combinatorial optimization problems

Author

Matsuda, Satoshi

Author_Institution

Comput. & Commun. Res. Center, Tokyo Electr. Power Co. Inc., Japan

Volume

7

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

4563

Abstract

The asymptotical stability and instability conditions of the solutions and nonsolutions are proved for corners of Hopfield neural hypercube in solving typical combinatorial optimization problems, i.e., traveling salesman problem, N-queen problem and Hitchcock problem. These conditions make the theoretical characterizations of many possibilities and impossibilities of Hopfield neural networks in solving combinatorial optimization problems

Keywords

Hopfield neural nets; asymptotic stability; combinatorial mathematics; mathematics computing; optimisation; travelling salesman problems; Hitchcock problem; Hopfield neural networks; N-queen problem; asymptotical stability; combinatorial optimization; instability conditions; operations research; traveling salesman problem; Asymptotic stability; Computer networks; Constraint optimization; Constraint theory; Hopfield neural networks; Hypercubes; Intelligent networks; Neural networks; Neurons; Traveling salesman problems;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.375009

Filename

375009