Solving large scale puzzles with neural networks

Author

Kajiura, M. ; Akiyama, Y. ; Anzai, Y.

Author_Institution

Dept. of Electr. Eng., Keio Univ., Yokohama, Japan

fYear

1989

fDate

23-25 Oct 1989

Firstpage

562

Lastpage

569

Abstract

The n-queens problem is solved with Boltzmann machines and a depth-first search (DFS) algorithm. In large-scale problems, the Boltzmann machines found a solution much faster than the DFS. The 1000-queens problem was solved using an energy minimization technique. The polyomino puzzles were also solved with Boltzman machines and a DFS algorithm. In small-scale problems, the DFS solved these puzzles faster than Boltzmann machines. Using Gaussian machines, large-size polyomino puzzles were solved successfully. For example, 36 unique solutions were obtained for the 1000-queens problem, and 5×8, 6×10, and 8×8 sized difficult polyomino puzzles were solved

Keywords

minimisation; neural nets; problem solving; search problems; Boltzmann machines; Gaussian machines; depth first search algorithm; energy minimization technique; large scale puzzles; n-queens problem; neural networks; polyomino puzzles; Artificial intelligence; Artificial neural networks; Computer networks; Concurrent computing; High performance computing; Hopfield neural networks; Large-scale systems; Neural networks; Neurons; Probability;

fLanguage

English

Publisher

ieee

Conference_Titel

Tools for Artificial Intelligence, 1989. Architectures, Languages and Algorithms, IEEE International Workshop on

Conference_Location

Fairfax, VA

Print_ISBN

0-8186-1984-8

Type

conf

DOI

10.1109/TAI.1989.65368

Filename

65368