Advertisement

Sudoku Solver by Q’tron Neural Networks

  • Tai-Wen Yue
  • Zou-Chung Lee
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4113)

Abstract

This paper presents a Sudoku solver based on the energydriven neural-network (NN) model, called the Q’tron NN model. The rules to solve Sudoku are formulated as an energy function in the same form as a Q’tron NN’s. The Q’tron NN for Sudoku can then be built simply by mapping. Equipping the NN with the proposed noise-injection mechanism, the Sudoku NN is ensured local-minima free. Besides solving Sudoku puzzles, the NN can also be used to generate Sudoku puzzles.

Keywords

Neural Network Neural Network Model Constraint Satisfaction Problem Simple Mode Boltzmann Machine 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aarts, E., Korst, J.: Simulated Annealing and Boltzmann Machines. Wiley and Sons, Chichester (1989)MATHGoogle Scholar
  2. 2.
    Ackley, D.H., Hinton, G.E., Sejnowski, T.J.: A Learning Algorithm for Boltzmann Machine. Cognitive Science 9, 147–169 (1985)CrossRefGoogle Scholar
  3. 3.
    Akiyama, Y., Yamashita, A., Kajiura, M., Aiso, H.: Combinatorial Optimization with Gaussian Machines. In: Proceedings of IEEE International Joint Conference on Neural Networks, Washington , DC, vol. 1, pp. 533–540 (1989)Google Scholar
  4. 4.
    Hayes, B.: Unwed Numbers - The mathematics of Sudoku: A Puzzle That Boasts ’No Math Required!’. American Scientist 94(1), 12–15 (2006)Google Scholar
  5. 5.
    Hopfield, J.J.: Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proceedings of Natl. Acad. Sci., USA 79, 2554–2558 (1982)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Hopfield, J.J., Tank, D.W.: Neural Computation of Decisions in Optimization Problems. Biological Cybernetics 52, 141–152 (1985)MATHMathSciNetGoogle Scholar
  7. 7.
    Jeong, H., Park, J.H.: Lower Bounds of Annealing Schedule for Boltzmann and Cauchy Machines. In: Proceeding of IEEE International Joint Conference on Neural Networks, Washington, DC, vol. 1, pp. 581–586 (1989)Google Scholar
  8. 8.
    Lee, B.W., Sheu, B.J.: Modified Hopfield Neural Networks for Retrieving the Optimal Solution. IEEE Transactions on Neural Networks 6, 137–142 (1991)CrossRefGoogle Scholar
  9. 9.
    Tjark, W.: A SAT-based Sudoku Solver. In: Sutcliffe, G., Voronkov, A. (eds.) LPAR 2005. LNCS (LNAI), vol. 3835. Springer, Heidelberg (2005)Google Scholar
  10. 10.
    Will, S.: Sudoku Easy. St. Martin’s Press, New York (2005)Google Scholar
  11. 11.
    Yato, T.: Seta. T.: Complexity and Completeness of Finding Another Solution and Its Application to Puzzles. IPSJ SIG Notes 2002-AL-87-2 (2002), http://www-imai.is.s.u-tokyo.ac.jp/~yato/data2/SIGAL87-2.pdf
  12. 12.
    Yue, T.W., Chen, M.C.: Q’tron Neural Networks for Constraint Satisfaction. In: Proceedings of Fourth International Conference on Hybrid Intelligent Systems (HIS 2004), Kitakyushu, Japan, pp. 398–403 (2004)Google Scholar
  13. 13.
    Yue, T.W.: A Goal-Driven Neural Network Approach for Combinatorial Optimization and Invariant Pattern Recognition. Phds Thesis, Department of Computer Engineering, National Taiwan University, Taiwan (1992)Google Scholar
  14. 14.
    Yue, T.W., Chiang, S.: Quench, Goal-Matching and Converge – The Three-Phase Resoning of A Q’tron Neural Network. In: Proceedings of IASTED 2002, International Conference on Artificial and Computational Intelligence, Tokyo, Japan, pp. 54–59 (2002)Google Scholar
  15. 15.
    Yue, T.W., Lee, Z.C.: A Goal-Driven Approach for Combinatorial Optimization Using Q’tron Neural Networks. In: Proceedings of IASTED 2002, International Conference on Artificial and Computational Intelligence, Tokyo, Japan, pp. 60–65 (2002)Google Scholar
  16. 16.
    Yue, T.W., Chen, M.C.: Associativity, Auto-reversibility and Question-Answering on Q’tron Neural Networks. In: Huang, D.-S., Zhang, X.-P., Huang, G.-B. (eds.) ICIC 2005. LNCS, vol. 3644, pp. 1023–1034. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  17. 17.
    Sudoku Solver. Sudoku Solver by Logic (2006), http://www.sudokusolver.co.uk/
  18. 18.
    Scanraid Ltd. Sudoku Solver (2006), http://www.scanraid.com/sudoku.htm
  19. 19.
    Wikipedia. Graph coloring (2006), http://en.wikipedia.org/wiki/Graph_coloring
  20. 20.
    Wikipedia. Mathematics of Sudoku (2006), http://en.wikipedia.org/wiki/Mathematics_of_Sudoku
  21. 21.
    Wikipedia. Sudoku (2006), http://en.wikipedia.org/wiki/Sudoku

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tai-Wen Yue
    • 1
  • Zou-Chung Lee
    • 1
  1. 1.Dept. of Computer Science and EngineeringTatung UniversityTaipeiTaiwan, R.O.C

Personalised recommendations