Binary neural networks for N-queens problems and their VLSI implementations

Control and Cybernetics

Volumn 31, Issue 2, 2002, Pages 271-296

  Funabiki, Nobuo ^a   Kurokawa, Takakazu ^b   Ohta, Masaya ^c  

^a OKAYAMA UNIVERSITY   (Japan)

^b NATIONAL DEFENSE ACADEMY   (Japan)

^c Osaka Prefecture University   (Japan)

Author keywords

Algorithm; Binary neural network; Combinatorial optimization; NP hard; VLSI design

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; COMPUTATIONAL COMPLEXITY; PROBLEM SOLVING; VLSI CIRCUITS;

BINARY NEURAL NETWORKS;

NEURAL NETWORKS;

EID: 0036914207     PISSN: 03248569     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (34)

1. Abramson, B. and Yung, M. (1989) Divide and conquer under global constraints: a solution to the N-queens problem. J. Para. Dist. Comp., 6, 649-662.
2. Bitner, J.R. and Reingold, E.M. (1975) Backtrack programming techniques. Commun. ACM, 18, 651-656.
3. Falkowski, B.-J. and Schmitz L. (1986) note on the queen's problem. Inf. Proc. Lett., 23, 39-46.
4. Fortes, J.A.B. (1987) Systolic arrays: A survey of seven projects, IEEE Computer, 20 91-103.
5. Hinton, G.E., Sejnowski, T.J. and Ackley, D.H. (1984) Boltzmann machines: constrained satisfaction networks that learn. CMU-CS-84-119, Carnegie Mellon University.
6. Hirai, Y. (1998) A 1,000-Neuron System with One Million 7-bit Physical Interconnections, in M.J. Jordan, M.J. Kearns and S.A.Sola eds., Advances in Neural Information Processing Systems, 10, The MIT Press, Cambridge, Massachusetts, 705-711.
7. http://www.viplab.is.tsukuba.ac.jp/PDM/.
8. Hopfield, J.J. and Tank, D.W. (1985) Neural computation of decisions in optimization problems. Bio. Cybern., 52, 141-152.
9. IEEE (1988) IEEE standard backplane bus specification for microprocessor architecture; Futurebus, ANSI/IEEE Std.896.1-1987.
10. Jagota, A. (1995) Approximating maximum clique with a Hopfield network. IEEE Trans. Neural Networks, 6, 724-735.
11. Kale, L.V. (1990) An almost perfect heuristic for the N nonattacking queens problem. Inf. Proc. Lett., 34, 173-178.
12. Kirkpatrick, S., Gelatt Jr., C.D. and Vecchi, M.P. (1983) Optimization by simulated annealing, Science, 220, 4598.
13. Kurokawa, T. and Takefuji, Y. (1992) Neural network parallel computing for BIBD problems, IEEE Trans., CAS., 39, 243-247.
14. Lee, K.C., Funabiki, N. and Takefuji, Y. (1992) A parallel improvement algorithm for the bipartite subgraph problem, IEEE Trans. Neural Networks, 3, 139-145.
15. McCulloch, W.S. and Pitts, W.H. (1943) A logical calculus of ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5, 115.
16. Nozawa, H. (1992) A neural network model as a globally coupled map and applications based on chaos. Chaos, 2, 377-386.
17. Ohta, M. (1999) On the Self-Feedback Controlled Chaotic Neural Network and its Application to N-Queen Problem, Proc. Int. Joint Conf. Neural Networks.
18. Ohta, M. (2002) Chaotic neural networks with reinforced self-feedbacks and its application to N-Queen problem, Mathematics and Computers in Simulation, 59, 305-317.
19. Ohta, M., Anzai Y., Yoneda, S. and Ogihara, A. (1993) A Theoretical Analysis of Neural Networks with Nonzero Diagonal Elements, IEICE Trans. Fundamentals, E76-A, 284-291.
20. Ohta, M., Ogihara, A. and Fukunaga, K. (1994) Binary Neural Network with Negative Self-Feedback and Its Application to N-Queens Problem, IEICE Trans. Inf. Syst., E77-D, 459-465.
21. Ohta, M., Ogihara, A., Takamatsu, S. and Fukunaga, K. (1995) A Study on the Mechanism of the Minimum Searching by the Chaotic Neural Network, Proc. IEEE Int. Conf. Neural-Networks, 1517-1520.
22. Paielli, R.A. (1988) Simulation tests of the optimization method of Hopfield and Tank using neural networks. NASA Tech. Memo. 101047.
23. Reichling, M. (1987) A simplified solution of the N queen's problem. Inf. Proc. Lett., 25, 253-255.
24. Russell, S. and Norvig, P. (1995) Artificial Intelligence A Modern Approach, Prentice Hall.
25. Shriver, B.D. ed. (1988) Artificial Neural Systems, IEEE Computer, 21, 8-117.
26. Stone, H.S. and Stone, J.M. (1987) Efficient search techniques: an empirical study of the N-queens problem. IBM J. Res. Dev., 31, 464-474.
27. Sundararajan, N. and Saratchandran, P. (1998) Parallel Architectures for Artificial Neural Networks: paradigms and implementations, IEEE Computer Society Press, Los Alamitos, California, 379.
28. Takefuji Y. (1992) Neural network parallel computing, Kluwer Academic Publishers.
29. Takefuji, Y. and Szu, H. (1989) Design of parallel distributed Cauchy machines. Proc. Int. Joint Conf. Neural Networks.
30. Wang, L. (1997) Discrete-time convergence theory and updating rules for neural networks with energy functions. IEEE Trans. Neural Networks, 8, 445-447.
31. Wang, R.-L., Tang, Z. and Cao, Q.-P., A. (2002) A near-optimum parallel algorithm for bipartite subgraph problem using the Hopfield neural network learning. IEICE Trans. Fundamentals, E85-A, 497-504.
32. Wieselheier, J.E., Barnhart, C.M. and Ephremides, A. (1994) A neural network approach to routing without interference in multihop radio networks. IEEE Trans. Commun. 42, 166-177.
33. Wilson, G.V. and Pawley, G.S. (1988) On stability of the travelling salesman problem algorithm. Biological Cybernetics, 58, 63-70.
34. Yoshio, H., Baba, T., Funabiki, N. and Nishikawa, S. (1997) Proposal of an N-parallel computation method for a neural network for the N queens problem. Elect. Commun. Japan, Part 3, 80, 12-20.