
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
S. Bhide, N. John, M.R. Kabuka, "A Boolean Neural Network Approach for the Traveling Salesman Problem," IEEE Transactions on Computers, vol. 42, no. 10, pp. 12711278, October, 1993.  
BibTex  x  
@article{ 10.1109/12.257714, author = {S. Bhide and N. John and M.R. Kabuka}, title = {A Boolean Neural Network Approach for the Traveling Salesman Problem}, journal ={IEEE Transactions on Computers}, volume = {42}, number = {10}, issn = {00189340}, year = {1993}, pages = {12711278}, doi = {http://doi.ieeecomputersociety.org/10.1109/12.257714}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Computers TI  A Boolean Neural Network Approach for the Traveling Salesman Problem IS  10 SN  00189340 SP1271 EP1278 EPD  12711278 A1  S. Bhide, A1  N. John, A1  M.R. Kabuka, PY  1993 KW  Boolean neural network; traveling salesman problem; NPcomplete problems; combinatorial optimization; simulation; simulated annealing algorithm; hardware complexity; noise immunity; realtime systems; job scheduling; Boolean functions; computational complexity; neural nets; realtime systems; scheduling; simulated annealing. VL  42 JA  IEEE Transactions on Computers ER   
It is shown that the Booleanneural network can be used to solve NPcomplete problems. The problem under consideration is the traveling salesman problem. The Boolean neural network has been modified to include the iterative procedure for solving combinatorial optimization problems. An architecture that utilizes this modified Boolean neural network (MBNN) is proposed for solving this problem. The simulation results have been found to be comparable to the simulated annealing algorithm (SAA), which is used as a test base. The MBNN implementation involves low hardware complexity, good noise immunity, and fast circuitry. This is very important in realtime systems and commercial job scheduling applications.
[1] E. Aarts and J. Korst,Simulated Annealing and Boltzmann Machines, A Stochastic Approach to Combinational Optimization ond Neural Computing. New York: Wiley, 1989.
[2] M. R. Garey and D. S. Johnson,Computers and Intractability: A Guide to Theory of NPCompleteness. San Francisco, CA: Freeman, 1979.
[3] J. Freeman and D. Skapura,Neural Networks: Algorithms, Applications, and Programming Techniques. Reading, MA: AddisonWesley, 1991.
[4] S. E. Fahlman and G. E. Hinton, "Connectionist architectures for artificial intelligence,"IEEE Comput. Mag., vol. 20, no. 1, pp. 100109, 1987.
[5] J. Hertz, A. Krogh, and R. G. Palmer.Introduction to the Theory of Neural Networks. Reading, MA: AddisonWesley, 1991.
[6] J. E. Dayhoff,Neural Network Architectures, An Introduction. New York: Van Nostrand Reinhold, 1990.
[7] M. Day and J. Zien, "Constrastive Hebbian learning and the traveling salesman problem," Presented atInt. Joint Conf. Neural Net., July, 1991.
[8] H. Yokoi and Y. Kakazu, "Approach to traveling salesman problem by a bionic model,"Intelligent Engineering Systems through Artificial Neural Networks, C. H. Dagli, S. R. Kumara, and Y. C. Shin, Eds. New York: ASME Press, 1991.
[9] D. Abramson, "A very high speed architecture for simulated annealing,"Computer, vol. 25, pp. 2736, May 1992.
[10] Clementet al., "Synaptic strengths for neural simulation of the traveling salesman problem"SPIE, vol. 937, Applications of Artificial Intelligence VI, 1988.
[11] J. J. Hopfield and D. W. Tank, "Neural computation of decisions in optimization problems,"Bio. Cybern., vol. 52, pp. 141152, 1985.
[12] S. Gazula and M. R. Kabuka, "Design of supervised classifiers using Boolean neural networks,"IEEE Trans. Pattern Anal. Machine Intell., to appear.
[13] S. Gazula and M. R. Kabuka, "Realtime implementation of supervised classifiers using Boolean Neural Networks,"Proc. Artificial Neural Networks in Engineering, C. H. Dagliet al., Eds., Nov. 1992.
[14] M. I. Gomez and M. R. Kabuka, "Implementation of a new digital neural network using ASIC technology,"Intelligent Engineering Systems through Artificial Neural Networks, C. H. Dagli, S. R. Kumara, and Y. C. Shin, Eds. New York: ASME Press, 1991.
[15] M. R. Kabuka, Internal Rep., Mar. 1992.
[16] B. Hussain and M. R. Kabuka, "Neural Net transformation of arbitrary Boolean functions,"SPIE 1992, Int. Symp. on Optical and Applied Science: Neural and Stochastic Methods in Image and Signal Processing, invited.
[17] B. Hussain and M. R. Kabuka, "A feature recognition neural network for hierarchical character recognition,"IEEE Trans. Pattern Anal. Machine Intell., to appear.
[18] B. Hussain and M. R. Kabuka, "A high performance recognition neural network for character recognition,"Second Int. Conf. Automation, Robotics and Computer Vision, 1992, invited.
[19] S. Lin and B. W. Kernighan, "An efficient heuristic algorithm for the traveling salesman problem,"Oper. Res., vol. 21, pp. 498516, Mar.Apr. 1973.
[20] S. Kirkpatrick, C. D. Gelatt, Jr., and M. P. Vecchi, "Optimization by simulated annealing,"Science, vol. 220, pp. 671680, 1983.