
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
G.A. Tagliarini, J.F. Christ, E.W. Page, "Optimization Using Neural Networks," IEEE Transactions on Computers, vol. 40, no. 12, pp. 13471358, December, 1991.  
BibTex  x  
@article{ 10.1109/12.106220, author = {G.A. Tagliarini and J.F. Christ and E.W. Page}, title = {Optimization Using Neural Networks}, journal ={IEEE Transactions on Computers}, volume = {40}, number = {12}, issn = {00189340}, year = {1991}, pages = {13471358}, doi = {http://doi.ieeecomputersociety.org/10.1109/12.106220}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Computers TI  Optimization Using Neural Networks IS  12 SN  00189340 SP1347 EP1358 EPD  13471358 A1  G.A. Tagliarini, A1  J.F. Christ, A1  E.W. Page, PY  1991 KW  optimisation; neural networks; feedback; design rule; probabilistic resource allocation task; highperformance parallel processor; simulation; feedback; neural nets; optimisation; simulation. VL  40 JA  IEEE Transactions on Computers ER   
The design of feedback (or recurrent) neural networks to produce good solutions to complex optimization problems is discussed. The theoretical basis for applying neural networks to optimization problems is reviewed, and a design rule that serves as a primitive for constructing a wide class of constraints is introduced. The use of the design rule is illustrated by developing a neural network for producing highquality solutions to a probabilistic resource allocation task. The resulting neural network has been simulated on a highperformance parallel processor that has been optimized for neural network simulation.
[1] S. Amari, "A theory of adaptive pattern classifiers,"IEEE Trans. Electron. Comput., vol. EC16, pp. 279307, 1967.
[2] C. S. Beightler, D. T. Phillips, and D. J. Wilde,Foundations of Optimization, 2nd ed. Englewood Cliffs, NJ: PrenticeHall, 1979.
[3] M. A. Cohen and S. Grossberg, "Absolute stability of global pattern formation and parallel memory storage by competitive neural networks,"IEEE Trans. Syst., Man, Cybern., vol. SMC13, pp. 815826, Sept./Oct. 1983.
[4] G. W. Cottrell, P. Munro, and D. Zipser, "Image compression by backpropagation: An example of extensional programming," ICS Rep. 8702, Univ. of California at San Diego, Feb. 1987.
[5] E. D. Dahl, "Neural network algorithm for an NPcomplete problem: Map and graph coloring," inProc. 1st. Int. Conf. Neural Networks, vol. III, San Diego, CA, 1987, pp. 113120.
[6] K. Fukushima, "Cognitron: A selforganizing multilayered neural network,"Biol. Cybern., vol. 20, no. 3/4, pp. 121136.
[7] R. P. Gorman and T. J. Sejnowski, "Analysis of hidden units in a layered network trained to classify sonar targets,"Neural Networks, vol. 1, no. 1, pp. 7589, 1988.
[8] S. Grossberg,Studies of Mind and Brain: Neural Principles of Learning, Perception, Development, Cognition, and Motor Control. Boston, MA: Reidel, 1982.
[9] S. Grossberg, "Nonlinear neural networks: Principles, mechanisms, and architectures,"Neural Networks, vol. 1, no. 1, pp. 1761, 1988.
[10] D. Hammerstrom, "A VLSI architecture for highperformance, lowcost, onchip learning," inProc. IJCNN'90, vol. II, San Diego, CA, June 1721, 1990, pp. 537544.
[11] J. B. Hampshire, II and A. H. Waibel, "A novel objective function for improved phoneme recognition using timedelay neural networks,"IEEE Trans. Neural Networks, vol. 1, no. 2, pp. 216228, June 1990.
[12] R. HechtNielson,Neurocomputing. Reading, MA: AddisonWesley, 1990.
[13] M. Holler, S. Tam, H. Castro, and R. Benson, "An electrically trainable artificial neural network (ETANN) with 10240 'floating gate' synapses," inProc. Int. Joint Conf Neural Networks, vol. II, Washington, DC, June 1989, pp. 191196.
[14] J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities, "Proc. Nat. Acad. Sci. U.S.A., vol. 79, pp. 25542558, 1982.
[15] J. J. Hopfield, "Neurons with graded response have collective computational properties like those of twostate neurons,"Proc. Nat. Acad. Sci. U.S.A., vol. 81, pp. 30883092, 1984.
[16] J. J. Hopfleld and D. W. Tank, "'Neural' composition of decisions optimization problems,"Biol. Cybern., vol. 52, pp. 141152, 1985.
[17] J. J. Hopfield, "Computing with neural circuits: A model,"Science, vol. 233, pp. 625633, Aug. 1986.
[18] T. Kimoto, K. Asakawa, M. Yoda, and M. Takeoka, "Stock market prediction system with modular neural networks," inProc. IJCNN'90, vol. I, 1990, pp. 16.
[19] T. Kohonen, "An introduction to neural computing,"Neural Networks, vol. 1, no. 1, pp. 316, 1988.
[20] Y. Le Cun, "Learning process in an asymmetric threshold network," inDisordered Systems and Biological Organization, E. Bienenstock, Ed. New York: SpringerVerlag, 1986, pp. 233240.
[21] WC. Lin, FY. Liao, CK. Tsao, and T. Lingutla, "A hierarchical multipleview approach to threedimensional object recognition,"IEEE Trans. Neural Networks, vol. 2, pp. 8492, Jan. 1991.
[22] S. P. Lloyd and H. S. Witsenhausen, "Weapon allocation is NPcomplete," inProc. 1986 Summer Comput. Simulation Conf., Reno, NV, 1986.
[23] C. A. Mead,Analog VLSI and Neural Systems. Reading, MA: AddisonWesley, 1989.
[24] C. A. Mead, "Neuromorphic electronic systems,"Proc. IEEE, vol. 78, pp. 16291636, Oct. 1990.
[25] W. A. Metler and F. L. Preston, "Solutions to a probabilistic resource allocation problem," inProc. 28th IEEE Conf. Decision and Contr., Tampa, FL, Dec. 1989, pp. 16061611.
[26] K. S. Narendra and K. Parthasarathy, "Identification and control of dynamical systems using neural networks,"IEEE Trans. Neural Networks, vol. 1, pp. 427, Mar. 1990.
[27] E. W. Page and G. A. Tagliarini, "Algorithm development for neural networks," inProc. SPIE Symp. Innovative Sci. and Technol., vol. 880, Los Angeles, CA, 1988, pp. 1119.
[28] D. B. Parker, "Learning logic: Casting the cortex of the human brain in silicon," TR47, M.I.T. Center for Computational Research in Economics and Management Science, Cambridge, MA, Feb. 1985.
[29] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representation by error propagation,"Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vols. 1 and 2. Cambridge, MA: MIT Press, 1986.
[30] G. A. Tagliarini and E. W. Page, "A neuralnetwork solution to the concentrator assignment problem," inProc. IEEE Conf. Neural Information Processing SystemsNatural and Synthetic, Denver, CO, IEEE/AIP, 1987, pp. 775782.
[31] G. A. Tagliarini and E. W. Page, "Solving constraint satisfaction problems with neural networks," inProc. 1st. Int. Conf. Neural Networks, vol. III, San Diego, CA, 1987, pp. 741748.
[32] G. A. Tagliarini, "Undesirable equilibria in systematically designed neural networks," inProc. IEEE SOUTHEASTCON'89, vol. I, Columbia, SC, Apr. 1989, pp. 6367.
[33] Y. Takefuji and KC. Lee, "A near optimum parallel planarization algorithm,"Science, vol. 245, pp. 12211223, 1989.
[34] D. W. Tank and J. J. Hopfield, "Simple 'neural' organization networks: An A/D converter, signal decision circuit and a linear programming circuit,"IEEE Trans. Circuits Syst., vol. CAS33, pp. 533541, May 1986.
[35] P. Werbos, "Beyond regression: New tools for predicting and analysis in the behavioral sciences," Ph.D. dissertation, Harvard Univ., 1974.
[36] B. Widrow and M. A. Lehr, "30 years of adaptive neural networks: Perceptron, madaline, and backpropagation,"Proc. IEEE, vol. 78, no. 9, pp. 14151442, 1990.