A Novel Optimizing Network Architecture with Applications

Neural Computation

Volumn 8, Issue 5, 1996, Pages 1041-1060

  Rangarajan, Anand ^a   Gold, Steven ^b   Mjolsness, Eric ^c  

^a YALE UNIVERSITY   (United States)

^b Yale University   (United States)

^c UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0000347693     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/neco.1996.8.5.1041     Document Type: Article

References (39)

1. Aiyer, S. V. B., Niranjan, M., and Fallside, F. 1990. A theoretical investigation into the performance of the Hopfield model. IEEE Trans. Neural Networks 1(2), 204-215.
2. Almohamad, H. A. 1991. A polynomial transform for matching pairs of weighted graphs. J. Appl. Math. Modeling 15(4).
3. Almohamad, H. A., and Duffuaa, S. O. 1993. A linear programming approach for the weighted graph matching problem. IEEE Trans. Patt. Anal. Mach. Intell. 15(5), 522-525.
4. Bridle, J. S. 1990. Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters. In Advances in Neural Information Processing Systems 2, D. S. Touretzky, ed., pp. 211-217. Morgan Kaufmann, San Mateo, CA.
5. Elfadel, I. 1995. Convex potentials and their conjugates in analog mean-field optimization. Neural Comp. 7(5), 1079-1104.
6. Gee, A. H., and Prager, R. W. 1994. Polyhedral combinatorics and neural networks. Neural Comp. 6(1), 161-180.
7. Gee, A. H., Aiyer, S. V. B., and Prager, R. W. 1993. An analytical framework for optimizing neural networks. Neural Networks 6(1), 79-97.
8. Geiger, D., and Yuille, A. L. 1991. A common framework for image segmentation. Int. J. Computer Vision 6(3), 227-243.
9. Gold, S., and Rangarajan, A. 1996a. A graduated assignment algorithm for graph matching. IEEE Trans. Patt. Anal. Mach. Intell. (in press).
10. Gold, S., and Rangarajan, A. 1996b. Softmax to softassign: Neural network algorithms for combinatorial optimization. J. Artificial Neural Networks. Special issue on neural networks for optimization. (in press).
11. Gold, S., Lu, C. P., Rangarajan, A., Pappu, S., and Mjolsness, E. 1995. New algorithms for 2-D and 3-D point matching: Pose estimation and correspondence. In Advances in Neural Information Processing Systems 7, G. Tesauro, D. Touretzky, and J. Alspector, eds., pp. 957-964. MIT Press, Cambridge, MA.
12. Gold, S., Rangarajan, A., and Mjolsness, E. 1996. Learning with preknowledge: Clustering with point- and graph-matching distance measures. Neural Comp. 8(4): 787-804.
13. Golden, B. L., and Stewart, W. R. 1985. Empirical analysis of heuristics, Chap. 7. In The Traveling Salesman Problem: A Guided Tour of Combinatorial Optimization, E. L. Lawler, J. K. Lenstra, A. H. G. R. Kan, and D. B. Shmoys, eds., pp. 207-249. John Wiley, New York.
14. Hopfield, J. J., and Tank, D. 1985. "Neural" computation of decisions in optimization problems. Biol. Cybern. 52, 141-152.
15. Jordan, M. I., and Jacobs, R. A. 1994. Hierarchical mixtures of experts and the EM algorithm. Neural Comp. 6(2), 181-214.
16. Kamgar-Parsi, B., and Kamgar-Parsi, B. 1990. On problem solving with Hopfield networks. Biol. Cybern. 62, 415-423.
17. Kanter, I., and Sompolinsky, H. 1987. Graph optimisation problems and the Potts glass. J. Phys. A 20, L673-L677.
18. Koch, C., Marroquin, J., and Yuille, A. L. 1986. Analog "neuronal" networks in early vision. Proc. Natl. Acad. Sci. U.S.A. 83, 4263-4267.
19. Kosowsky, J. J., and Yuille, A. L. 1994. The invisible hand algorithm: Solving the assignment problem with statistical physics. Neural Networks 7(3), 477-490.
20. Luenberger, D. 1984. Linear and Nonlinear Programming. Addison-Wesley, Reading, MA.
21. Mjolsness, E. 1987. Control of attention in neural networks. In IEEE International Conference on Neural Networks (ICNN), Vol. 2, pp. 567-574. IEEE Press, New York.
22. Mjolsness, E., and Garrett, C. 1990. Algebraic transformations of objective functions. Neural Networks 3, 651-669.
23. Mjolsness, E., and Miranker, W. 1993. Greedy Lagrangians for neural networks. Tech. Rep. YALEU/DCS/TR-945, Department of Computer Science, Yale University.
24. Mjolsness, E., Gindi, G., and Anandan, P. 1989. Optimization in model matching and perceptual organization. Neural Comp. 1(2), 218-229.
25. Peterson, C., and Söderberg, B. 1989. A new method for mapping optimization problems onto neural networks. Inter. J. Neural Syst. 1(1), 3-22.
26. Rangarajan, A., and Mjolsness, E. 1994. A Lagrangian relaxation network for graph matching. In IEEE International Conference on Neural Networks (ICNN), Vol. 7, pp. 4629-4634. IEEE Press, New York.
27. Simić, P. D. 1990. Statistical mechanics as the underlying theory of 'elastic' and 'neural' optimisations. Network 1, 89-103.
28. Simić, P. D. 1991. Constrained nets for graph matching and other quadratic assignment problems. Neural Comp. 3, 268-281.
29. Sinkhorn, R. 1964. A relationship between arbitrary positive matrices and doubly stochastic matrices. Ann. Math. Statist. 35, 876-879.
30. Strang, G. 1986. Introduction to Applied Mathematics, p. 688. Wellesley-Cambridge Press, Wellesley, MA.
31. Umeyama, S. 1988. An eigendecomposition approach to weighted graph matching problems. IEEE Trans. Patt. Anal. Mach. Intell. 10(5), 695-703.
32. Van den Bout, D. E., and Miller, T. K. 1989. Improving the performance of the Hopfield-Tank neural network through normalization and annealing. Biol. Cybern. 62, 129-139.
33. Van den Bout, D. E., and Miller, T. K. 1990. Graph partitioning using annealed neural networks. IEEE Trans. Neural Networks 1(2), 192-203.
34. von der Malsburg, C. 1988. Pattern recognition by labeled graph matching. Neural Networks 1, 141-148.
35. von der Malsburg, C. 1990. Network self-organization. In An Introduction to Neural and Electronic Networks, S. F. Zornetzer, J. L. Davis, and C. Lau, eds., pp. 421-432. Academic Press, San Diego, CA.
36. Waugh, F. R., and Westervelt, R. M. 1993. Analog neural networks with local competition. I. Dynamics and stability. Phys. Rev. E 47(6), 4524-4536.
37. Wilson, G. V., and Pawley, G. S. 1988. On the stability of the traveling salesman problem algorithm of Hopfield and Tank. Biol. Cybern. 58, 63-70.
38. Wolfe, W. J., Parry, M. H., and MacMillan, J. M. 1994. Hopfield-style neural networks and the TSP. In IEEE International Conference on Neural Networks (ICNN), Vol. 7, pp. 4577-4582. IEEE Press, New York.
39. Yuille, A. L., and Kosowsky, J. J. 1994. Statistical physics algorithms that converge. Neural Comp. 6(3), 341-356.