Abstract
We propose a k-winner-takes-all (KWTA) classifier for structures represented by graphs. The KWTA classifier is a neural network implementation of the k-nearest neighbor (KNN) rule. The commonly used comparator for identifying the k nearest neighbors of a given input structure is replaced by an inhibitory winner-takes-all network for k-maximum selection. Due to the principle elimination of competition the KWTA classifier circumvents the problem of determining computational intensive structural similarities between a given input structure and several model structures. In experiments on handwritten digits we compare the performance of the self-organizing KWTA classifier with the canonical KNN classifier, which uses a supervising comparator.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ambler, A.P., Barrow, H.G., Brown, C.M., Burstall, R.M., Popplestone, R.J.: A versatile computer-controlled assembly system. In: International Joint Conference on Artificial Intelligence, Stanford University, California, pp. 298–307 (1973)
Barrow, H., Burstall, R.: Subgraph isomorphism, matching relational structures and maximal cliques. Information Processing Letters 4, 83–84 (1976)
Bomze, I.M., Budinich, M., Pardalos, P.M., Pelillo, M.: The maximum clique problem. In: Du, D.-Z., Pardalos, P.M. (eds.) Handbook of Combinatorial Optimization, vol. 4, pp. 1–74. Kluwer Academic Publishers, Boston (1999)
Christmas, W.J., Kittler, J., Petrou, M.: Structural matching in computer vision using probabilistic relaxation. IEEE Transactions on Pattern Analysis and Machine Intelligence 17(8), 749–764 (1995)
Eshera, M.A., Fu, K.S.: An image understanding system using attributed symbolic representation and inexact graph-matching. IEEE Transactions on Pattern Analysis and Machine Intelligence 8(5), 604–618 (1986)
Garey, M., Johnson, D.: Computers and Intractability: A Guide to the Theory of NPCompleteness. W.H. Freeman and Company, New York (1979)
Gold, S., Rangarajan, A.: A graduated assignment algorithm for graph matching. IEEE Transactions on Pattern Analysis and Machine Intelligence 18(4), 377–388 (1996)
Günter, S., Bunke, H.: Adaptive self-organizing map in the graph domain. In: Bunke, H., Kandel, A. (eds.) Hybrid Methods in Pattern Recognition, pp. 61–74. World Scientific, Singapore (2002)
Günter, S., Bunke, H.: Self-organizing map for clustering in the graph domain. Pattern Recognition Letters 23, 401–417 (2002)
Hopfield, J.J., Tank, D.W.: Neural computation of decisions in optimization problems. Biological Cybernetics 52, 141–152 (1985)
Jagota, A.: Approximating maximum clique with a Hopfield network. IEEE Trans. Neural Networks 6, 724–735 (1995)
Jain, B.J., Wysotzki, F.: Fast winner-takes-all networks for the maximum clique problem. In: 25th German Conference on Artificial Intelligence, pp. 163–173. Springer, Heidelberg (2002)
Jain, B.J., Wysotzki, F.: A novel neural network approach to solve exact and inexact graph isomorphism problems. In: Kaynak, O., Alpaydın, E., Oja, E., Xu, L. (eds.) ICANN 2003 and ICONIP 2003. LNCS, vol. 2714. Springer, Heidelberg (2003)
Koutroumbas, K., Kalouptsidis, N.: Qualitative analysis of the parallel and asynchronous modes of the hamming network. IEEE Transactions on Neural Networks 15(3), 380–391 (1994)
LeCun, Y.: The MNIST Database of Handwritten Digits. NEC Research Institute, Princeton, NJ (2003), http://yann.lecun.com/exdb/mnist/
Levi, G.: Anote on the derivation of maximal common subgraphs of two directed or undirected graphs. Calcolo 9, 341–352 (1972)
Lippman, R.P.: An introduction to computing with neural nets. IEEE ASSP Magazine, 4–22 (April 1987)
Lumini, A., Maio, D., Maltoni, D.: Inexact graph matching for fingerprint classification. Machine GRAPHICS and VISION, Special issue on Graph Transformations in Pattern Generation and CAD 8(2), 231–248 (1999)
Majani, E., Erlanson, R., Abu-Mostafa, Y.: On the k-winner-take-all network. Advances in Neural Information Processing Systems 1, 634–642 (1989)
Pelillo, M., Siddiqi, K., Zucker, S.W.: Matching hierarchical structures using association graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence 21(11), 1105–1120 (1999)
Rangarajan, S.: Gold, and E. Mjolsness. A novel optimizing network architecture with applications. Neural Computation 8(5), 1041–1060 (1996)
Raymond, J.W., Gardiner, E.J., Willett, P.: Heuristics for similarity searching of chemical graphs using a maximum common edge subgraph algorithm. Journal of Chemical Information and Computer Sciences 42(2), 305–316 (2002)
Schädler, K., Wysotzki, F.: Comparing structures using a Hopfield-style neural network. Applied Intelligence 11, 15–30 (1999)
Shapiro, L.G., Haralick, R.M.: Structural descriptions and inexact matching. IEEE Transaction on Pattern Analysis and Machine Intelligence 3, 514–519 (1981)
Siddiqi, K., Shokoufandeh, A., Dickinson, S., Zucker, S.: Shock graphs and shape matching. International Journal of Computer Vision 35, 13–32 (1999)
Sperduti, A., Starita, A.: Supervised neural networks for the classification of structures. IEEE Transactions on Neural Networks 8(3), 714–735 (1997)
Suganthan, P., Teoh, E., Mital, D.: Pattern recognition by graph matching using potts mft networks. Pattern Recognition 28, 997–1009 (1995)
Wong, A., You, M.: Entropy and distance of random graphs with application to structural pattern recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 7(5), 599–609 (1985)
Yu, S.-S., Tsai, W.-H.: Relaxation by the hopfield neural network. Pattern Recognition 25(2), 197–209 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jain, B.J., Wysotzki, F. (2003). A k-Winner-Takes-All Classifier for Structured Data. In: Günter, A., Kruse, R., Neumann, B. (eds) KI 2003: Advances in Artificial Intelligence. KI 2003. Lecture Notes in Computer Science(), vol 2821. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39451-8_25
Download citation
DOI: https://doi.org/10.1007/978-3-540-39451-8_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20059-8
Online ISBN: 978-3-540-39451-8
eBook Packages: Springer Book Archive