Abstract
This paper presents a novel neural network model, called similarity neural network (SNN), designed to learn similarity measures for pairs of patterns. The model guarantees to compute a non negative and symmetric measure, and shows good generalization capabilities even if a very small set of supervised examples is used for training. Preliminary experiments, carried out on some UCI datasets, are presented, showing promising results.
Chapter PDF
Similar content being viewed by others
Keywords
- Similarity Measure
- Mahalanobis Distance
- Neural Network Approach
- Pairwise Constraint
- Sigmoidal Activation Function
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Tversky, A.: Features of Similarity. Psychological Review 84(4), 327–352 (1977)
Xing, E., Ng, A., Jordan, M., Russell, S.: Distance metric learning, with application to clustering with side-information. Advances in Neural Information Processing Systems 15, 505–512 (2003)
De Bie, T., Momma, M., Cristianini, N.: Efficiently learning the metric using side-information. In: Proc. Int. Conf. on Algorithmic Learning Theory, pp. 175–189 (2003)
Bilenko, M., Basu, S., Mooney, R.: Integrating constraints and metric learning in semi-supervised clustering. In: Proc. Int. Conf. on Machine Learning, pp. 81–88 (2004)
Basu, S., Bilenko, M., Mooney, R.: A probabilistic framework for semi-supervised clustering. In: Proc. Int. Conf. on Knowledge Discovery and Data Mining, pp. 59–68 (2004)
Bar-Hillel, A., Hertz, T., Shental, N., Weinshall, D.: Learning a Mahalanobis Metric from Equivalence Constraints. J. Machine Learning Research 6, 937–965 (2005)
Tsang, I., Kwok, J.: Distance metric learning with kernels. In: Proc. Int. Conf. on Artificial Neural Networks, pp. 126–129 (2003)
Bianchini, M., Gori, M., Scarselli, F.: Processing directed acyclic graphs with recursive neural networks. IEEE Trans. on Neural Networks 12(6), 1464–1470 (2001)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Melacci, S., Sarti, L., Maggini, M., Bianchini, M. (2008). A Neural Network Approach to Similarity Learning. In: Prevost, L., Marinai, S., Schwenker, F. (eds) Artificial Neural Networks in Pattern Recognition. ANNPR 2008. Lecture Notes in Computer Science(), vol 5064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69939-2_13
Download citation
DOI: https://doi.org/10.1007/978-3-540-69939-2_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69938-5
Online ISBN: 978-3-540-69939-2
eBook Packages: Computer ScienceComputer Science (R0)
