Abstract
Many applications require to jointly learn a set of related functions for which some a–priori mutual constraints are known. In particular, we consider a multitask learning problem in which a set of constraints among the different tasks are know to hold in most cases. Basically, beside a set of supervised examples provided to learn each task, we assume that some background knowledge is available in the form of functions that define the admissible configurations of the task function outputs for almost each input. We exploit a semi–supervised approach in which a potentially large set of unlabeled examples is used to enforce the constraints on a large region of the input space by means of a proper penalty function. However, since the constraints are known to be subject to exceptions and the inputs corresponding to these exceptions are not known a–priori, we propose to embed a selection criterion in the penalty function that reduces the constraint effect on those points that are likely to yield an exception. We report some experiments on multi–view object recognition showing the benefits of the proposed selection mechanism with respect to an uniform enforcement of the constraints.
Keywords
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.
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
Shawe-Taylor, J.: Symmetries and discriminability in feedforward network architectures. IEEE Transactions on Neural Networks 4(5), 816–826 (1993)
Abu-Mostafa, Y.S.: Hints. Neural Computation 7(4), 639–671 (1995)
Caruana, R.: Multitask learning. Machine Learning 28(1), 41–75 (1997)
Melacci, S., Maggini, M., Gori, M.: Semi—supervised learning with constraints for multi—view object recognition. In: Alippi, C., Polycarpou, M., Panayiotou, C., Ellinas, G. (eds.) ICANN 2009. LNCS, vol. 5769, pp. 653–662. Springer, Heidelberg (2009)
Klir, G., Yuan, B.: Fuzzy sets and fuzzy logic: theory and applications. Prentice-Hall, Upper Saddle River (1995)
Murase, H., Nayar, S.: Visual learning and recognition of 3-d objects from appearance. International Journal of Computer Vision 14(1), 5–24 (1995)
Pontil, M., Verri, A.: Support vector machines for 3D object recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(6), 637–646 (1998)
Mori, G., Belongie, S., Malik, J.: Shape Contexts Enable Efficient Retrieval of Similar Shapes. In: Proc. of Int. Conf. on CVPR, vol. 1, pp. 723–730 (2001)
Liu, X., Srivastava, A.: 3D object recognition using perceptual components. In: Proc. of Int. Joint Conf. on Neural Networks, vol. 1, pp. 553–558 (2001)
Obdrzalek, S., Matas, J.: Object recognition using local affine frames on distinguished regions. In: Proc. of British Machine Vision, vol. 1, pp. 113–122 (2002)
Obdrzalek, S., Matas, J.: Sub-linear indexing for large scale object recognition. In: Proc. of the British Machine Vision Conf., vol. 1, pp. 1–10 (2005)
Lyu, S.: Mercer Kernels for Object Recognition with Local Features. In: Proc. of Int. Conf. on CVPR, vol. 2, pp. 223–229 (2005)
Christoudias, C.M., Urtasun, R., Darrell, T.: Unsupervised feature selection via distributed coding for multi-view object recognition. In: Proc. of CVPR, pp. 1–8 (2008)
Roobaert, D., Van Hulle, M.: View-based 3D object recognition with support vector machines. In: Neural Networks for Signal Processing, pp. 77–84 (1999)
Caputo, B., Dorko, G.: How to Combine Color and Shape Information for 3D Object Recognition: Kernels do the Trick. In: Advances in NIPS, pp. 1399–1406 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Maggini, M., Papini, T. (2010). Multitask Semi–supervised Learning with Constraints and Constraint Exceptions. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds) Artificial Neural Networks – ICANN 2010. ICANN 2010. Lecture Notes in Computer Science, vol 6354. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15825-4_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-15825-4_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15824-7
Online ISBN: 978-3-642-15825-4
eBook Packages: Computer ScienceComputer Science (R0)