Abstract
The Error-Correcting Output Codes (ECOC) is a representative approach of the binary ensemble classifiers for solving multi-class problems. There have been so many researches on an output coding method built on an ECOC foundation. In this paper, we revisit representative conventional ECOC methods in an overlapped learning viewpoint. For this purpose, we propose new OPC based output coding methods in the ECOC point of view, and define a new measure to describe their properties. From the experiment on a face recognition domain, we investigate whether a problem complexity is more important than the overlapped learning or an error correction concept.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Dietterich, T., Bakiri, G.: Solving Multiclass Learning Problems via Error-Correcting Output Codes. Journal of Artificial Intelligence Research 2, 263–286 (1995)
Masulli, F., Valentini, G.: Effectiveness of Error Correcting Output Codes in Multiclass Learning Problems. In: Kittler, J., Roli, F. (eds.) MCS 2000. LNCS, vol. 1857, pp. 107–115. Springer, Heidelberg (2000)
Windeatt, T., Ghaderi, R.: Coding and decoding strategies for multi-class learning problems. Information Fusion 4, 11–21 (2003)
Rassch, G., Smola, A.: Adapting Codes and Embeddings for Polychotomies. In: Advances in Neural Information Processing Systems, vol. 15 (2003)
James, G., Hastie, T.: The Error Coding Method and PICTs. Computational and Graphical Statistics 7, 337–387 (1998)
Furnkranz, J.: Round Robin Rule Learning. In: Proc. of the 18th Int’l Conf. on Machine Learning, pp. 146–153 (2001)
Vapnik, V.: Statistical Learning Theory. John Wiley & Sons, New York (1998)
Tumar, K., Gosh, J.: Error Correlation and Error Reduction in Ensemble Classifier. Tech. Report, Dept. of ECE, Univ. Texas (July 11, 1996)
Allwein, E., Schapire, R., Singer, Y.: Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers. Journal of Machine Learning Research 1, 113–141 (2000)
Moreira, M., Mayoraz, E.: Improved Pairwise Coupling Classification with Correcting Classifiers. In: Nédellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398, pp. 160–171. Springer, Heidelberg (1998)
Ghosh, J.: Multiclassifier Systems: Back to the Future. In: Roli, F., Kittler, J. (eds.) MCS 2002. LNCS, vol. 2364, pp. 1–15. Springer, Heidelberg (2002)
Hastie, T., Tibshirani, R.: Classification by Pairwise Coupling. In: Advances in Neural Information Processing Systems, vol. 10, pp. 507–513. MIT Press, Cambridge (1998); The Annals of Statistics 26(1), 451–471 (1998)
Phillips, P., Moon, H., Rizvi, S., Rauss, P.: The FERET evaluation methodology for face-recognition algorithms. IEEE Trans. Pattern Analysis and Machine Intelligence 22(10), 1090–1104 (2000)
Almedia, M.: SMOBR-A SMO program for training SVMs, Dept. of EE, Univ. of Minas Gerais (2000), Available http://www.litc.cpdee.ufmg.br/~barros/svm/smobr
Platt, J.: Sequential minimal optimization: A fast algorithm for training support vector machines. Tech. Report 98-14, Microsoft Research, Redmond (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ko, J., Kim, E. (2005). On ECOC as Binary Ensemble Classifiers. In: Perner, P., Imiya, A. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2005. Lecture Notes in Computer Science(), vol 3587. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11510888_1
Download citation
DOI: https://doi.org/10.1007/11510888_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26923-6
Online ISBN: 978-3-540-31891-0
eBook Packages: Computer ScienceComputer Science (R0)