Abstract
We present a wide experimental work evaluating the behaviour of Recursive ECOC (RECOC) [1] learning machines based on Low Density Parity Check (LDPC) coding structures. We show that owing to the iterative decoding algorithms behind LDPC codes, RECOC multiclass learning is progressively achieved. This learning behaviour confirms the existence of new boosting dimension, the one provided by the coding space. We present a method for searching potential good RECOC codes from LDPC ones. Starting from a properly selected LDPC code, we assess the effect of boosting in both weak and strong binary learners. For nearly all domains, we find that boosting a strong learner like a Decision Tree is as effective as boosting a weak one like a Decision Stump. This surprising result substantiates the hypothesis that weakening strong classifiers by boosting has a decorrelation effect, which can be used to improve RECOC learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Tapia, E., González, J.C., García Villalba, J., Villena, J.: Recursive Adaptive ECOC models. In: Brazdil, P.B., Jorge, A.M. (eds.) EPIA 2001. LNCS (LNAI), vol. 2258, p. 96. Springer, Heidelberg (2001)
Dietterich, T., Bakiri, G.: Error-correcting output codes: A general method for improving multiclass inductive learning programs. In: Proceedings of the Ninth National Conference on Artificial Intelligence (AAAI 1991), pp. 572–577. AAAI Press, Anaheim (1991)
Crammer, K., Singer, Y.: On the Learnability and Design of Output Codes for Multiclass Problems. In: Cesa-Bianchi, N., Goldman, S.A. (eds.) Proceedings COLT 2000, pp. 35–46. Morgan Kaufmann, Palo Alto (2000)
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)
Tapia, E., González, J.C., García, J.: Good Error Correcting Output Codes For Adaptive Multiclass Learning. In: Windeatt, T., Roli, F. (eds.) MCS 2003. LNCS, vol. 2709, Springer, Heidelberg (2003)
Tanner, M.: A recursive approach to Low Complexity Error Correcting Codes. IEEE Trans. Inf. Theory 27, 533–547 (1981)
Kschischang, F., Frey, B.: Iterative decoding of compound codes by probability propagation in graphical models. IEEE Journal on Sel. Areas in Communications 16(2), 219–230 (1998)
Gallager, R.G.: Low Density Parity-Check Codes. M.I.T. Press, Cambridge (1963)
MacKay, D.J.: Good Error Correcting Codes based on Very Sparse Matrices. IEEE Trans. Inf. Theory 45, 399–431 (1999)
Guruswami, V., Sahai, A.: Multiclass Learning, Boosting, and Error-Correcting Codes. In: Proceedings COLT 1999, Santa Cruz, CA, USA, pp. 145–155 (1999)
Masulli, F., Valentini, G.: Dependence among Codeword Bits Error in ECOC Learning: An Experimental Analysis. In: Kittler, J., Roli, F. (eds.) MCS 2001. LNCS, vol. 2096, p. 158. Springer, Heidelberg (2001)
Schapire, R.E., Singer, Y.: Improved Boosting Algorithms Using Confidence - rated Predictions. Machine Learning 37(3), 277–296 (1999)
Tapia, E., González, J.C., García-Villalba, J.: A Generalized Class of Boosting Algorithms based on Recursive Error Correcting Codes. In: Kittler, J., Roli, F. (eds.) MCS 2001. LNCS, vol. 2096, p. 22. Springer, Heidelberg (2001)
Witten, I., Frank, E.: Data Mining, Practical Machine Learning Tools and Techniques with JAVA Implementations. Morgan Kaufmann Publishers, San Francisco (2000)
Furkranz, J.: Round Robin Classification. Journal of Machine Learning Research 2, 721–747 (2002)
Rifkin, R.: Everything Old is New Again: A Fresh Look at the Historical Approaches in Machine Learning. Ph.D. Thesis. Massachusetts Institute of Technology (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tapia, E., González, J.C., Hütermann, A., García, J. (2004). Beyond Boosting: Recursive ECOC Learning Machines. In: Roli, F., Kittler, J., Windeatt, T. (eds) Multiple Classifier Systems. MCS 2004. Lecture Notes in Computer Science, vol 3077. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-25966-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-540-25966-4_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22144-9
Online ISBN: 978-3-540-25966-4
eBook Packages: Springer Book Archive