Abstract
When dealing with large evolving datasets one needs machine learning models able to adapt to the growing number of information. In particular, stream classification is a research topic where classifiers need an ability to rapidly change their solutions and behave stably after many changes in training set structure. In this paper we show how recently proposed Extreme Entropy Machine can be trained in an online fashion supporting not only adding/removing points to/from the model but even changing the size of the internal representation on demand. In particular we show how one can build a well-conditioned covariance estimator in an online scenario. All these operations are guaranteed to converge to the optimal solutions given by their offline counterparts.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
\(A^2\) denotes element-wise squaring of A.
- 2.
Up to numerical errors.
- 3.
- 4.
\(\text {BAC} = \tfrac{1}{2}\left( \tfrac{\text {TP}}{\text {TP} + \text {FN}} + \tfrac{\text {TN}}{\text {TN} + \text {FP}} \right) \).
- 5.
We use Moore–Penrose pseudoinverse solution.
References
Bache, K., Lichman, M.: UCI machine learning repository. http://archive.ics.uci.edu/ml (2013)
Bartocha, K., Podolak, I.T.: Classifier ensembles for virtual concept drift-the DEnboost algorithm. In: Corchado, E., Kurzyński, M., Woźniak, M. (eds.) Hybrid Artificial Intelligent Systems, pp. 164–171. Springer, Berlin (2011)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Chong, E.K., Zak, S.H.: An Introduction to Optimization, vol. 76. Wiley, New York (2013)
Czarnecki, W.M., Tabor, J.: Extreme entropy machines: robust information theoretic classification. Pattern Anal. Appl. (2015). doi:10.1007/s10044-015-0497-8
Czarnecki, W.M., Tabor, J.: Multithreshold entropy linear classifier: theory and applications. Expert Syst. Appl. 42, 5591–5606 (2015)
Drineas, P., Mahoney, M.W.: On the nyström method for approximating a gram matrix for improved kernel-based learning. J. Mach. Learn. Res. 6, 2153–2175 (2005)
Fernández-Delgado, M., Cernadas, E., Barro, S., Amorim, D.: Do we need hundreds of classifiers to solve real world classification problems? J. Mach. Learn. Res. 15(1), 3133–3181 (2014)
Gaber, M.M., Zaslavsky, A., Krishnaswamy, S.: Mining data streams: a review. ACM Sigmod Rec. 34(2), 18–26 (2005)
Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: a new learning scheme of feedforward neural networks. In: Proceedings. 2004 IEEE International Joint Conference on Neural Networks, vol. 2, pp. 985–990. IEEE (2004)
Kosina, P., Gama, J.: Very fast decision rules for classification in data streams. Data Min. Know. Discov. 29(1), 168–202 (2015)
Krawczyk, B., Stefanowski, J., Wozniak, M.: Data stream classification and big data analytics. Neurocomputing 150, 238–239 (2015)
Lakshminarayanan, B., Roy, D.M., Teh, Y.W.: Mondrian forests: efficient online random forests. In: Advances in Neural Information Processing Systems, pp. 3140–3148 (2014)
Ledoit, O., Wolf, M.: A well-conditioned estimator for large-dimensional covariance matrices. J. Multivar. Anal. 88(2), 365–411 (2004)
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Settles, B.: Active learning. Synth. Lect. Artif. Intel. Mach. Learn. 6(1), 1–114 (2012)
Zong, W., Huang, G.B., Chen, Y.: Weighted extreme learning machine for imbalance learning. Neurocomputing 101, 229–242 (2013)
Acknowledgments
The work of the first author was partially founded by National Science Centre Poland grant no. 2013/09/N/ST6/03015, while the work of the second one by National Science Centre Poland grant no. 2014/13/B/ST6/01792.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Czarnecki, W.M., Tabor, J. (2016). Online Extreme Entropy Machines for Streams Classification and Active Learning. In: Burduk, R., Jackowski, K., Kurzyński, M., Woźniak, M., Żołnierek, A. (eds) Proceedings of the 9th International Conference on Computer Recognition Systems CORES 2015. Advances in Intelligent Systems and Computing, vol 403. Springer, Cham. https://doi.org/10.1007/978-3-319-26227-7_35
Download citation
DOI: https://doi.org/10.1007/978-3-319-26227-7_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26225-3
Online ISBN: 978-3-319-26227-7
eBook Packages: EngineeringEngineering (R0)