Learning about the Learning Process
This work addresses the problem of mining data stream generated in dynamic environments where the distribution underlying the observations may change over time. We present a system that monitors the evolution of the learning process. The system is able to self-diagnosis degradations of this process, using change detection mechanisms, and self-repairs the decision models. The system uses meta-learning techniques that characterize the domain of applicability of previously learned models. The meta-learns can detect re-occurrence of contexts, using unlabeled examples, and take pro-active actions by activating previously learned models.
KeywordsData streams concept drift meta-learning recurrent concepts
Unable to display preview. Download preview PDF.
- 3.Granitzer, M., Kröll, M., Seifert, C., Rath, A.S., Weber, N., Dietzel, O., Lindstaedt, S.N.: Analysis of machine learning techniques for context extraction. In: Pichappan, P., Abraham, A. (eds.) ICDIM, pp. 233–240. IEEE, Los Alamitos (2008)Google Scholar
- 7.Klinkenberg, R.: Learning drifting concepts: Example selection vs. example weighting. Intelligent Data Analysis 8(3), 281–300 (2004)Google Scholar
- 8.Lazarescu, M.M.: A multi-resolution learning approach to tracking concept drift and recurrent concepts. In: Proceedings of the 5th International Workshop on Pattern Recognition in Information Systems (2005)Google Scholar
- 9.Ortega, J.: Exploiting multiple existing models and learning algorithms. In: AAAI 1996 - Workshop in Induction of Multiple Learning Models, pp. 17–21 (1995)Google Scholar
- 11.Ramamurthy, S., Bhatnagar, R.: Tracking recurrent concept drift in streaming data using ensemble classifiers. In: ICMLA 2007: Proceedings of the Sixth International Conference on Machine Learning and Applications, pp. 404–409. IEEE Computer Society, Washington, DC, USA (2007)Google Scholar
- 13.Nick Street, W., Kim, Y.: A streaming ensemble algorithm (sea) for large-scale classification. In: Knowledge Discovery and Data Mining, pp. 377–382. ACM Press, New York (2001)Google Scholar
- 14.Turney, P.: The management of context-sensitive features: A review of strategies (1996)Google Scholar
- 16.Widmer, G., Kubat, M.: Learning in the presence of concept drift and hidden contexts. Machine Learning 23(1), 69–101 (1996)Google Scholar