Ortega, J. (1996) Exploiting Multiple Existing Models and Learning Algorithms. AAAI96 Workshop on Integrating Multiple Learned Models for Improving and Scaling Machine Learning Algorithms [http://www.cs.fit.edu/~imlm/imlm96/]. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Combining Classifiers with Meta Decision Trees - Todorovski, Dzeroski (2003) (1 citation) (Correct)
....classi ers. An area of expertise of a base level classi er is relative in the sense that its predictive performance in that area is better as compared to the performances of the other base level classi ers. This is di erent from an area of expertise of an individual base level classi er [15], which is a subset of the data where the predictions of a single base level classi er are correct. Note that in the process of inducing meta decision trees two types of attributes are used. Ordinary attributes are used in the decision (inner) nodes of the MDT (e.g. attributes Conf 1 and Conf 2 ....
....ers, the class attributes are used in the same way as ordinary attributes. The partitioning of the data set into relative areas of expertise is based on the values of the ordinary meta level attributes used to induce MDTs. In existing studies about areas of expertise of individual classi ers [15], the original base level attributes from the domain at hand are used. We use a di erent set of ordinary attributes for inducing MDTs. These are properties of the class probability distributions predicted by the base level classi ers and re ect the certainty and con dence of the predictions. ....
[Article contains additional citation context not shown here]
Ortega, J. (1996) Exploiting Multiple Existing Models and Learning Algorithms. AAAI96 Workshop on Integrating Multiple Learned Models for Improving and Scaling Machine Learning Algorithms [http://www.cs.fit.edu/~imlm/imlm96/].
Combining Classifiers with Meta Decision Trees - Todorovski, Dzeroski (2003) (1 citation) (Correct)
....base level classi ers. An area of expertise of a base level classi er is relative in the sense that its predictive performance in that area is better as compared to the performances of the other base level classi ers. This is di erent from an area of expertise of an individual base level classi er [15], which is a subset of the data where the predictions of a single base level classi er are correct. Note that in the process of inducing meta decision trees two types of attributes are used. Ordinary attributes are used in the decision (inner) nodes of the MDT (e.g. attributes Conf 1 and Conf 2 ....
....ers, the class attributes are used in the same way as ordinary attributes. 8 The partitioning of the data set into relative areas of expertise is based on the values of the ordinary meta level attributes used to induce MDTs. In existing studies about areas of expertise of individual classi ers [15], the original base level attributes from the domain at hand are used. We use a di erent set of ordinary attributes for inducing MDTs. These are properties of the class probability distributions predicted by the base level classi ers and re ect the certainty and con dence of the predictions. ....
[Article contains additional citation context not shown here]
Ortega, J. (1996) Exploiting Multiple Existing Models and Learning Algorithms. AAAI96 Workshop on Integrating Multiple Learned Models for Improving and Scaling Machine Learning Algorithms [http://www.cs.fit.edu/~imlm/imlm96/].
Local Cascade Generalization - Gama (1998) (3 citations) (Correct)
....From uniform voting where the opinion of all base classifiers contributes to the final classification with the same strength, to weighted voting, where each base classifier has a weight associated, that could change over the time, and strengthens the classification given by the classifier. Ortega [20] presents the Model Applicability Induction approach for combining predictions from multiple models. The approach consists of learning for each available model a referee that characterize situations in which each of the models is able to make correct predictions. In future instances these ....
J. Ortega. Exploiting multiple existing models and learning algorithms. In AAAI 96 - Workshop in Induction of Multiple Learning Models, 1995.
Local Cascade Generalization - Gama (1998) (3 citations) (Correct)
....From uniform voting where the opinion of all base classifiers contributes to the final classification with the same strength, to weighted voting, where each base classifier has a weight associated, that could change over the time, and strengthens the classification given by the classifier. Ortega [17] presents MAI Model Applicability Induction approach for combining predictions from multiple models. The approach consists on learning for each available model a referee that characterize situations in which each of the models is able to make correct predictions. In future instances these ....
J. Ortega. Exploiting multiple existing models and learning algorithms. In AAAI 96 - Workshop in Induction of Multiple Learning Models, 1995.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC