Combining Multiple Models with Meta Decision Trees

Todorovski, Ljupčo; Džeroski, Sašo

doi:10.1007/3-540-45372-5_6

Cited by 109 publications

(105 citation statements)

References 8 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to [39], the entropy of the probability distribution reflects the certainty of the classifier in the predicted class value. The entropy of the probability distribution is computed as:…”

Section: Active Learning: Uncertainty Methods Bmentioning

confidence: 99%

Selective generation of training examples in active meta-learning

Prudêncio

Ludermir

2008

HIS

View full text Add to dashboard Cite

Abstract. Meta-Learning has been successfully applied to acquire knowledge used to support the selection of learning algorithms. Each training example in Meta-Learning (i.e. each meta-example) is related to a learning problem and stores the experience obtained in the empirical evaluation of a set of candidate algorithms when applied to the problem. The generation of a good set of meta-examples can be a costly process depending for instance on the number of available learning problems and the complexity of the candidate algorithms. In this work, we proposed the Active Meta-Learning, in which Active Learning techniques are used to reduce the set of meta-examples by selecting only the most relevant problems for meta-example generation. In an implemented prototype, we evaluated the use of two different Active Learning techniques applied in two different Meta-Learning tasks. The performed experiments revealed a significant gain in the Meta-Learning performance when the active techniques were used to support the meta-example generation.

show abstract

Section: Active Learning: Uncertainty Methods Bmentioning

confidence: 99%

Selective generation of training examples in active meta-learning

Prudêncio

Ludermir

2008

HIS

View full text Add to dashboard Cite

show abstract

“…In [7], a variant of stacking using the Multi-response Logistic Regression (MLR) for the meta classifier is proposed and it makes full use of the class distributions from the base classifiers to gain a good ensemble. In [8], the stacking using a modified decision tree as the meta classifier is proposed. In [9], StackingC, a variant of stacking with MLR, is proposed for multi-class classification.…”

Section: Related Workmentioning

confidence: 99%

“…Exhaustive search, with no doubt, would cause a large cost of time and is impractical. In the earlier years, researchers used fixed configurations for classification [7,8,9,10]. But the results were ragged over multiple datasets because the configuration selection is domain specific.…”

Section: Introductionmentioning

confidence: 99%

An Advanced Genetic Approach for Stacking Classifiers

Qin¹,

Wang²,

Peng³

et al. 2017

dtcse

View full text Add to dashboard Cite

Abstract.A key to obtain a high quality of stacking ensemble is to select a proper configuration for the specific dataset. Various approaches are proposed on this topic. GA-Ensemble is an effective approach using genetic algorithm to select the configuration. However, the weakness of the problem encoding and the reproduction of unnecessary individuals in GA-Ensemble impact the accuracy of the approach. In this work, the subspace partition and a tabu strategy are used to improve the accuracy of GA-Ensemble. The results over 13 UCI datasets show that the new proposed approach has a better performance.

show abstract

“…One of the approaches to meta-learning develops methods of decision committee construction and various stacking strategies, also performing nontrivial analysis of member models to draw committee conclusions (Chan and Stolfo, 1996;Prodromidis and Chan, 2000;Todorovski and Dzeroski, 2003;Duch and Itert, 2003;Jankowski and Grąbczewski, 2005;Troć and Unold, 2010). Another group of meta-learning enterprises (Pfahringer et al, 2000;Brazdil et al, 2003;Bensusan et al, 2000;Peng et al, 2002) is based on data characterization techniques (characteristics of data like the number of features/vectors/classes, feature variances, information measures on features, also from decision trees, etc.)…”

Section: Introductionmentioning

confidence: 99%

Graph-based generation of a meta-learning search space

Jankowski

2012

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

Meta-learning is becoming more and more important in current and future research concentrated around broadly defined data mining or computational intelligence. It can solve problems that cannot be solved by any single, specialized algorithm. The overall characteristic of each meta-learning algorithm mainly depends on two elements: the learning machine space and the supervisory procedure. The former restricts the space of all possible learning machines to a subspace to be browsed by a meta-learning algorithm. The latter determines the order of selected learning machines with a module responsible for machine complexity evaluation, organizes tests and performs analysis of results. In this article we present a framework for meta-learning search that can be seen as a method of sophisticated description and evaluation of functional search spaces of learning machine configurations used in meta-learning. Machine spaces will be defined by specially defined graphs where vertices are specialized machine configuration generators. By using such graphs the learning machine space may be modeled in a much more flexible way, depending on the characteristics of the problem considered and a priori knowledge. The presented method of search space description is used together with an advanced algorithm which orders test tasks according to their complexities.

show abstract

Combining Multiple Models with Meta Decision Trees

Cited by 109 publications

References 8 publications

Selective generation of training examples in active meta-learning

Selective generation of training examples in active meta-learning

An Advanced Genetic Approach for Stacking Classifiers

Graph-based generation of a meta-learning search space

Contact Info

Product

Resources

About