Constructive meta-learning with machine learning method repositories

Hidenao Abe, Takahira Yamaguchi

研究成果: Conference article査読

19 被引用数 (Scopus)


Here is discussed what is constructive meta-learning and how it goes well compared with selective meta-learning that already becomes popular. Selective meta-learning takes multiple learning schemes with the following different ways: bagging, boosting, cascading and stacking methods. On the other hand, constructive meta-learning constructs the learning scheme proper to a given data set. We have implemented constructive meta-learning by recomposing methods into learning schemes with mining (inductive learning) method repositories that come from decomposition of popular mining algorithms. To evaluate our constructive meta-learning, we have done the comparison of the performances of our constructive meta-learning and those of two stacking methods, using UCI/ML common data sets. It has shown us that our constructive meta-learning goes better than the two stacking methods. Furthermore, it turns out to be promising that we apply constructive meta-learning to meta-learner in selective meta-learning.

ジャーナルLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
出版ステータスPublished - 2004 12 9
イベント17th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, IEA/AIE 2004 - Ottowa, Ont., Canada
継続期間: 2004 5 172004 5 20

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

フィンガープリント 「Constructive meta-learning with machine learning method repositories」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。