Generation of attributes for learning algorithms
作者： Yuh-Jyh Hu , Dennis Kibler
DOI:
关键词:
摘要: Inductive algorithms rely strongly on their representational biases. Constructive induction can mitigate inadequacies. This paper introduces the notion of a relative gain measure and describes new constructive algorithm (GALA) which is independent learning algorithm. Unlike most previous research induction, our methods are designed as preprocessing step before standard machine applied. We present results demonstrate effectiveness GALA artificial real domains for several learners: C4.5, CN2, percept ron backpropagation.
nctu.edu.tw
osti.gov参考文章(15)
Steven W. Norton, Generating better decision trees international joint conference on artificial intelligence. pp. 800- 805 ,(1989)
Larry A. Rendell, Christopher J. Matheus, Constructive induction on decision trees international joint conference on artificial intelligence. pp. 645- 650 ,(1989)
Der-Shung Yang, Larry Rendell, Gunnar Blix, A scheme for feature construction and a comparison of empirical methods international joint conference on artificial intelligence. pp. 699- 704 ,(1991)
Larry Rendell, Harish Ragavan, Improving the design of induction methods by analyzing algorithm functionality and data-based concept complexity international joint conference on artificial intelligence. pp. 952- 959 ,(1993)
Larry Rendell, Antoinette Tessmer, Harish Ragavan, Michael Shaw, Complex concept acquisition through directed search and feature caching international joint conference on artificial intelligence. pp. 946- 951 ,(1993)
David W. Aha, Incremental Constructive Induction: An Instance-Based Approach Machine Learning Proceedings 1991. pp. 117- 121 ,(1991) , 10.1016/B978-1-55860-200-7.50027-1
Tom E. Fawcett, Paul E. Utgoff, Automatic Feature Generation for Problem Solving Systems international conference on machine learning. pp. 144- 153 ,(1992) , 10.1016/B978-1-55860-247-2.50024-3
Thomas G. Dietterich, Ryszard S. Michalski, Inductive learning of structural descriptions: Evaluation criteria and comparative review of selected methods Artificial Intelligence. ,vol. 16, pp. 257- 294 ,(1981) , 10.1016/0004-3702(81)90002-3
JEFFREY C. SCHLIMMER, Incremental Adjustment of Representations for Learning Proceedings of the Fourth International Workshop on MACHINE LEARNING#R##N#June 22–25, 1987 University of California, Irvine. pp. 79- 90 ,(1987) , 10.1016/B978-0-934613-41-5.50012-X
Harish Ragavan, Larry Rendell, Lookahead feature construction for learning hard concepts international conference on machine learning. pp. 252- 259 ,(1993) , 10.1016/B978-1-55860-307-3.50039-3