摘要: This paper presents a novel approach for the creation of intelligent machine learning programs. It introduces generic tasks as basic processes and describes their representation integration. The role knowledge in an system is identified to fine granularity. new allows integration multiple into that can select appropriate process based on its background task. Three ways which improves bias over similar classes problems are identified. demonstrated domain bridge design. work has been supported by Engineering Design Research Center, NSF part Sun Company grant Research. University Libraries Carnegie Mellon Pittsburgh, Pennsylvania 15213
参考文章(24)
Steven Minton, Quantitative results concerning the utility of explanation-based learning national conference on artificial intelligence. pp. 564- 569 ,(1988)
Stuart J. Russell, Tree-structured bias national conference on artificial intelligence. pp. 641- 645 ,(1988)
Jean-Gabriel Ganascia, Improvement and refinement of the learning bias semantic european conference on artificial intelligence. pp. 384- 389 ,(1988)
Stuart J. Russell, Benjamin N. Grosof, A declarative approach to bias in concept learning national conference on artificial intelligence. pp. 505- 510 ,(1987)
Chris S. Wallace, Michael P. Georgeff, A general selection criterion for inductive inference european conference on artificial intelligence. pp. 219- 228 ,(1984)
Jeffrey C. Schlimmer, Learning and representation change national conference on artificial intelligence. pp. 511- 515 ,(1987)
Paul E. Utgoff, Machine Learning of Inductive Bias ,(1986)
LARRY RENDELL, RAJ SESHU, DAVID TCHENG, MORE ROBUST CONCEPT LEARNING USING DYNAMICALLY – VARIABLE BIAS Proceedings of the Fourth International Workshop on MACHINE LEARNING#R##N#June 22–25, 1987 University of California, Irvine. pp. 66- 78 ,(1987) , 10.1016/B978-0-934613-41-5.50011-8
Robert E. Stepp, Bradley L. Whitehall, Lawrence B. Holder, Towards intelligent machine learning algorithms european conference on artificial intelligence. pp. 333- 338 ,(1988) , 10.21236/ADA197049
Douglas Bruce Lenat, AM, an artificial intelligence approach to discovery in mathematics as heuristic search ,(1976)