Correcting Imperfect Domain Theories: A Knowledge-Level Analysis

作者: Scott B. Huffman , Douglas J. Pearson , John E. Laird

DOI: 10.1007/978-1-4615-3172-2_6

关键词: Domain theoryVariety (cybernetics)Focus (optics)Descriptive knowledgeComputer scienceContrast (statistics)Theoretical computer scienceDomain (software engineering)Task (project management)Imperfect

摘要: Explanation-Based Learning (Mitchell et al., 1986; DeJong and Mooney, 1986) has shown promise as a powerful analytical learning technique. However, EBL is severely hampered by the requirement of complete correct domain theory for successful to occur. Clearly, in non-trivial domains, developing such nearly impossible task. Therefore, much research been devoted understanding how an imperfect can be corrected extended during system performance. In this paper, we present characterization problem, use it analyze past area. Past characterizations problem (e.g, Rajamoney DeJong, 1987)) have viewed types performance errors caused faulty primary. contrast, focus primarily on knowledge deficiencies theory, from these derive that result. Correcting search through space possible theories, with variety sources used guide search.

参考文章(60)
Jack Mostow, Subrata Roy, Parsing to learn fine grained rules national conference on artificial intelligence. pp. 547- 551 ,(1988)
Richard J. Doyle, Constructing and refining causal explanations from an inconsistent domain theory national conference on artificial intelligence. pp. 538- 544 ,(1986)
Scott W. Bennett, Approximation in mathematical domains international joint conference on artificial intelligence. pp. 239- 241 ,(1987)
Ajay Gupta, Explanation-based failure recovery national conference on artificial intelligence. pp. 606- 610 ,(1987)
Michael J. Pazzani, Detecting and correcting errors of omission after explanation-based learning international joint conference on artificial intelligence. pp. 713- 718 ,(1989)
FRANCESCO BERGADANO, ATTILIO GIORDANA, A Knowledge Intensive Approach to Concept Induction. international conference on machine learning. pp. 305- 317 ,(1988) , 10.1016/B978-0-934613-64-4.50037-2
Andrea Pohoreckyj Danyluk, The use of explanations for similarity-based learning international joint conference on artificial intelligence. pp. 274- 276 ,(1987)
R. James Firby, An investigation into reactive planning in complex domains national conference on artificial intelligence. pp. 202- 206 ,(1987)
Jack Mostow, Neeraj Bhatnagar, Failsafe: a floor planner that uses EBG to learn from its failures international joint conference on artificial intelligence. pp. 249- 255 ,(1987)
Steve A. Chien, Using and refining simplifications: explanation-based learning of plans in intractable domains international joint conference on artificial intelligence. pp. 590- 595 ,(1989)