Thomas Ellman. Approximate theory formation: An explanation-based approach. In Proceedings of the Seventh National Conference on Artificial Intelligence, pp. 570-574, 1988. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Acquiring (Ir)relevance Knowledge for Problem Solving - Levy, Motoda, Iwasaki (Correct)
....[ Levy and Sagiv, 1992 ] In addition, as emphasized in this paper, we extend the definition of irrelevance to other subjects, such as predicate and object distinctions. Recently, the issue of automatically generating abstractions and evaluating their utility has received much attention [ Ellman, 1988; Bennett, 1986; Giunchiglia and Walsh, 1992; Knoblock, 1990; Yoshida and Motoda, 1990; Yoshida and Motoda, 1992; Williams, 1990 ] and in the context of modeling of physical devices [ Falkenhainer and Forbus, 1991; Nayak, 1992 ] Space limitations enable us to discuss only one of these works in ....
Thomas Ellman. Approximate theory formation: An explanation-based approach. In Proceedings of the Seventh National Conference on Artificial Intelligence, pp. 570-574, 1988.
An Adaptive Problem-Solving Solution to Large-Scale Scheduling.. - Gratch, al. (1994) (Correct)
....of different heuristics from a randomly set of training examples, and explore an explicit space of heuristics with greedy search techniques. Examples of such systems are the COMPOSER system of Gratch and DeJong [Gratch92] the PALO system of Greiner and Jurisica [Greiner92] Ellman s POLLYANNA [Ellman88 ], and the statistical component of Minton s MULTI TAC [Minton93] Similar approaches have also been investigated in the operations research community [Yakowitz90] These techniques are easy to use, apply to a variety of domains and utility functions, and can provide strong statistical guarantees ....
T. Ellman, "Approximate Theory Formation: An Explanation--Based Approach, " Proceedings of the National Conference on Artificial Intelligence, St. Paul, MN, August 1988, pp. 570--574.
Feature Discovery for Inductive Concept Learning - Fawcett (1993) (2 citations) (Correct)
....abstraction system. All other such systems require a human to control the application of the transformation. This research, using feedback from an inductive concept learner to control the transformations automatically, will constitute an advance in this field [Mostow Fawcett, 1987; Ellman, 1988; Mostow Prieditis, 1989] An implementation of this theory has been undertaken, and the preliminary results are very encouraging. Feature generation can be automated in intractable domains. The successful completion of this work will make a significant advance in the state of the art of A ....
Ellman, T. (1988). Approximate theory formation: An explanation-based approach. Proceedings of the Seventh National Conference on Artificial Intelligence (pp. 95-99). Saint Paul, MN: Morgan Kaufmann.
Learning Search-Control Heuristics for Logic Programs.. - Zelle (1993) (2 citations) (Correct)
....advantage of recent progress in relational learning, namely, Foil. The first use of approximations in learning control rules was probably MetaLEX (Keller, 1987) which used a simple technique for removing conditions. Most other recent investigations have not focussed on learning control rules (Ellman, 1988; Tadepalli, 1989; Chien, 1989) or have not employed induction (Chase et al. 1989) Yoo and Fisher (Yoo and Fisher, 1991) combine induction and explanation to improve performance in a problem solving framework. They enhance the utility of EBL macros by clustering them in a Cobweb style ....
Ellman, T. (1988). Approximate theory formation: An explanation-based approach. In Proceedings of the Seventh National Conference on Artificial Intelligence, pages 564--569. St. Paul, MN.
Knowledge Compilation: Bridging the Gap between Specification.. - Dietterich (1991) (1 citation) (Correct)
....the correctness of the target system. In addition, it is sometimes necessary to sacrifice correctness to obtain efficiency. For example, it is often convenient to specify design tasks in terms of minimizing cost while maximizing performance parameters. In practice, however, satisficing methods[8] are applied to find a design of sufficiently low cost and sufficiently high performance. To address the problem of unexecutable specifications, one approach is to analyze the domain to find observable proxy variables that can approximate unobservable quantities. Another approach is to adopt ....
Ellman, T. Approximate theory formation: an explanation-based approach. In Proceedings of the Seventh National Conference on Artificial Intelligence, pages 570--574, St. Paul, MN, 1988. Morgan Kaufmann.
Learning Approximate Control Rules Of High Utility - Cohen (1990) (27 citations) (Correct)
....are faster is that the best control rules learned by AxA EBL outperform the best control rules learned by A EBL, requiring 1.5 seconds versus 12.9 seconds to solve the 50 problems in the test set. knowledge against a benchmark. This would be prohibitively expensive in a real world domain. Ellman [ Ellman, 1988 ] Tadepalli [ Tadepalli, 1989 ] and Chien [ Chien, 1989 ] have also investigated explanation based learning of approximate theories. The search techniques described by these authors improve on Keller s by taking advantage of a partial order on approximate theories; however, they have not been ....
Tom Ellman. Approximate theory formation: An explanation-based approach. In Proceedings of the Seventh National Conference on Artificial Intelligence, Saint Paul, Minnesota, 1988. Morgan Kaufmann.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC