Khardon, R.: Learning Horn Expressions with LogAn-H, Proc. of the Seventeenth International Conference on Machine Learning, 2000. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
A New Algorithm for Learning Range Restricted Horn.. - Arias, Khardon (2000) (1 citation) (Correct)
....is allowed to ask are membership and equivalence queries. While our work is purely theoretical, there are systems that are able to learn using equivalence and membership queries (MIS [Sha83] CLINT [RB92] for example) These ideas have also been used in systems that learn from examples only [Kha00]. A learning algorithm for the class of range restricted Horn expressions is presented. The main property of this class is that all the terms in the conclusion This work was partly supported by EPSRC Grant GR M21409. 1 The unknown expression to be identified is commonly referred to as target ....
Roni Khardon. Learning horn expressions with LOGAN-H. To appear in ICML, 2000.
Learning Closed Horn Expressions - Arias, Khardon (2002) Self-citation (Khardon) (Correct)
....and equivalence queries. While our work is purely theoretical, there are systems that are able to learn using equivalence and membership queries (MIS [23] CLINT [18] for example) Some of the techniques developed in this framework have been adapted for systems that learn from examples only [21, 12]. We present an algorithm to learn certain subsets of Horn expressions. The algorithm is related to the ones in [10, 11] which learn Range Restricted Horn expressions. The algorithms in [10, 11] and here use two main procedures. The rst, given a counterexample clause, minimises the clause while ....
Roni Khardon. Learning Horn expressions with LogAn-H. In Proceedings of the International Conference on Machine Learning, pages 471-478, 2000.
Recent Progress in Learning Horn Expressions with Queries - Khardon Self-citation (Khardon) (Correct)
....(e.g. 20, 17, 9, 5] Since only limited classes of expressions are learnable from examples [6] heuristics are used to obtain good results in practice. One recent strand of theoretical work has shown that larger classes of expressions are learnable if the learner is allowed to ask questions [12, 21, 4, 22, 16, 14, 13, 3, 15]. These works use standard oracles from learning theory [1] as well as new types of questions appropriate for the rst order setting. Two main challenges remain in this area. One is to further clarify which classes are learnable and with what complexity. The other is to establish applications of ....
....membership queries and other oracles are used to identify successful re nements and safe size reducing operations. Applications There are several ways to apply such algorithms in practical situations. The natural approach is to develop interactive systems relying on users to answer questions [24, 8, 15]. These can be useful in tools supporting the development of logic programs. A challenging possibility arises in domains where one can perform experiments e.g. lab tests in chemical domains to answer membership queries. If this is feasible then one might be able to automate the entire learning ....
[Article contains additional citation context not shown here]
R. Khardon. Learning Horn expressions with LogAn-H. In International Conference on Machine Learning, 2000.
Learning Recursive Theories in the Normal ILP Setting - Malerba (2003) (1 citation) (Correct)
No context found.
Khardon, R.: Learning Horn Expressions with LogAn-H, Proc. of the Seventeenth International Conference on Machine Learning, 2000.
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