caa a22 4500 465814832 CHVBK 20180323112124.0 cr unu---uuuuu 170327e19900301xx s 000 0 eng 10.1007/BF00115894 doi (NATIONALLICENCE)springer-10.1007/BF00115894 Shavlik Iude Computer Sciences Department, University of Wisconsin, 1210 West Dayton Street, 53706, Madison, WI aut Acquiring recursive and iterative concepts with explanation-based learning [Elektronische Daten] [Iude Shavlik] Inexplanation-based learning, a specific problem's solution is generalized into a form that can be later used to solve conceptually similar problems. Most research in explanation-based learning involves relaxing constraints on the variables in the explanation of a specific example, rather than generalizing thegraphical structure of the explanation itself. However, this precludes the acquisition of concepts where an iterative or recursive process is implicitly represented in the explanation by a fixed number of applications. This paper presents an algorithm that generalizes explanation structures and reports empirical results that demonstrate the value of acquiring recursive and iterative concepts. Thebagger2 algorithm learns recursive and iterative concepts, integrates results from multiple examples, and extracts useful subeoncepts during generalization. On problems where learning a recursive rule is not appropriate, the system produces the same results as standard explanation-based methods. Applying the learned recursive rules only requires a minor extension to aprolog-like problem solver, namely, the ability to explicitly call a specific rule. Empirical studies demonstrate that generalizing the structure of explanations helps avoid the recently reported negative effects of learning. Kluwer Academic Publishers, 1990 Explanation-based generalization nationallicence generalizing explanation structures nationallicence generalizing to N nationallicence generalizing number nationallicence utilitly of learning nationallicence operationality versus generality nationallicence Machine Learning Kluwer Academic Publishers 5/1(1990-03-01), 39-70 0885-6125 5:1<39 1990 5 10994 https://doi.org/10.1007/BF00115894 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00115894 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Shavlik Iude Computer Sciences Department, University of Wisconsin, 1210 West Dayton Street, 53706, Madison, WI aut NATIONALLICENCE 773 0- Machine Learning Kluwer Academic Publishers 5/1(1990-03-01), 39-70 0885-6125 5:1<39 1990 5 10994 Metadata rights reserved Springer special CC-BY-NC licence nationallicence SWISSBIB 465814735 BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer