McDermott J. R1: A rule-based con gurer of computer systems. Arti- cial Intelligence, 19, 1982. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Rule Extraction from Trained ANN: A Survey - Darbari (2001) (Correct)
....B, C, D then A. if C, D, and not(E) then A. if B, D, and not(E) then A. if B, C, and not(E) then A. a) b) Figure 4: Rule Extraction using the SUBSet al..gorithm. Interestingly though the SUBSet al..gorithm extracts a large set of rules, it is much lesser than many hand crafted systems (e.g. [20]) Hence SUBSET delivers sets of rules that are potentially tractable. However these rules tend to hide signi cant structures in trained networks. For instance in Figure 4, part(a) the links to B, C and D all have the same weight, while the link to E has the negative of that weight. Looking at ....
McDermott J. R1: A rule-based con gurer of computer systems. Arti- cial Intelligence, 19, 1982.
Developing a Declarative Rule Language for Applications in.. - Soininen, Niemelä (1999) (23 citations) (Correct)
....is based on a translator from rules to normal programs and on an existing high performance implementation of the stable model semantics, the Smodels system. 1 Introduction Product con guration has been a fruitful topic of research in arti cial intelligence for the past two decades (see, e.g. [10, 15, 1, 8]) In the last ve years product con guration has also become a commercially successful application of arti cial intelligence techniques. Knowledge based systems (KBS) employing techniques such as constraint satisfaction (CSP) 19] have been applied to product con guration. However, the product ....
J. McDermott. R1: a rule-based congurer of computer systems. Articial Intelligence, 19(1):39-88, 1982.
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