A. Kakas and F. Riguzzi. Abductive concept learning. New Generation Computing, 1999.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....were rated good and relevant. For more details, we refer to the published papers. 6.7. DISCUSSION 151 6.6.3 Abductive Concept Learning While all above mentioned applications use ICL as a stand alone system, ICL can also be applied as part of a larger system. This has been done in the work of [Kakas and Riguzzi, 2000] and [Riguzzi, 1998] where ICL has been incorporated in the abductive concept learner ACL. Abductive Concept Learning (ACL) is a learning framework which extends the one of ILP and allows to learn from incomplete knowledge 2. This means that both the background and the learned theory can be an ....

A.C. Kakas and F. Riguzzi. Abductive concept learning. /Veto Generation Computing, 18(3), 2000.

....a solution. It enables abductive reductions to be pruned early by setting new suitable CLP constraints on the abductive solution that is constructed. The framework of ACLP has also been integrated with Inductive Logic Programming to allow a form of machine learning under incomplete information [62]. The ACLP system [60, 49] developed at the University of Cyprus, implements the ACLP framework of ALP for a restricted sub language of the full ACLP framework. Currently, the system is implemented as a metainterpreter on top of the CLP language of ECLiPSe using the CLP constraint solver of ....

....missing or inconsistent data that explain the example or training data using the background theory. This process gives alternative possibilities for assimilating and generalizing this data. In another integration of ALP and ILP, ILP is extended to learn ALP theories from incomplete background data [62]. This allows the framework to perform Multiple Predicate Learning in a natural way. As we have seen in previous sections several approaches to ALP have recognized the importance of linking this together with Constraint Logic Programming. They have shown that the integration of constraint solving ....

A.C. Kakas and F. Riguzzi. Abductive Concept Learning. New Generation Computing, Vol. 18, pp. 243-294, 2000.

....to be pruned early by setting new suitable CLP constraints on the abductive solution that is constructed. ACLP has been applied to several di erent types of problems including scheduling, planning, time tabling and information integration. The 11 framework of ACLP has also been integrated [54] with Inductive Logic Programming to allow a form of machine learning under incomplete information. Extended and Preference Abduction In order to broaden the applicability of ALP in AI and databases, Inoue and Sakama propose two kinds of extensions of ALP: Extended abduction [37] and Preference ....

A.C. Kakas and F. Riguzzi. Abductive Concept Learning. New Generation Computing, Vol. 18, pp. 243-294, 2000.

....to learn is itself inherently abductive or non monotonic (e.g. containing nested hierarchies of exceptions) in which case the hypothesis space for learning is a space of abductive theories. Frameworks for learning abductive theories include the early system of LAB [14] and the more recent work of [7, 8, 3, 9] where both explanatory and confirmatory induction are used to generate abductive theories that include integrity constraints. Also in [6] the problem of learning abductive logic programs for capturing non monotonic theories is studied. 5 Concluding Remarks The cycle of cooperation between ....

Antonis C. Kakas and Fabrizio Riguzzi. Abductive concept learning. New Generation Computing, 1999.

No context found.

A. Kakas and F. Riguzzi. Abductive concept learning. New Generation Computing, 1999.

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