ECAI-2002 Conference Paper

[full paper]

Updating a Hybrid Rule Base with Changes to its Symbolic Source Knowledge

Jim Prentzas, Ioannis Hatzilygeroudis

Neurules are a kind of hybrid rules that combine a symbolic (production rules) and a connectionist (adaline unit) representation. One way that neurules (target knowledge) can be produced is by converting symbolic rules (source knowledge). However, source knowledge may change, so that updating corresponding target knowledge is necessary. Changes concern insertion of new and removal of old symbolic rules. In this paper, methods for updating target knowledge to follow changes made in corresponding source knowledge are presented. The methods are efficient in the sense that they do not require retraining of the whole affected part of the target knowledge, but of as small portion of it as possible.

Keywords: Knowledge Maintenance, Knowledge-Based Systems, Knowledge Representation

Citation: Jim Prentzas, Ioannis Hatzilygeroudis: Updating a Hybrid Rule Base with Changes to its Symbolic Source Knowledge. In F. van Harmelen (ed.): ECAI2002, Proceedings of the 15th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2002, pp.250-254.