A Fully Connectionist Model Generator for Covered First-Order Logic Programs

TitleA Fully Connectionist Model Generator for Covered First-Order Logic Programs
Publication TypeConference Paper
Year of Publication2007
AuthorsSebastian Bader, Steffen Holldobler, Andreas Witzel, Pascal Hitzler
Conference NameTwentieth International Joint Conference on Artificial Intelligence, IJCAI-07
Pagination666-671
Conference LocationHyderabad, India
Abstract

We present a fully connectionist system for the learning of first-order logic programs and the generation of corresponding models: Given a program and a set of training examples, we embed the associated semantic operator into a feed-forward network and train the network using the examples. This results in the learning of first-order knowledge while damaged or noisy data is handled gracefully.

Full Text

Sebastian Bader, Pascal Hitzler, Steffen Holldobler, Andreas Witzel, 'A Fully Connectionist Model Generator for Covered First-Order Logic Programs,' Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07, Hyderabad, India, January 2007, Menlo Park CA, 2007, pp. 666-671.

hasURL: http://portal.acm.org/citation.cfm?id=1625275.1625382