A connectionist inductive learning system for modal logic programming

Neural-Symbolic integration has become a very active research area in the last decade. In this paper, we present a new massively parallel model for modal logic. We do so by extending the language of Modal Prolog [32, 37] to allow modal operators in the head of the clauses. We then use an ensemble of C-IL2P neural networks [14, 15] to encode the extended modal theory (and its relations), and show that the ensemble computes a fixpoint semantics of the extended theory. An immediate result of our approach is the ability to perform learning from examples efficiently using each network of the ensemble. Therefore, one can adapt the extended C-IL2P system by training possible world representations. Keywords: Neural-Symbolic Integration, Artificial Neural Networks, Modal Logic, Change of Representation, Learning from Structured Data