Approximating the Semantics of Logic Programs by RecurrentNeural
نویسنده
چکیده
; Abstract. In 8] we have shown how to construct a 3{layer recurrent neural network that computes the iteration of the meaning function T P of a given propositional logic program, what corresponds to the computation of the semantics of the program. In this article we deene a notion of approximation for interpretations and prove that there exists a 3{layer feed forward neural network that approximates the calculation of T P for a given ((rst order) recurrent logic program with an injective level mapping arbitrarily well. Extending the feed forward network by recurrent connections one obtains an recurrent neural network whose iteration approximates the xed point of T P. This result is proved by taking advantage of the fact that for recurrent logic programs T P is a contraction mapping on the complete metric space of the interpretations for the program. Mapping this metric space to the metric space IR a real valued function f P can be found which corresponds to T P , is continuous as well a contraction, and | for this reason | can be approximated by an appropriately chosen class of feed forward neural networks.
منابع مشابه
Semantics of Logic Programs with Aggregates
Aggregates are functions that take sets as arguments. Examples are the function that maps a set to the number of its elements or the function which maps a set to its minimal element. Aggregates are frequently used in relational databases and have many applications in combinatorial search problems and knowledge representation. Aggregates are of particular importance for several extensions of log...
متن کاملReconciling Well-Founded Semantics of DL-Programs and Aggregate Programs
Logic programs with aggregates and description logic programs (dl-programs) are two recent extensions to logic programming. In this paper, we study the relationships between these two classes of logic programs, under the well-founded semantics. The main result is that, under a satisfaction-preserving mapping from dl-atoms to aggregates, the well-founded semantics of dl-programs by Eiter et al.,...
متن کاملAproximating the Well-Founded Semantics for Normal Logic Programs using Abstract Interpretation
The well-founded semantics for normal logic programs is deened in a constructive way through the use of a xpoint operator and in general is not computable. We propose an approach for approximating through abstract interpretation the concrete behavior of normal logic programs described by the well-founded semantics. We provide also an abstract well-founded semantics scheme, based on an abstract ...
متن کاملUltimate Well-Founded and Stable Semantics for Logic Programs with Aggregates
In [3] we investigate the problem of defining a well-founded and stable semantics for programs with aggregates. Our work is based on Approximation Theory [1] which is a general algebraic framework for approximating non-monotone operators on a complete lattice L by approximating operators on the bi-lattice L. The theory identifies basic properties of the approximating operators and gives a metho...
متن کاملUnfounded Sets and Well-Founded Semantics of Answer Set Programs with Aggregates
Logic programs with aggregates (LP) are one of the major linguistic extensions to Logic Programming (LP). In this work, we propose a generalization of the notions of unfounded set and well-founded semantics for programs with monotone and antimonotone aggregates (LPm,a programs). In particular, we present a new notion of unfounded set for LPm,a programs, which is a sound generalization of the or...
متن کامل