An ASP Approach for Reasoning on Neural Networks under a Finitely Many-Valued Semantics for Weighted Conditional Knowledge Bases

Abstract Weighted knowledge bases for description logics with typicality have been recently considered under a “concept-wise” multipreference semantics (in both the two-valued and fuzzy case), as basis of logical multilayer perceptrons (MLPs). In this paper we consider weighted conditional $\mathcal{ALC}$ in finitely many-valued case, through three different semantic constructions. For boolean fragment $\mathcal{LC}$ exploit answer set programming asprin reasoning concept-wise entailment $\varphi$ -coherent , suitable to characterize stationary states MLPs. As proof concept, experiment proposed approach checking properties trained