An ASP approach for reasoning on neural networks under a finitely many-valued semantics for weighted conditional knowledge bases

2022/02/02 by Laura Giordano, Giordano, Laura, Daniele Theseider Dupré +1 · 1 citation
Computer Science · #68T27 #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Fuzzy Logic and Control Systems #I.2.4 #Rough Sets and Fuzzy Logic #Semantic Web and Ontologies

paper · pdf · doi:10.48550/arxiv.2202.01123

openalex publication_date 2022/02/02 · openalex created_date 2022/04/03 · openalex updated_date 2026/07/28

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 the basis of a logical semantics of MultiLayer Perceptrons (MLPs). In this paper we consider weighted conditional ALC knowledge bases with typicality in the finitely many-valued case, through three different semantic constructions. For the boolean fragment LC of ALC we exploit ASP and "asprin" for reasoning with the concept-wise multipreference entailment under a phi-coherent semantics, suitable to characterize the stationary states of MLPs. As a proof of concept, we experiment the proposed approach for checking properties of trained MLPs. The paper is under consideration for acceptance in TPLP.

Cited by

• Improving ASP-based ORS Schedules through Machine Learning Predictions

Related

• A preferential interpretation of MultiLayer Perceptrons in a conditional logic with typicality
• From Weighted Conditionals of Multilayer Perceptrons to Gradual\n Argumentation and Back
• Weighted defeasible knowledge bases and a multipreference semantics for a deep neural network model
• On the KLM properties of a fuzzy DL with Typicality
• From Common Sense Reasoning to Neural Network Models through Multiple Preferences: an overview