Italiano (Italian) English (Inglese)
Sunday, 23 June 2024

Technical Reports

Technical Report Details
Authors:Laura Giordano
Daniele Theseider Dupré
Scientific Area:Artificial Intelligence
Logic-Based Reasoning
Neural Networks
Title:Weighted defeasible knowledge bases and a multipreference semantics for a deep neural network model
Published on:TR-INF-2020-12-05-UNIPMN
Publisher:DiSIT, Computer Science Institute, UPO
Abstract:In this paper we investigate the relationships between a multipreferential semantics for defeasible reasoning in knowledge representation and a deep neural network model. Weighted knowledge bases for description logics are considered under a ``concept-wise" multipreference semantics. The semantics is further extended to fuzzy interpretations and exploited to provide a preferential interpretation of Multilayer Perceptrons.