Italiano (Italian) English (Inglese)
venerdì, 22 gennaio 2021


Dettagli Pubblicazione
Autori:Laura Giordano
Daniele Theseider Dupré
Area Scientifica:Artificial Intelligence
Logic-Based Reasoning
Neural Networks
Titolo:Weighted defeasible knowledge bases and a multipreference semantics for a deep neural network model
Apparso su:TR-INF-2020-12-05-UNIPMN
Editore:DiSIT, Computer Science Institute, UPO
Tipo Pubblicazione:Technical Report
Sommario: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.