2022 | OriginalPaper | Buchkapitel
DeduDeep: An Extensible Framework for Combining Deep Learning and ASP-Based Models
verfasst von : Pierangela Bruno, Francesco Calimeri, Cinzia Marte
Erschienen in: Logic Programming and Nonmonotonic Reasoning
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
DeduDeep
, the prototypical implementation of a framework explicitly conceived with the aim of tackling such limitations by making use of deductive declarative formalisms. In particular, the framework aims at enabling the declarative encoding of explicit knowledge, and, by relying on the use of Answer Set Programming (ASP), taking advantage of it for driving decisions taken by neural networks and refining the output. The framework has been tested using different artificial neural networks tailored to semantic segmentation tasks over Laryngeal Endoscopic Images and Freiburg Sitting People Images.