no code implementations • 5 Aug 2023 • Renato Lui Geh, Jonas Gonçalves, Igor Cataneo Silveira, Denis Deratani Mauá, Fabio Gagliardi Cozman
We also discuss how gradient-based learning can be performed with neural predicates and probabilistic choices under selected semantics.
1 code implementation • 8 Feb 2022 • Marcos Menon José, Marcelo Archanjo José, Denis Deratani Mauá, Fábio Gagliardi Cozman
Deep learning transformers have drastically improved systems that automatically answer questions in natural language.
no code implementations • 19 Aug 2020 • Lilith Mattei, Alessandro Antonucci, Denis Deratani Mauá, Alessandro Facchini, Julissa Villanueva Llerena
In this work, we develop the credal sentential decision diagrams, a generalisation of their probabilistic counterpart that allows for replacing the local probabilities with (so-called credal) sets of mass functions.
no code implementations • 31 Jan 2017 • Fabio Gagliardi Cozman, Denis Deratani Mauá
We examine the meaning and the complexity of probabilistic logic programs that consist of a set of rules and a set of independent probabilistic facts (that is, programs based on Sato's distribution semantics).
no code implementations • 4 Dec 2016 • Fabio Gagliardi Cozman, Denis Deratani Mauá
We examine the complexity of inference in Bayesian networks specified by logical languages.