Centre de Recherche en Informatique de LensRecherches en intelligence artificielle et ses applications.
|
Le laboratoire:Directeur: Pierre Marquis Le CRIL est localisé sur deux sites à Lens : la faculté des sciences Jean Perrin et l’IUT. Il regroupe près de 70 membres : chercheurs, enseignants-chercheurs, doctorants et personnels administratifs et techniques. Le CRIL participe à la Confédération Européenne de Laboratoires en Intelligence Artificielle CLAIRE et à l'alliance régionale humAIn. Il bénéficie du soutien du Ministère de l’Enseignement Supérieur et de la Recherche, du CNRS, de l’Université d’Artois et de la région Hauts de France.
Texte intégral453
Notices1 240
Actualités
In this talk, we will discuss the problem of automatically constructing computer programs from input-output examples, especially when the target language is domain-specific and defined using a context-free grammar. I will introduce a theoretical framework called distribution-based search, discuss its challenges, and present several search strategies based on learning the weights of a probabilistic context-free grammar (PCFG) and then using this PCFG to enumerate the most promising candidate programs efficiently. The presentation will be based on the following paper published at AAAI'2022: https://arxiv.
Probabilistic reasoning is a key aspect of artificial intelligence. In this talk we will look at probabilistic reasoning through the lens of ProbLog, a probabilistic logic programming language. This language extends the logical facts and rules of Prolog with probabilistic facts. Probabilistic reasoning in this language is achieved through knowledge compilation techniques. We will delve deeper into the details of this reasoning pipeline and highlight some of ProbLog's extensions. In particular we consider DeepProbLog, which heavily benefits from inference through d-DNNF compilation.
The CRIL cluster has been providing the laboratory's researchers with computing resources since it was set up in 2009. Since then, the evolution of these resources has been continuous, leading to a heterogeneous architecture in which traditional computing nodes, nodes dedicated to distributed computing, GPU nodes and various servers to drive this computing power cohabit, all driven by the Slurm resource manager. The aim of this talk is to present the calculation tools available, and how to use them (correctly) via Slurm.
|