Zobrazeno 1 - 10
of 1 994
pro vyhledávání: '"Preux P"'
Publikováno v:
Diabetes, Metabolic Syndrome and Obesity, Vol Volume 12, Pp 2201-2208 (2019)
Amal Shahwan Jamee,1–3 Victor Aboyans,1,2,4 Julien Magne,1,2,4 Pierre Marie Preux,1,2 Philippe Lacroix1,2,51Tropical Neuroepidemiology, Inserm UMR 1094, Limoges, France; 2School of Medicine, Institute of Neuroepidemiology and Tropical Neurology, CN
Externí odkaz:
https://doaj.org/article/28cb77c16cb7406a9c2b3a82851d6ee8
Deep reinforcement learning agents are prone to goal misalignments. The black-box nature of their policies hinders the detection and correction of such misalignments, and the trust necessary for real-world deployment. So far, solutions learning inter
Externí odkaz:
http://arxiv.org/abs/2405.14956
Embracing the pursuit of intrinsically explainable reinforcement learning raises crucial questions: what distinguishes explainability from interpretability? Should explainable and interpretable agents be developed outside of domains where transparenc
Externí odkaz:
http://arxiv.org/abs/2404.10906
Conversational systems have made significant progress in generating natural language responses. However, their potential as conversational search systems is currently limited due to their passive role in the information-seeking process. One major lim
Externí odkaz:
http://arxiv.org/abs/2402.16608
Autor:
Vasconcellos, Eduardo Charles, Sampaio, Ronald M, Araújo, André P D, Clua, Esteban Walter Gonzales, Preux, Philippe, Guerra, Raphael, Gonçalves, Luiz M G, Martí, Luis, Lira, Hernan, Sanchez-Pi, Nayat
Publikováno v:
NeurIPS 2023 Workshop on Robot Learning Workshop: Pretraining, Fine-Tuning, and Generalization with Large Scale Models, Dec 2023, New Orelans, United States
This work focuses on the main challenges and problems in developing a virtual oceanic environment reproducing real experiments using Unmanned Surface Vehicles (USV) digital twins. We introduce the key features for building virtual worlds, considering
Externí odkaz:
http://arxiv.org/abs/2402.03337
A peculiarity of conversational search systems is that they involve mixed-initiatives such as system-generated query clarifying questions. Evaluating those systems at a large scale on the end task of IR is very challenging, requiring adequate dataset
Externí odkaz:
http://arxiv.org/abs/2311.06119
Interpretability of AI models allows for user safety checks to build trust in such AIs. In particular, Decision Trees (DTs) provide a global look at the learned model and transparently reveal which features of the input are critical for making a deci
Externí odkaz:
http://arxiv.org/abs/2309.13365
Finding an optimal decision tree for a supervised learning task is a challenging combinatorial problem to solve at scale. It was recently proposed to frame the problem as a Markov Decision Problem (MDP) and use deep reinforcement learning to tackle s
Externí odkaz:
http://arxiv.org/abs/2309.12701
Autor:
Saux, Patrick, Bauvin, Pierre, Raverdy, Violeta, Teigny, Julien, Verkindt, Hélène, Soumphonphakdy, Tomy, Debert, Maxence, Jacobs, Anne, Jacobs, Daan, Monpellier, Valerie, Lee, Phong Ching, Lim, Chin Hong, Andersson-Assarsson, Johanna C, Carlsson, Lena, Svensson, Per-Arne, Galtier, Florence, Dezfoulian, Guelareh, Moldovanu, Mihaela, Andrieux, Severine, Couster, Julien, Lepage, Marie, Lembo, Erminia, Verrastro, Ornella, Robert, Maud, Salminen, Paulina, Mingrone, Geltrude, Peterli, Ralph, Cohen, Ricardo V, Zerrweck, Carlos, Nocca, David, Roux, Carel W Le, Caiazzo, Robert, Preux, Philippe, Pattou, François
Background Weight loss trajectories after bariatric surgery vary widely between individuals, and predicting weight loss before the operation remains challenging. We aimed to develop a model using machine learning to provide individual preoperative pr
Externí odkaz:
http://arxiv.org/abs/2308.16585
Autor:
Mathieu, Timothée, Della Vecchia, Riccardo, Shilova, Alena, Centa, Matheus Medeiros, Kohler, Hector, Maillard, Odalric-Ambrym, Preux, Philippe
Recently, the scientific community has questioned the statistical reproducibility of many empirical results, especially in the field of machine learning. To solve this reproducibility crisis, we propose a theoretically sound methodology to compare th
Externí odkaz:
http://arxiv.org/abs/2306.10882