Zobrazeno 1 - 10
of 1 169
pro vyhledávání: '"P. Weerts"'
Autor:
Denton, Will, Chiavetta, Lilly, Bryant, Michael, Shah, Vedarsh, Zhu, Rico, Weerts, Ricky, Xue, Phillip, Chen, Vincent, Le, Hung, Lin, Maxwell, Camacho, Austin, Council, Drew, Horowitz, Ethan, Ong, Jackie, Chu, Morgan, Pool, Alex
The Duke Robotics Club is proud to present our robot for the 2023 RoboSub Competition: Oogway. Oogway marks one of the largest design overhauls in club history. Beyond a revamped formfactor, some of Oogway's notable features include all-new computer
Externí odkaz:
http://arxiv.org/abs/2410.10900
Publikováno v:
2024 ACM Conference on Fairness, Accountability, and Transparency (FAccT '24)
Emerging scholarship suggests that the EU legal concept of direct discrimination - where a person is given different treatment on grounds of a protected characteristic - may apply to various algorithmic decision-making contexts. This has important im
Externí odkaz:
http://arxiv.org/abs/2404.14050
Autor:
Weerts, Hilde, Xenidis, Raphaële, Tarissan, Fabien, Olsen, Henrik Palmer, Pechenizkiy, Mykola
Publikováno v:
2024 ACM Conference on Fairness, Accountability, and Transparency (FAccT '24)
Various metrics and interventions have been developed to identify and mitigate unfair outputs of machine learning systems. While individuals and organizations have an obligation to avoid discrimination, the use of fairness-aware machine learning inte
Externí odkaz:
http://arxiv.org/abs/2404.12143
Publikováno v:
Hydrology and Earth System Sciences, Vol 28, Pp 5107-5131 (2024)
Groundwater is under pressure from a changing climate and increasing anthropogenic demands. In this study, we project the effect of these two processes onto future groundwater status. Climate projections of Representative Concentration Pathway 4.5 (R
Externí odkaz:
https://doaj.org/article/0f8a05e460dc41a09c3d90ad9264664d
Autor:
Gulcehre, Caglar, Paine, Tom Le, Srinivasan, Srivatsan, Konyushkova, Ksenia, Weerts, Lotte, Sharma, Abhishek, Siddhant, Aditya, Ahern, Alex, Wang, Miaosen, Gu, Chenjie, Macherey, Wolfgang, Doucet, Arnaud, Firat, Orhan, de Freitas, Nando
Reinforcement learning from human feedback (RLHF) can improve the quality of large language model's (LLM) outputs by aligning them with human preferences. We propose a simple algorithm for aligning LLMs with human preferences inspired by growing batc
Externí odkaz:
http://arxiv.org/abs/2308.08998
Autor:
Weerts, Hilde, Xenidis, Raphaële, Tarissan, Fabien, Olsen, Henrik Palmer, Pechenizkiy, Mykola
Publikováno v:
2023 ACM Conference on Fairness, Accountability, and Transparency (FAccT '23)
Concerns regarding unfairness and discrimination in the context of artificial intelligence (AI) systems have recently received increased attention from both legal and computer science scholars. Yet, the degree of overlap between notions of algorithmi
Externí odkaz:
http://arxiv.org/abs/2305.13938
Autor:
Bram Droppers, Oldrich Rakovec, Leandro Avila, Shima Azimi, Nicolás Cortés-Torres, David De León Pérez, Ruben Imhoff, Félix Francés, Stefan Kollet, Riccardo Rigon, Albrecht Weerts, Luis Samaniego
Publikováno v:
Scientific Data, Vol 11, Iss 1, Pp 1-14 (2024)
Abstract Although Essential Climate Variables (ECVs) have been widely adopted as important metrics for guiding scientific and policy decisions, the Earth Observation (EO) and Land Surface and Hydrologic Model (LSM/HM) communities have yet to treat te
Externí odkaz:
https://doaj.org/article/9461d42242d142b98224ca1fe59e39eb
Publikováno v:
Translational Psychiatry, Vol 14, Iss 1, Pp 1-8 (2024)
Abstract The neurohormone oxytocin (OT) has been proposed as a treatment for alcohol and nicotine use disorders. The aim of the present study was to examine whether intravenous (IV) OT decreases alcohol oral self-administration and consumption in non
Externí odkaz:
https://doaj.org/article/71b1f066d62d4698842be1da449dbc7c
Fairlearn is an open source project to help practitioners assess and improve fairness of artificial intelligence (AI) systems. The associated Python library, also named fairlearn, supports evaluation of a model's output across affected populations an
Externí odkaz:
http://arxiv.org/abs/2303.16626
Autor:
Weerts, Hilde, Pfisterer, Florian, Feurer, Matthias, Eggensperger, Katharina, Bergman, Edward, Awad, Noor, Vanschoren, Joaquin, Pechenizkiy, Mykola, Bischl, Bernd, Hutter, Frank
Publikováno v:
Journal of Artificial Intelligence Research 79 (2024) 639-677
The field of automated machine learning (AutoML) introduces techniques that automate parts of the development of machine learning (ML) systems, accelerating the process and reducing barriers for novices. However, decisions derived from ML models can
Externí odkaz:
http://arxiv.org/abs/2303.08485