Zobrazeno 1 - 10
of 2 681
pro vyhledávání: '"A, Devic"'
Autor:
Kazemi, Mehran, Dikkala, Nishanth, Anand, Ankit, Devic, Petar, Dasgupta, Ishita, Liu, Fangyu, Fatemi, Bahare, Awasthi, Pranjal, Guo, Dee, Gollapudi, Sreenivas, Qureshi, Ahmed
With the continuous advancement of large language models (LLMs), it is essential to create new benchmarks to effectively evaluate their expanding capabilities and identify areas for improvement. This work focuses on multi-image reasoning, an emerging
Externí odkaz:
http://arxiv.org/abs/2406.09175
Calibration is a well-studied property of predictors which guarantees meaningful uncertainty estimates. Multicalibration is a related notion -- originating in algorithmic fairness -- which requires predictors to be simultaneously calibrated over a po
Externí odkaz:
http://arxiv.org/abs/2406.06487
We demonstrate a compactness result holding broadly across supervised learning with a general class of loss functions: Any hypothesis class $H$ is learnable with transductive sample complexity $m$ precisely when all of its finite projections are lear
Externí odkaz:
http://arxiv.org/abs/2402.10360
Rankings are ubiquitous across many applications, from search engines to hiring committees. In practice, many rankings are derived from the output of predictors. However, when predictors trained for classification tasks have intrinsic uncertainty, it
Externí odkaz:
http://arxiv.org/abs/2402.09326
The quintessential learning algorithm of empirical risk minimization (ERM) is known to fail in various settings for which uniform convergence does not characterize learning. It is therefore unsurprising that the practice of machine learning is rife w
Externí odkaz:
http://arxiv.org/abs/2309.13692
The prevalence and importance of algorithmic two-sided marketplaces has drawn attention to the issue of fairness in such settings. Algorithmic decisions are used in assigning students to schools, users to advertisers, and applicants to job interviews
Externí odkaz:
http://arxiv.org/abs/2302.03810
Autor:
Jason Oke, Fergus Gleeson, Sarah Wilson, Matthew L Costa, Daniel Jones, Alpesh Mistry, Susan Shelmerdine, James Teh, Alex Novak, Nick Woznitza, David Metcalfe, Jian Shen Kiam, Sarim Ather, Nattakarn Limphaibool, Abdala Trinidad Espinosa Morgado, Max Hollowday, James Vaz, Jeanne Ventre, Lois Greenhalgh, Nick Welch, Natasa Devic
Publikováno v:
BMJ Open, Vol 14, Iss 9 (2024)
Introduction Missed fractures are the most frequent diagnostic error attributed to clinicians in UK emergency departments and a significant cause of patient morbidity. Recently, advances in computer vision have led to artificial intelligence (AI)-enh
Externí odkaz:
https://doaj.org/article/8e8c1a7c1fed4723b3b0d6ae6d47830a
Autor:
Viorica Chelban, Henriette Aksnes, Reza Maroofian, Lauren C. LaMonica, Luis Seabra, Anette Siggervåg, Perrine Devic, Hanan E. Shamseldin, Jana Vandrovcova, David Murphy, Anne-Claire Richard, Olivier Quenez, Antoine Bonnevalle, M. Natalia Zanetti, Rauan Kaiyrzhanov, Vincenzo Salpietro, Stephanie Efthymiou, Lucia V. Schottlaender, Heba Morsy, Annarita Scardamaglia, Ambreen Tariq, Alistair T. Pagnamenta, Ajia Pennavaria, Liv S. Krogstad, Åse K. Bekkelund, Alessia Caiella, Nina Glomnes, Kirsten M. Brønstad, Sandrine Tury, Andrés Moreno De Luca, Anne Boland-Auge, Robert Olaso, Jean-François Deleuze, Mathieu Anheim, Benjamin Cretin, Barbara Vona, Fahad Alajlan, Firdous Abdulwahab, Jean-Luc Battini, Rojan İpek, Peter Bauer, Giovanni Zifarelli, Serdal Gungor, Semra Hiz Kurul, Hanns Lochmuller, Sahar I. Da’as, Khalid A. Fakhro, Alicia Gómez-Pascual, Juan A. Botía, Nicholas W. Wood, Rita Horvath, Andreas M. Ernst, James E. Rothman, Meriel McEntagart, Yanick J. Crow, Fowzan S. Alkuraya, Gaël Nicolas, SYNaPS Study Group, Thomas Arnesen, Henry Houlden
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-20 (2024)
Abstract Primary familial brain calcification (PFBC) is characterized by calcium deposition in the brain, causing progressive movement disorders, psychiatric symptoms, and cognitive decline. PFBC is a heterogeneous disorder currently linked to varian
Externí odkaz:
https://doaj.org/article/1b66ac89bf354c83adcf4b0c6dc91661
Autor:
Pecić, Stevan, Vićić, Miloš, Kurij, Ljubomir, Belča, Ivan, Stojadinović, Strahinja, Dević, Slobodan
Publikováno v:
In Radiation Physics and Chemistry October 2024 223
The emergence of diverse network applications demands more flexible and responsive resource allocation for networks. Network slicing is a key enabling technology that provides each network service with a tailored set of network resources to satisfy s
Externí odkaz:
http://arxiv.org/abs/2201.07363