Zobrazeno 1 - 10
of 5 365
pro vyhledávání: '"Boussard, ."'
Autor:
Wang, Yuqing, Zhao, Yun, Keller, Sara Alessandra, de Hond, Anne, van Buchem, Marieke M., Pillai, Malvika, Hernandez-Boussard, Tina
The advancement of large language models (LLMs) has demonstrated strong capabilities across various applications, including mental health analysis. However, existing studies have focused on predictive performance, leaving the critical issue of fairne
Externí odkaz:
http://arxiv.org/abs/2406.12033
In this paper, we employ the mathematical framework on Transformers developed by \citet{sander2022sinkformers,geshkovski2023emergence,geshkovski2023mathematical} to explore how variations in attention parameters and initial token values impact the st
Externí odkaz:
http://arxiv.org/abs/2402.15415
In the high-stakes realm of healthcare, ensuring fairness in predictive models is crucial. Electronic Health Records (EHRs) have become integral to medical decision-making, yet existing methods for enhancing model fairness restrict themselves to unim
Externí odkaz:
http://arxiv.org/abs/2402.00955
R\'enyi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration
Pufferfish privacy is a flexible generalization of differential privacy that allows to model arbitrary secrets and adversary's prior knowledge about the data. Unfortunately, designing general and tractable Pufferfish mechanisms that do not compromise
Externí odkaz:
http://arxiv.org/abs/2312.13985
Artificial intelligence and data access are already mainstream. One of the main challenges when designing an artificial intelligence or disclosing content from a database is preserving the privacy of individuals who participate in the process. Differ
Externí odkaz:
http://arxiv.org/abs/2312.07139
Autor:
Boussard, Julien, Nagda, Chandni, Kaltenborn, Julia, Lange, Charlotte Emilie Elektra, Brouillard, Philippe, Gurwicz, Yaniv, Nowack, Peer, Rolnick, David
Climate models, such as Earth system models (ESMs), are crucial for simulating future climate change based on projected Shared Socioeconomic Pathways (SSP) greenhouse gas emissions scenarios. While ESMs are sophisticated and invaluable, machine learn
Externí odkaz:
http://arxiv.org/abs/2312.02858
Autor:
Sulaiman Somani, Sneha S. Jain, Ashish Sarraju, Alexander T. Sandhu, Tina Hernandez-Boussard, Fatima Rodriguez
Publikováno v:
Communications Medicine, Vol 4, Iss 1, Pp 1-5 (2024)
Abstract Background The prevalence of obesity has been increasing worldwide, with substantial implications for public health. Obesity is independently associated with cardiovascular morbidity and mortality and is estimated to cost the health system o
Externí odkaz:
https://doaj.org/article/adb7381178a446d5a48a6624f3591aaa
Publikováno v:
AMIA Informatics Summit 2023
Clinical notes are an essential component of a health record. This paper evaluates how natural language processing (NLP) can be used to identify the risk of acute care use (ACU) in oncology patients, once chemotherapy starts. Risk prediction using st
Externí odkaz:
http://arxiv.org/abs/2209.13860
Autor:
Carcreff, Julie, Nazabal, Virginie, Troles, Johann, Boussard-Plédel, Catherine, Masselin, Pascal, Starecki, Florent, Braud, Alain, Camy, Patrice, Coq, David Le
Publikováno v:
Photonics 2022, 9, 549
With the ultimate goal of developing rare-earth doped chalcogenide fiber fabrication for sensing, amplification, and laser applications, a core/clad germanium-gallium sulfide fiber doped with Pr$^{3+}$ has been fabricated. The compositions of the cor
Externí odkaz:
http://arxiv.org/abs/2208.11046