Índice
Literatura académica sobre el tema "Équité du ML"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte las listas temáticas de artículos, libros, tesis, actas de conferencias y otras fuentes académicas sobre el tema "Équité du ML".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Artículos de revistas sobre el tema "Équité du ML"
Pégny, Maël. "Revue de l'équité algorithmique". Lato Sensu: Revue de la Société de philosophie des sciences 10, n.º 1 (15 de diciembre de 2023): 93–105. http://dx.doi.org/10.20416/lsrsps.v10i1.7.
Texto completoDailloux, M., C. Henry y D. Terver. "Observation et étude expérimentale de mycobactéries atypiques en aquariums d'eau douce et d'eau de mer". Revue des sciences de l'eau 5, n.º 1 (12 de abril de 2005): 69–82. http://dx.doi.org/10.7202/705121ar.
Texto completoHassanain, M. M. "Emploi de l’éthyléneimine binaire pour la production d’un vaccin inactivé contre la peste équine. Résultats préliminaires". Revue d’élevage et de médecine vétérinaire des pays tropicaux 45, n.º 3-4 (1 de marzo de 1992): 231–34. http://dx.doi.org/10.19182/remvt.8908.
Texto completoROCHE, C., M. E. VALLE-MEDINA, G. PALLARES, P. SCHMITT, A. PALLARES, M. MEILLIEZ y J. LAURENT. "Décantabilité de boues activées conventionnelles et densifiées : caractérisation des régimes de sédimentation, perspectives opérationnelles". Techniques Sciences Méthodes 5 (22 de mayo de 2023): 35–46. http://dx.doi.org/10.36904/tsm/202305035.
Texto completoGILLOT, S., Y. FAYOLLE y C. ROCHE. "Densification des boues activées par hydrocyclones – impact de la granulation partielle sur les performances de traitement". Techniques Sciences Méthodes 12 (20 de enero de 2023): 133–47. http://dx.doi.org/10.36904/202212133.
Texto completoZongo, Moussa, Auguste Yamboué, Issa Nabaloum y Drissa Sanou. "Echographie du développement folliculaire et de l’ovulation chez la chèvre du Sahel en œstrus induit". Revue d’élevage et de médecine vétérinaire des pays tropicaux 71, n.º 4 (25 de enero de 2019): 157. http://dx.doi.org/10.19182/remvt.31671.
Texto completoOkouyi, Marcel W. M. y Christian Hanzen. "Effects of insemination timing and GnRH treatment on pregnancy rates of N’Dama cattle after estrus induction with progestin". Revue d’élevage et de médecine vétérinaire des pays tropicaux 69, n.º 2 (17 de noviembre de 2016): 73. http://dx.doi.org/10.19182/remvt.31182.
Texto completoDangbemey, P., M. Aboubakar, R. Atade, RS Imorou, M. Tamegnon, M. Ogoudjobi, B. Hounkpatin et al. "C53: Expérience des centres de dépistage du cancer du col de l'utérus au Bénin et perspectives de passage à l'échelle". African Journal of Oncology 2, n.º 1 Supplement (1 de marzo de 2022): S23—S24. http://dx.doi.org/10.54266/ajo.2.1s.c53.uori5299.
Texto completoAgbokponto, J. E., A. Idé, A. Warnant, L. Y. A. Yemoa, J. Quetin-Leclercq y Y. Larondelle. "Evaluation du profil d’acide gras et statuts d’oxydation de sept huiles alimentaires commercialisées au Bénin". Journal Africain de Technologie Pharmaceutique et Biopharmacie (JATPB) 2, n.º 3 (20 de diciembre de 2023). http://dx.doi.org/10.57220/jatpb.v2i3.104.
Texto completoTesis sobre el tema "Équité du ML"
Kaplan, Caelin. "Compromis inhérents à l'apprentissage automatique préservant la confidentialité". Electronic Thesis or Diss., Université Côte d'Azur, 2024. http://www.theses.fr/2024COAZ4045.
Texto completoAs machine learning (ML) models are increasingly integrated into a wide range of applications, ensuring the privacy of individuals' data is becoming more important than ever. However, privacy-preserving ML techniques often result in reduced task-specific utility and may negatively impact other essential factors like fairness, robustness, and interpretability. These challenges have limited the widespread adoption of privacy-preserving methods. This thesis aims to address these challenges through two primary goals: (1) to deepen the understanding of key trade-offs in three privacy-preserving ML techniques—differential privacy, empirical privacy defenses, and federated learning; (2) to propose novel methods and algorithms that improve utility and effectiveness while maintaining privacy protections. The first study in this thesis investigates how differential privacy impacts fairness across groups defined by sensitive attributes. While previous assumptions suggested that differential privacy could exacerbate unfairness in ML models, our experiments demonstrate that selecting an optimal model architecture and tuning hyperparameters for DP-SGD (Differentially Private Stochastic Gradient Descent) can mitigate fairness disparities. Using standard ML fairness datasets, we show that group disparities in metrics like demographic parity, equalized odds, and predictive parity are often reduced or remain negligible when compared to non-private baselines, challenging the prevailing notion that differential privacy worsens fairness for underrepresented groups. The second study focuses on empirical privacy defenses, which aim to protect training data privacy while minimizing utility loss. Most existing defenses assume access to reference data---an additional dataset from the same or a similar distribution as the training data. However, previous works have largely neglected to evaluate the privacy risks associated with reference data. To address this, we conducted the first comprehensive analysis of reference data privacy in empirical defenses. We proposed a baseline defense method, Weighted Empirical Risk Minimization (WERM), which allows for a clearer understanding of the trade-offs between model utility, training data privacy, and reference data privacy. In addition to offering theoretical guarantees on model utility and the relative privacy of training and reference data, WERM consistently outperforms state-of-the-art empirical privacy defenses in nearly all relative privacy regimes.The third study addresses the convergence-related trade-offs in Collaborative Inference Systems (CISs), which are increasingly used in the Internet of Things (IoT) to enable smaller nodes in a network to offload part of their inference tasks to more powerful nodes. While Federated Learning (FL) is often used to jointly train models within CISs, traditional methods have overlooked the operational dynamics of these systems, such as heterogeneity in serving rates across nodes. We propose a novel FL approach explicitly designed for CISs, which accounts for varying serving rates and uneven data availability. Our framework provides theoretical guarantees and consistently outperforms state-of-the-art algorithms, particularly in scenarios where end devices handle high inference request rates.In conclusion, this thesis advances the field of privacy-preserving ML by addressing key trade-offs in differential privacy, empirical privacy defenses, and federated learning. The proposed methods provide new insights into balancing privacy with utility and other critical factors, offering practical solutions for integrating privacy-preserving techniques into real-world applications. These contributions aim to support the responsible and ethical deployment of AI technologies that prioritize data privacy and protection