Добірка наукової літератури з теми "Apprentissage à partir de peu d’exemples"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Apprentissage à partir de peu d’exemples".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Статті в журналах з теми "Apprentissage à partir de peu d’exemples"
Lhermie, Christian. "Les stratégies du distributeur." Décisions Marketing N° 8, no. 2 (June 1, 1996): 75–81. http://dx.doi.org/10.3917/dm.08.0075.
Повний текст джерелаEl Hage, Georges. "Regard orthodoxe sur la synodalité : un apprentissage mutuel des différentes confessions." Transversalités 169, no. 2 (April 8, 2024): 45–57. http://dx.doi.org/10.3917/trans.169.0045.
Повний текст джерелаHomola, Stéphanie. "Jeu, divination et cognition. La portée de Jouer de Roberte Hamayon." Cahiers d'Extrême-Asie 30, no. 1 (2021): 143–68. http://dx.doi.org/10.3406/asie.2021.1568.
Повний текст джерелаRavaud, Élisabeth, Gilles Bastian, Thomas Calligaro, Myriam Eveno, Éric Laval, and Laurent Pichon. "Nouveaux regards sur Léonard de Vinci par l’imagerie scientifique." Léonard de Vinci, l’expérience de l’art Hors-série (2024): 172–85. http://dx.doi.org/10.4000/11v4c.
Повний текст джерелаFierens, F., A. Modave, and G. Remion. "Les pivots culturels et les soirées du Quart-monde." Éducation populaire, culture et pouvoir, no. 2 (January 29, 2016): 37–39. http://dx.doi.org/10.7202/1034848ar.
Повний текст джерелаBoutaleb, Assia, and Laurence Dufresne Aubertin. "Bringing the administration back in." Mondes arabes N° 1, no. 1 (May 18, 2022): 71–96. http://dx.doi.org/10.3917/machr2.001.0071.
Повний текст джерелаPapas, Christian. "La traduction des métaphores au regard de la psychologie cognitive." Meta 52, no. 1 (March 12, 2007): 123–28. http://dx.doi.org/10.7202/014727ar.
Повний текст джерелаSqualli, Hassane. "La généralisation algébrique: Un processus mathématique peu développé chez les élèves à la fin de l’école secondaire." ITM Web of Conferences 39 (2021): 01002. http://dx.doi.org/10.1051/itmconf/20213901002.
Повний текст джерелаLaplante, Benoît, and Guy Bellevance. "L'évolution de la formation des artistes québécois au xxe siècle." Recherche 42, no. 3 (April 12, 2005): 543–84. http://dx.doi.org/10.7202/057475ar.
Повний текст джерелаQuesnay, Paul, Marianne Poumay, and Rémi Gagnayre. "Accompagner la mise en œuvre de l’approche par compétences dans les formations en santé : perspectives d’une stratégie de changement pragmatique portée par un individu tercéisateur dans un institut de formation en ostéopathie." Pédagogie Médicale 23, no. 1 (2022): 49–67. http://dx.doi.org/10.1051/pmed/2022001.
Повний текст джерелаДисертації з теми "Apprentissage à partir de peu d’exemples"
Deschamps, Sébastien. "Apprentissage actif profond pour la reconnaissance visuelle à partir de peu d’exemples." Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS199.
Повний текст джерелаAutomatic image analysis has improved the exploitation of image sensors, with data coming from different sensors such as phone cameras, surveillance cameras, satellite imagers or even drones. Deep learning achieves excellent results in image analysis applications where large amounts of annotated data are available, but learning a new image classifier from scratch is a difficult task. Most image classification methods are supervised, requiring annotations, which is a significant investment. Different frugal learning solutions (with few annotated examples) exist, including transfer learning, active learning, semi-supervised learning or meta-learning. The goal of this thesis is to study these frugal learning solutions for visual recognition tasks, namely image classification and change detection in satellite images. The classifier is trained iteratively by starting with only a few annotated samples, and asking the user to annotate as little data as possible to obtain satisfactory performance. Deep active learning was initially studied with other methods and suited our operational problem the most, so we chose this solution. In this thesis, we have developed an interactive approach, where we ask the most informative questions about the relevance of the data to an oracle (annotator). Based on its answers, a decision function is iteratively updated. We model the probability that the samples are relevant, by minimizing an objective function capturing the representativeness, diversity and ambiguity of the data. Data with high probability are then selected for annotation. We have improved this approach, using reinforcement learning to dynamically and accurately weight the importance of representativeness, diversity and ambiguity of the data in each active learning cycle. Finally, our last approach consists of a display model that selects the most representative and diverse virtual examples, which adversely challenge the learned model, in order to obtain a highly discriminative model in subsequent iterations of active learning. The good results obtained against the different baselines and the state of the art in the tasks of satellite image change detection and image classification have demonstrated the relevance of the proposed frugal learning models, and have led to various publications (Sahbi et al. 2021; Deschamps and Sahbi 2022b; Deschamps and Sahbi 2022a; Sahbi and Deschamps2022)
Moummad, Ilyass. "Invariant representation learning for few-shot bioacoustic event detection and classification." Electronic Thesis or Diss., Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2024. http://www.theses.fr/2024IMTA0442.
Повний текст джерелаThis thesis focuses on developing robust and transferable representation learning techniques for few-shot bioacoustic event detection and classification, addressing core challenges in deep learning such as domain generalization, domain adaptation, data scarcity, and class imbalance. Through the exploration of self-supervised invariant representation learning, we demonstrate that domain-agnostic data augmentations can yield informative and discriminative representations. A key focus of this work is the use of supervised contrastive learning to enhance model generalization across different species and acoustic environments. Furthermore, we propose a novel supervised contrastive loss, inspired by prototypical networks, that reduces the computational complexity of the traditional supervised contrastive loss while maintaining performance. Additional contributions include leveraging metadata to improve generalization and tackling imbalanced multi-label classification. Although the primary application of this thesis is bioacoustic monitoring, the deep learning techniques developed are generalizable and can be applied to other audio domains, modalities, and applications
Tuo, Aboubacar. "Extraction d'événements à partir de peu d'exemples par méta-apprentissage." Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPASG098.
Повний текст джерелаInformation Extraction (IE) is a research field with the objective of automatically identifying and extracting structured information within a given domain from unstructured or minimally structured text data. The implementation of such extractions often requires significant human efforts, either in the form of rule development or the creation of annotated data for systems based on machine learning. One of the current challenges in information extraction is to develop methods that minimize the costs and development time of these systems whenever possible. This thesis focuses on few-shot event extraction through a meta-learning approach that aims to train IE models from only few data. We have redefined the task of event extraction from this perspective, aiming to develop systems capable of quickly adapting to new contexts with a small volume of training data. First, we propose methods to enhance event trigger detection by developing more robust representations for this task. Then, we tackle the specific challenge raised by the "NULL" class (absence of events) within this framework. Finally, we evaluate the effectiveness of our proposals within the broader context of event extraction by extending their application to the extraction of event arguments
Grativol, Ribeiro Lucas. "Neural network compression in the context of federated learning and edge devices." Electronic Thesis or Diss., Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2024. http://www.theses.fr/2024IMTA0444.
Повний текст джерелаFederated learning is a collaborative, decentralized machine learning framework driven by growing concerns about data privacy. By shifting model training to local nodes and keeping data local, it enables more privacy-conscious training. However, this approach imposes additional communication and computation overhead on those who adopt it. In this manuscript, we examine the key challenges in federated learning and propose solutions to increase efficiency and reduce hardware requirements. Specifically, we explore classic compression techniques, such as pruning, and low-rank approximations to lower the costs associated with federated learning. For scenarios where participants have limited communication capabilities, we introduce a co-design methodology for an embedded few-shot learning algorithm. Our proposed solution integrates hardware constraints into a deployment pipeline for FPGA platforms, resulting in a low-latency algorithm that can also be leveraged to implement post-federated learning models
Baki, Islem. "Une approche heuristique pour l’apprentissage de transformations de modèles complexes à partir d’exemples." Thèse, 2014. http://hdl.handle.net/1866/11699.
Повний текст джерелаModel-driven engineering (MDE) is a well-established software engineering paradigm that promotes models as main artifacts in software development and maintenance activities. As several models may be manipulated during the software life-cycle, model transformations (MT) ensure their coherence by automating model generation and update tasks when possible. However, writing model transformations remains a difficult task that requires much knowledge and effort that detract from the benefits brought by the MDE paradigm. To address this issue, much research effort has been directed toward MT automation. Model Transformation by Example (MTBE) is, in this regard, a promising approach. MTBE aims to learn transformation programs starting from a set of source and target model pairs supplied as examples. In this work, we propose a process to learn model transformations from examples. Our process aims to learn complex MT by tackling three observed requirements, namely, context exploration of the source model, source attribute value testing, and complex target attribute derivation. We experimentally evaluate our approach on seven model transformation problems. The learned transformation programs are able to produce perfect target models in three transformation cases, whereas, precision and recall higher than 90% are recorded for the four remaining ones.
Частини книг з теми "Apprentissage à partir de peu d’exemples"
BERK, Cybèle. "Enseigner la grammaire turque." In Enseignement-apprentissage de la grammaire en langue vivante étrangère, 21–32. Editions des archives contemporaines, 2023. http://dx.doi.org/10.17184/eac.5810.
Повний текст джерелаPambou, Jean-Aimé. "Appropriation du français à travers les détournements de sigles, d’acronymes ou d’abréviations chez des apprenants de filières techniques au Gabon." In Écoles, langues et cultures d’enseignement en contexte plurilingue africain, 67–90. Observatoire européen du plurilinguisme, 2018. http://dx.doi.org/10.3917/oep.agbef.2018.01.0067.
Повний текст джерелаTonato, Kocou Prosper. "Apprentissage du français dans l’enseignement primaire au Bénin : Nécessité de repenser le dispositif pédagogique." In Langues, formations et pédagogies : le miroir africain, 45–64. Observatoire européen du plurilinguisme, 2018. http://dx.doi.org/10.3917/oep.agbef.2018.02.0045.
Повний текст джерела