Academic literature on the topic 'Apprentissage contrastif'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Apprentissage contrastif.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Apprentissage contrastif"
Dozin, Florence. "Langues en contact – langues en contraste. Typologie, plurilinguismes et apprentissages." International Journal of Bilingual Education and Bilingualism 17, no. 5 (July 12, 2013): 624–27. http://dx.doi.org/10.1080/13670050.2013.809912.
Full textBricet, Roxane, and Héloïse Lucas. "Tutorat, parrainage, mentorat : des dispositifs aux effets contrastés pour lutter contre les inégalités des chances." Sciences & Actions Sociales N° 20, no. 2 (February 1, 2024): 10–33. http://dx.doi.org/10.3917/sas.020.0004.
Full textGarcía de Toro, Cristina. "La investigación sobre la traducción entre catalán y español: estudios lingüísticos." Meta 60, no. 1 (July 22, 2015): 71–89. http://dx.doi.org/10.7202/1032400ar.
Full textBarthès, Didier. "Statut et rôles des artefacts matériels dans les situations d’enseignement – apprentissage en langue: Étude comparée dans deux collèges contrastés." Procedia - Social and Behavioral Sciences 34 (2012): 20–24. http://dx.doi.org/10.1016/j.sbspro.2012.02.005.
Full textElbaz, Pascale, and Jun Miao. "Le lexique du wen (culture) dans le discours politique chinois et dans sa traduction française au prisme de la textométrie." FORUM / Revue internationale d’interprétation et de traduction / International Journal of Interpretation and Translation 21, no. 1 (July 6, 2023): 25–50. http://dx.doi.org/10.1075/forum.00027.mia.
Full textDolz, Joaquim, Jean-Paul Mabillard, Catherine Tobola Couchepin, and Yann Vuillet. "Analyse contrastée des difficultés des élèves dans la rédaction d’une réponse au courrier des lecteurs, et de leur traitement en classe." Swiss Journal of Educational Research 31, no. 3 (December 1, 2009): 541–64. http://dx.doi.org/10.24452/sjer.31.3.4818.
Full textIMENE, Ksentini. "Problèmes d’interférences arabe/français dans les productions écrites d’élèves de secondaire." FRANCISOLA 3, no. 2 (March 2, 2019): 114. http://dx.doi.org/10.17509/francisola.v3i2.15745.
Full textSnow, Kathy. "Social Justice or Status Quo? Blended Learning in a Western Canadian Teacher Education Program | Justice sociale ou statu quo ? L’apprentissage mixte dans un programme de formation d’enseignants dans l’Ouest canadien." Canadian Journal of Learning and Technology / La revue canadienne de l’apprentissage et de la technologie 42, no. 3 (August 8, 2016). http://dx.doi.org/10.21432/t23k8t.
Full textDissertations / Theses on the topic "Apprentissage contrastif"
Denize, Julien. "Self-supervised representation learning and applications to image and video analysis." Electronic Thesis or Diss., Normandie, 2023. http://www.theses.fr/2023NORMIR37.
Full textIn this thesis, we develop approaches to perform self-supervised learning for image and video analysis. Self-supervised representation learning allows to pretrain neural networks to learn general concepts without labels before specializing in downstream tasks faster and with few annotations. We present three contributions to self-supervised image and video representation learning. First, we introduce the theoretical paradigm of soft contrastive learning and its practical implementation called Similarity Contrastive Estimation (SCE) connecting contrastive and relational learning for image representation. Second, SCE is extended to global temporal video representation learning. Lastly, we propose COMEDIAN a pipeline for local-temporal video representation learning for transformers. These contributions achieved state-of-the-art results on multiple benchmarks and led to several academic and technical published contributions
Bakkali, Souhail. "Multimodal Document Understanding with Unified Vision and Language Cross-Modal Learning." Electronic Thesis or Diss., La Rochelle, 2022. http://www.theses.fr/2022LAROS046.
Full textThe frameworks developed in this thesis were the outcome of an iterative process of analysis and synthesis between existing theories and our performed studies. More specifically, we wish to study cross-modality learning for contextualized comprehension on document components across language and vision. The main idea is to leverage multimodal information from document images into a common semantic space. This thesis focuses on advancing the research on cross-modality learning and makes contributions on four fronts: (i) to proposing a cross-modal approach with deep networks to jointly leverage visual and textual information into a common semantic representation space to automatically perform and make predictions about multimodal documents (i.e., the subject matter they are about); (ii) to investigating competitive strategies to address the tasks of cross-modal document classification, content-based retrieval and few-shot document classification; (iii) to addressing data-related issues like learning when data is not annotated, by proposing a network that learns generic representations from a collection of unlabeled documents; and (iv) to exploiting few-shot learning settings when data contains only few examples
Papanastasiou, Effrosyni. "Feasibility of Interactions and Network Inference of Online Social Networks." Electronic Thesis or Diss., Sorbonne université, 2024. http://www.theses.fr/2024SORUS173.
Full textThis thesis deals with the problem of network inference in the domain of Online So-cial Networks. The main premise of network inference problems is that the networkwe are observing is not the network that we really need. This is especially prevalentin today's digital space, where the abundance of information usually comes withcrucial unreliability, in the form of noise and missing points in the data. However, existing approaches either ignore or do not guarantee to infer networks in a waythat can explain the data we have at hand. As a result, there is an ambiguity around the meaning of the network that we are inferring, while also having little intuition or control over the inference itself. The goal of this thesis is to further explore this problem. To quantify how well an inferred network can explain a dataset, we introduce a novel quality criterion called feasibility. Our intuition is that if a dataset is feasible given an inferred network, we might also be closer to the ground truth. To verify this,we propose a novel network inference method in the form of a constrained, Maximum Likelihood-based optimization problem that guarantees 100% feasibility. It is tailored to inputs from Online Social Networks, which are well-known sources of un-reliable and restricted data. We provide extensive experiments on one synthetic andone real-world dataset coming from Twitter/X. We show that our proposed method generates a posterior distribution of graphs that guarantees to explain the dataset while also being closer to the true underlying structure when compared to other methods. As a final exploration, we look into the field of deep learning for more scalable and flexible alternatives, providing a preliminary framework based on Graph Neural Networks and contrastive learning that gives promising results
Do, Quoc khanh. "Apprentissage discriminant des modèles continus en traduction automatique." Thesis, Université Paris-Saclay (ComUE), 2016. http://www.theses.fr/2016SACLS071/document.
Full textOver the past few years, neural network (NN) architectures have been successfully applied to many Natural Language Processing (NLP) applications, such as Automatic Speech Recognition (ASR) and Statistical Machine Translation (SMT).For the language modeling task, these models consider linguistic units (i.e words and phrases) through their projections into a continuous (multi-dimensional) space, and the estimated distribution is a function of these projections. Also qualified continuous-space models (CSMs), their peculiarity hence lies in this exploitation of a continuous representation that can be seen as an attempt to address the sparsity issue of the conventional discrete models. In the context of SMT, these echniques have been applied on neural network-based language models (NNLMs) included in SMT systems, and oncontinuous-space translation models (CSTMs). These models have led to significant and consistent gains in the SMT performance, but are also considered as very expensive in training and inference, especially for systems involving large vocabularies. To overcome this issue, Structured Output Layer (SOUL) and Noise Contrastive Estimation (NCE) have been proposed; the former modifies the standard structure on vocabulary words, while the latter approximates the maximum-likelihood estimation (MLE) by a sampling method. All these approaches share the same estimation criterion which is the MLE ; however using this procedure results in an inconsistency between theobjective function defined for parameter stimation and the way models are used in the SMT application. The work presented in this dissertation aims to design new performance-oriented and global training procedures for CSMs to overcome these issues. The main contributions lie in the investigation and evaluation of efficient training methods for (large-vocabulary) CSMs which aim~:(a) to reduce the total training cost, and (b) to improve the efficiency of these models when used within the SMT application. On the one hand, the training and inference cost can be reduced (using the SOUL structure or the NCE algorithm), or by reducing the number of iterations via a faster convergence. This thesis provides an empirical analysis of these solutions on different large-scale SMT tasks. On the other hand, we propose a discriminative training framework which optimizes the performance of the whole system containing the CSM as a component model. The experimental results show that this framework is efficient to both train and adapt CSM within SMT systems, opening promising research perspectives
Contreras, Roa Leonardo. "Prosodie et apprentissage des langues : étude contrastive de l’interlangue d’apprenants d’anglais francophones et hispanophones." Thesis, Rennes 2, 2019. http://www.theses.fr/2019REN20053.
Full textThis thesis is a study of the prosodic interlanguage of students of English as a foreign language whose native language is French or Spanish. It is organized in two main parts. The first part is a study of the methods of conception and representation of prosody for the analysis of interlanguage – a hybrid linguistic system which includes characteristics of the student's native language, characteristics of the target language, and intermediate developmental or characteristics. This provides a methodological framework for the phonetic analysis and phonological interpretation of this type of prosodic systems. The second part is the implementation of this methodology through a contrastive interlanguage analysis conducted through the study of an oral corpus of students of English as a foreign language. The results show traces of the influence of their respective native languages at the phonetic and phonological levels, as well as developmental characteristics common to both groups of learners. The results serve as a basis for reflection on the levels of abstraction in the study of prosody and on the didactic priorities for teaching oral English at a university level
Incorvaia, Nicolas. "L'enseignement-apprentissage de l'arabe standard moderne aux-par les apprenants français." Electronic Thesis or Diss., Toulouse 2, 2020. http://www.theses.fr/2020TOU20036.
Full textThe relationships between the inhabitants of France and the speakers of the Arab language-culture are very old, as they date back at least to the Crusades and the first Latin translations of the Koran. After reminding the main historical steps of the teaching of Arabic in France (officially organised in France since the 16th century), we will look into the current situation of this language in France, where it is considered the second most spoken language. However, this language presents a remarkable pluriglossia situation with five varieties living alongside: Classical Arabic, Modern Standard Arabic (or MSA), Middle Arabic, the Arabic dialects and the “francarabe”. These historical and sociolinguistic elements, completed by a comparative study between MSA and Standard French, allow us to approach our problematic that falls into the didactics of languages-cultures : What are the main issues that can be encountered by a adult French learner who starts studying MSA? The analysis of a corpus of errors allows us to answer this question and to proffer some didactic proposals to facilitate the learning of communication in MSA. In order to deepen our thinking on this matter, we also sought to know the motivations that led the respondents to learn MSA, as well as the uses they made of their skills in Arabic. Our problematic is also set in the social context of contemporary France, where intercultural communication is of paramount importance
Chéhab, L'Émir Omar. "Advances in Self-Supervised Learning : applications to neuroscience and sample-efficiency." Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPASG079.
Full textSelf-supervised learning has gained popularity as a method for learning from unlabeled data. Essentially, it involves creating and then solving a prediction task using the data, such as reordering shuffled data. In recent years, this approach has been successful in training neural networks to learn useful representations from data, without any labels. However, our understanding of what is actually being learned and how well it is learned is still somewhat limited. This document contributes to our understanding of self-supervised learning in these two key aspects.Empirically, we address the question of what is learned. We design prediction tasks specifically tailored to learning from brain recordings with magnetoencephalography (MEG) or electroencephalography (EEG). These prediction tasks share a common objective: recognizing temporal structure within the brain data. Our results show that representations learnt by solving these tasks contain interpretable cognitive and clinical neurophysiological features.Theoretically, we explore the quality of the learning procedure. Our focus is on a specific category of prediction tasks: binary classification. We extend prior research that has highlighted the utility of binary classification for statistical inference, though it may involve trading off some measure of statistical efficiency for another measure of computational efficiency. Our contributions aim to improve statistical efficiency. We theoretically analyze the statistical estimation error and find situations when it can be provably reduced. Specifically, we characterize optimal hyperparameters of the binary classification task and also prove that the popular heuristic of "annealing" can lead to more efficient estimation, even in high dimensions
Louiset, Robin. "Learning pathological representations in neuroimaging : Predicting psychiatric diagnosis by integrating heterogeneity constraints." Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPAST044.
Full textThe biological mechanisms that underlie the symptoms of psychiatric diseases, such as schizophrenia, bipolar, or autistic disorders, are still poorly understood in many regards.One of the main reasons is the neurobiological heterogeneity associated with these diseases. Furthermore, healthy subjects usually share common but irrelevant factors of variation with the patients, such as age, sex, acquisition site, and ethnicity. These two major obstacles hamper the identification of consistent and interpretable biological markers associated with these diseases and their clinical scales, such as paranoia, anxiety, or depression.One of the main reasons is the neurobiological heterogeneity associated with these diseases. This hampers the identification of clear and interpretable biological markers associated with these diseases. In this thesis, our goal is to develop machine learning techniques to automatically stratify psychiatric diseases into homogeneous subgroups or to automatically identify the pathological latent distinct and interpretable generative factors, based on objective biological markers acquired through neuroanatomical MRI imaging techniques.At first, this thesis focused on developing clustering methods to stratify a disorder into homogeneous subgroups. Our first contribution was a extit{linear} subgroup discovery algorithm, called UCSL (Unsupervised Clustering driven by Supervised Learning), which identifies subgroups that stem only from the pathological variability specific to the disorder while disregarding the common variability shared with the healthy population. As a second contribution, this was then extended with a non-linear deep features extractor, potentially more powerful in recognizing complex pathological signatures. This new deep learning method entitled Deep UCSL, can directly extract features from anatomical MRI images, showed state-of-the-art results in neuro-psychiatric subgroup identification, and demonstrated generalization capabilities to other medical imaging domains (eye and lung pathologies). Ultimately, to illustrate the usefulness of such Subgroup Discovery methods, the linear method UCSL was leveraged to identify subtypes in a cohort of individuals with schizophrenia and to analyze their clinical relevance.Another line of research investigated in this thesis consisted of estimating the latent distinct and interpretable generative factors that underpin the neurobiological heterogeneity proper to the psychiatric disorder. To address this objective, this thesis investigated a class of representation learning methods that enable separating pathological patterns from healthy patterns of variability: contrastive analysis methods. These methods do not require assuming the existence of homogeneous subgroups. This field of statistical learning aims at separating ''common'' and ''target'' variability factors given a ''source'' dataset and a ''target'' dataset. In our case, the goal is to identify, on the one hand, the projection that allows identifying healthy variability patterns and, on the other hand, the projection that allows identifying ''pathological signatures'' that exist only in the class of patients and not in the class of healthy people. A contrastive variational autoencoder method entitled SepVAE was developed and contributed to competing methods in two ways: by adding a classification task in the pathological space and by adding a cost function based on mutual information to minimize information redundancy between the common space and the pathological space. Eventually, to provide a rich methodological perspective, a novel contrastive analysis strategy was developed. This method extends the framework of contrastive analysis methods to another promising class of representation learning methods: mutual information maximization learning. These methodological contributions were then validated on vision, medical, and neuroimaging datasets
Poezevara, Guillaume. "Fouille de graphes pour la découverte de contrastes entre classes : application à l'estimation de la toxicité des molécules." Phd thesis, Université de Caen, 2011. http://tel.archives-ouvertes.fr/tel-01018425.
Full textZhang, Yarui. "Non-linear electromagnetic imaging : from sparsity-preserving wavelet-based algorithms to deep learning." Electronic Thesis or Diss., université Paris-Saclay, 2022. http://www.theses.fr/2022UPAST167.
Full textThis work deals with nonlinear ill-posed electromagnetic imaging from time-harmonic data within a two-dimensional scattering experiment, the focus being on two approaches in the framework of the contrast-source inversion (CSI). The first approach is a group sparsity penalized CSI in the wavelet domain, the second is an unrolled deep learning scheme. In the first approach, dependency exists between wavelet coefficients at different scales, referred to as parent-child relationship, which yields a wavelet quadtree structure so that wavelet coefficients are both pixel-wise and group-wise sparse. Emphasis is on the dual-tree complex wavelet transform (CWT) to achieve this result. A '2;1 norm added to the standard cost function is to enforce group sparsity onto the wavelet coefficients of the spatially-varying contrast. The replication strategy is combined with the proximal method to solve the overlapping group penalized problem. The second approach is inspired by the unrolled method. By embedding the CSI iterations into the deep learning model, the domain knowledge is incorporated into the learning process. In both cases, thorough numerical tests are carried out to evaluate performance, stability, robustness, and reliability with comparisons with more standard solutions (like CSI, discrete wavelet transform (DWT) and U-net), which exhibit the advantage of the proposed approaches under many aspects
Books on the topic "Apprentissage contrastif"
Borel, Stéphane. Langues en contact, langues en contraste: Typologie, plurilinguismes et apprentissages. Bern: Peter Lang, 2012.
Find full textWieslaw, Oleksy, ed. Contrastive pragmatics. Amsterdam: J. Benjamins Pub. Co., 1989.
Find full textSELINKER, LARRY. Rediscovering Interlanguage. Routledge, 2013.
Find full textPurves, Alan C. Writing Across Languages and Cultures: Issues in Contrastive Rhetoric (SAGE Series on Written Communication). Sage Publications, Inc, 1988.
Find full textPurves, Alan C. Writing Across Languages and Cultures: Issues in Contrastive Rhetoric (SAGE Series on Written Communication). Sage Publications, Inc, 1988.
Find full textBook chapters on the topic "Apprentissage contrastif"
WANG, Xinxia, Xialing SHEN, and Jing GUO. "La métaphore dans les dictionnaires bilingues d’apprentissage :." In Dictionnaires et apprentissage des langues, 79–88. Editions des archives contemporaines, 2021. http://dx.doi.org/10.17184/eac.4627.
Full textCOLIN RODEA, Marisela, and Mihaela MIHAELIESCU. "Dictionnaire d’apprentissage de langue roumaine." In Dictionnaires et apprentissage des langues, 7–14. Editions des archives contemporaines, 2021. http://dx.doi.org/10.17184/eac.4498.
Full textKIM, Jin-Ok. "L'enseignement de la particule de thème et de contraste en coréen." In Enseignement-apprentissage de la grammaire en langue vivante étrangère, 77–104. Editions des archives contemporaines, 2023. http://dx.doi.org/10.17184/eac.5817.
Full textTran, Tri. "Transmission du savoir-faire et apprentissage dans les marines écossaise et anglaise (du quinzième au dix-huitième siècles) : une histoire contrastée." In The Production and Dissemination of Knowledge in Scotland, 123–36. Presses universitaires de Franche-Comté, 2017. http://dx.doi.org/10.4000/books.pufc.40585.
Full textSore, Ousséni. "Influence du substrat de la langue maternelle moore sur le français des apprenants du post-primaire." In Didactique des langues, plurilinguisme et sciences sociales en Afrique francophone : quelles places à l’interdisciplinarité ?, 193–210. Observatoire européen du plurilinguisme, 2020. http://dx.doi.org/10.3917/oep.agbef.2020.01.0193.
Full text