Dissertations / Theses on the topic 'Méthodes d'apprentissage de la lecture'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Méthodes d'apprentissage de la lecture.'
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.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Doré-Mazars, Karine. "Le fonctionnement du système saccadique pendant la lecture : la programmation de la saccade vers un mot." Paris 5, 1996. http://www.theses.fr/1996PA05H003.
Full textThe goal of this thesis is to study the relationships between language perception and saccade computation during reading. In particular, we try to demonstrate how different integration levels of word information influence landing position in isolated words. The results illustrate the time course of word-information integration, starting with physical variables, until abstract variables such as lexical representation. The level of word information integration depends on saccade latency. In the earlier phases, representation in parafoveal vision is pre-lexical : orthographic irregularities modify the center of gravity of the word, initially determined by the word length. In the later phases, the landing position depends on the lexical information carried by the initial letters of the word that is presented in parafoveal vision. This work shows that landing position in words is a function of word global properties and also depends on the orthographic and lexical properties of linguistic stimuli
Maisonneuve, Luc. "Apprentissage de la lecture : méthodes et manuels." Rennes 2, 2001. http://www.theses.fr/2001REN20003.
Full text@This research focuses on the analysis of the eleven learning to read textbooks the most sold in France in 1999. Method and objectives : through the analysis of the pedagogical approach and the scientific and/or empirical rationale opf these eleven learning to read textbooks, this research aims at understanding their success by finding out how the take into account and reconcile pedagogical aspects, research findings, official guide-lines and economic constraints. Part one : A review of learning to read. What does reading mean ? (current description, brief historical account), existing konwledge (learning to speak, the debate about-pre-requisites- phonological conscience, knowledge about the written language, vocabulary) ; the relationship to learning (cultural differences, teacher effect) ; learning to read ? (main current models, reading-writting relations, learning problems). Part two : the various methodologi cal approaches to learning to read ; the role of initial and in-service training in teacher education. Part three ; analysis of the selected eleven textbooks from four angles : definitions and references about reading and learning to read, aims and assessment (pedagogical guide-lines and teacher books) teaching approach, semantic and axiological (pupil's books, exercise-books). Results ; If, on the one hand, this research can only make conjectures about the reasons of the success of these eleven textbooks (importance of the pedagogical aids, lack of training, routine, relationship with families), then the other hand, it evinces large similarities in the teachning approaches (in spite of the sometimes widely differing conceptions put forward) : stereotyped reading lessons, lack of definition of the reading act, absence of aims, teachers and texts no longer in the foreground, constant use of games, key role of pictures
Juanéda-Albarède, Christiane. "L'enfant et l'apprentissage de la lecture en France, au XIXe siècle : lecture et compréhension." Paris 5, 1990. http://www.theses.fr/1990PA05H070.
Full textHundreds of reading methods were conceived in France in the 19th century| how can we explain this phenomenon? There are political, economical and social factors as well as psychological and human ones which explain this widespread desire to improve the current practices beside ways considered by some as means, some authors suggest more important changes of the methods themselves. M. A. Peigne, for instance, emphasizing the fact that understanding what he reads is fundamental for a child, provokes what prost qualifies as a pedagogical "revolution" but in the 18th century, N. Adam's method of "mots entiers" gave importance to the notion that a child must understand what he reads. Nevertheless, such a method was reserved to private tutoring whereas with Peigne. In 1831, those ideas are applied to all school children. A few years before Peigne, two authors, orgeret and jacotot had used the theory of "mots entiers" a high number of methods throughout the 19th century give to a certain extent , an important place to reading and understanding but only nime of them among the 562 listed begin by "mots entiers" from the very first lessons. On the one hand peigne's method and on the other hand the analytic methods, a double "revolution" in the 19th century occurs in reading practises, one seems to be adapted to the teaching of read. In of that period, the other totally modify the current practises. Though the methoddology of "mots entiers" does not become current practise. The idea makes it way
Devaux, Jean-Michel. "Acquisition de la lecture : du maître à l'élève : représentation des maitres du cycle 2 sur la lecture et pratiques rémédiatives." Nantes, 2001. http://www.theses.fr/2001NANT3011.
Full textViriot-Goeldel, Caroline. "Aider l'apprenti lecteur en difficulté à l'école primaire : une perspective comparée : essai d'analyse théorique et praxéologique des processus d'aide dans les classes de l'enseignement primaire en France, au Québec et dans le Bade-Wurtemberg." Lyon 2, 2006. http://theses.univ-lyon2.fr/documents/lyon2/2006/viriot-goeldel_c.
Full textThis research follows the curriculum of first and second-grade classes in France, Germany (Baden-Württemberg) and Canada (Quebec) through regular interviews with their teachers and observation in reading remedial instruction. It analyses the detection of reading difficulties and the development of reading recovery programs from an organisational as well as from a didactical point of view. The comparison of the different strategies allows the discovery of strengths and weaknesses of each school system and suggests appropriate responses to effective intervention
Guimarães, Thomazi Aurea Regina. "L'enseignant de l'école élémentaire et le curriculum de la lecture : enquête à Belo Horizonte (Brésil)." Paris 5, 2005. http://www.theses.fr/2005PA05H012.
Full textThis research paper is aimed at the reading practices developed by teachers, preliminary school, in Brazil. We try to know the possibilities of reader formation at school and we focus our analysis on the making up of a reading curriculum for every teacher, based upon their declarations concerning the types of texts they use, activities engaged at the classrooms and at the library of the class or school. We then analyse other aspects concerning the teacher : his background, his beliefs in shaping a student reader, his workday, his planning, and above all his personal relationship with reading, at childhood, as a teenager and today. Or theoretical framework is based on the sociology of teachers, the sociology of curriculum and the sociology of reading. The methodology is grounded on interviews, answers to written questions and documents, handled through content analysis
Delpierre-Sahuc, Marie-Elisabeth. "De l'apprenti-lecteur au producteur habile : méthode de lecture et orthographe : quels liens?" Paris 3, 2008. http://www.theses.fr/2008PA030020.
Full textA correlation between the writing performance of elementary classes’ students and the reading method used in the “CP” class was underlined in 2000 (Master’s study). The purpose of the present research is to confirm this impact and to describe the development of writing automatisms and psycho-cognitive process evolution, which are both essential for the writing processing, in reading and spelling. The students’ longitudinal follow up, from the CP to the CM2, shows that the CP teaching may have a positive impact on establishing the writing processes and the performances of young readers and writers. Certain types of errors in dictation, copy work and essay can be observed until the CM2. Three methods have been analysed: the “dumb dictations” inspired by M. Montessori, the Freinet Natural method and the AFL Protocol, which differ in their theoretical, educational and linguistic bases. They are compared with the mixed, analytic and synthetic approaches. The results show that one of the essential teachings is the teaching of the grapho-phonological code, which settles reading skills and facilitates the control of spelling set of rules. The research underlines a “teacher’s practice” effect for the mixed methods restricted to reading’s teaching in the CP class and a “method” effect for those approaches which organize the teaching on all three cycles of primary school. The results show the necessity of an efficient textual activity, in order to develop the writing skills. The observed trends show a less effect of the socio-cultural environment on the performances of those cohorts which have received a phonologically based learning of letter-sound rules
Haidar, Rouba. "Élaboration et test d’un programme de remédiation aux difficultés en lecture au Cours Préparatoire." Thesis, Mulhouse, 2015. http://www.theses.fr/2015MULH5951/document.
Full textOur first objective in this study, carried out with Year 2 pupils, was to identify the least well- mastered skills relating to the identification of words and the comprehension of a text using a grid of basic skills established by the Ministry of Education. The second objective was to create and test the effectiveness of a remedial program based on training in the process of learning to read in Year 2, and reading comprehension skills (anaphora and inference) adapted for six-year-old pupils with difficulties. The number of pupils taking part in the study was 61: 42 in the two trial groups and 19 in the control group. Our study showed that on the one hand, students the students in the two trial groups made better progress than the control group in 8 out of the 10 skills. On the other hand, progress made by pupils lasted over a period of time and the intervention program showed itself to be equally successful for girls as for boys
Gaguet, Laurent. "Attitudes mentales et planification en intelligence artificielle : modélisation d'un agent rationnel dans un environnement multi-agents." Clermont-Ferrand 2, 2000. http://www.theses.fr/2000CLF20023.
Full textVinter, Patricia. "Est-il possible et souhaitable d’enseigner la technique de la lecture indépendamment de sa finalité ? : elaboration d'une méthode de lecture qui différencie le décodage de la compréhension en phase d’apprentissage explicite et sa mise à l'épreuve en éducation prioritaire." Thesis, Lyon 2, 2015. http://www.theses.fr/2015LYO20002.
Full textSchool failure continues to increase in France, as well as the gap between the lowest and highest performing pupils (PISA 2003, 2006, 2009, 2012). Reading is a complex activity that requires mastering conjointly two skills, word identification and meaning understanding. Word identification is the main cause of reading difficulty: the code that binds oral and written information must be understood as being based on conventions, and the pupils who cannot access to symbols encounter difficulties in this understanding. In the present work, we have developed a new learning device that makes clear to children the relationships between oral and written syllables. This device comprises a representation of the writing system and material that enables to manipulate phonogrammes. To this end, we have included an additional step within a reading and writing method, the identification of pseudo-words, that is to say, of “signifieds” (plausible words) without “signifiers” (no corresponding referee or meaning). In order not to neglect the understanding dimension at the beginning of the learning phase, oral stories were presented to the children. They were extracted from an album of 30 chapters in which the heroine, a young witch, attributes meaning to these pseudo-words through her magic spells. In the training phase, the pseudo-words (associated with its signifier) are presented inside various reading - identification and understanding - and writing activities. Our specific training had the expected positive effects in unselected grade 1 elementary pupils from areas of prioritary education. These effects concerned mainly the identification and production of words, without adverse effects in other aspects of writing
Navarro, Marion. "Utilisation de la tablette digitale pour réduire les difficultés dans l'apprentissage de la lecture." Thesis, Lyon, 2017. http://www.theses.fr/2017LYSE2088.
Full textThe main objective of this thesis work is to discuss the place of the touch-screen tablet in an adapted and targeted teaching system with children detected at risk of subsequent difficulties in reading. To meet this objective, we have presented two main axes, based on the results of the scientific literature. An experimental axis, made up of three studies, allowed us to measure the impact of a specific intensive and individual training, via the touch-screen tablet, on the performances in written words identification of poor (pre)readers in Kindergarten and First Grade. More precisely, the results of the longitudinal follow-up of the aforementioned students seem to be in favor of an improvement of the phonological awareness and the grapho-syllabic treatment. The second axis aims to highlight the importance of ergonomic criteria for the development of two edutainment apps. The results of the subjective evaluations identify points that requiring additional work, which may hinder the processing of crucial information for the learning of reading
Cléder, Catherine. "Planification didactique et construction de l'objectif d'une session de travail individualisée : modélisation des connaissances et du raisonnement mis en jeu." Clermont-Ferrand 2, 2002. http://www.theses.fr/2002CLF20019.
Full textPélissier, Chrysta. "Fonctionnalités et méthodologie de conception d'un module de type ressource : application dans un environnement informatique d'aide à l'apprentissage de la lecture." Phd thesis, Université Blaise Pascal - Clermont-Ferrand II, 2002. http://tel.archives-ouvertes.fr/tel-00661571.
Full textDepecker, Marine. "Méthodes d'apprentissage statistique pour le scoring." Phd thesis, Télécom ParisTech, 2010. http://pastel.archives-ouvertes.fr/pastel-00572421.
Full textKopinski, Thomas. "Méthodes d'apprentissage pour l'interaction homme-machine." Thesis, Université Paris-Saclay (ComUE), 2016. http://www.theses.fr/2016SACLY002/document.
Full textThis thesis aims at improving the complex task of hand gesture recognition by utilizing machine learning techniques to learn from features calculated from 3D point cloud data. The main contributions of this work are embedded in the domains of machine learning and in the human-machine interaction. Since the goal is to demonstrate that a robust real-time capable system can be set up which provides a supportive means of interaction, the methods researched have to be light-weight in the sense that descriptivity balances itself with the calculation overhead needed to, in fact, remain real-time capable. To this end several approaches were tested:Initially the fusion of multiple ToF-sensors to improve the overall recognition rate was researched. It is examined, how employing more than one sensor can significantly boost recognition results in especially difficult cases and get a first grasp on the influence of the descriptors for this task as well as the influence of the choice of parameters on the calculation of the descriptor. The performance of MLPs with standard parameters is compared with the performance of SVMs for which the parameters have been obtained via grid search.Building on these results, the integration of the system into the car interior is shown. It is demonstrated how such a system can easily be integrated into an outdoor environment subject to strongly varying lighting conditions without the need for tedious calibration procedures. Furthermore the introduction of a modified light-weight version of the descriptor coupled with an extended database significantly boosts the frame rate for the whole recognition pipeline. Lastly the introduction of confidence measures for the output of the MLPs allows for more stable classification results and gives an insight on the innate challenges of this multiclass problem in general.In order to improve the classification performance of the MLPs without the need for sophisticated algorithm design or extensive parameter search a simple method is proposed which makes use of the existing recognition routines by exploiting information already present in the output neurons of the MLPs. A simple fusion technique is proposed which combines descriptor features with neuron confidences coming from a previously trained net and proves that augmented results can be achieved in nearly all cases for problem classes and individuals respectively.These findings are analyzed in-depth on a more theoretical scale by comparing the effectiveness of learning solely on neural activities in the output layer with the previously introduced fusion approach. In order to take into account temporal information, the thesis describes a possible approach on how to exploit the fact that we are dealing with a problem within which data is processed in a sequential manner and therefore problem-specific information can be taken into account. This approach classifies a hand pose by fusing descriptor features with neural activities coming from previous time steps and lays the ground work for the following section of making the transition towards dynamic hand gestures. Furthermore an infotainment system realized on a mobile device is introduced and coupled with the preprocessing and recognition module which in turn is integrated into an automotive setting demonstrating a possible testing environment for a gesture recognition system.In order to extend the developed system to allow for dynamic hand gesture interaction a simplified approach is proposed. This approach demonstrates that recognition of dynamic hand gesture sequences can be achieved with the simple definition of a starting and an ending pose based on a recognition module working with sufficient accuracy and even allowing for relaxed restrictions in terms of defining the parameters for such a sequence
DUPEYRON, JURADO SOPHIE. "Les difficultes d'apprentissage de la lecture : approche psychopathologique." Amiens, 1994. http://www.theses.fr/1994AMIEM038.
Full textKanj, Sawsan. "Méthodes d'apprentissage pour la classification multi label." Thesis, Compiègne, 2013. http://www.theses.fr/2013COMP2076.
Full textMulti-label classification is an extension of traditional single-label classification, where classes are not mutually exclusive, and each example can be assigned by several classes simultaneously . It is encountered in various modern applications such as scene classification and video annotation. the main objective of this thesis is the development of new techniques to adress the problem of multi-label classification that achieves promising classification performance. the first part of this manuscript studies the problem of multi-label classification in the context of the theory of belief functions. We propose a multi-label learning method that is able to take into account relationships between labels ant to classify new instances using the formalism of representation of uncertainty for set-valued variables. The second part deals withe the problem of prototype selection in the framework of multi-label learning. We propose an editing algorithm based on the k-nearest neighbor rule in order to purify training dataset and improve the performances of multi-label classification algorithms. Experimental results on synthetic and real-world datasets show the effectiveness of our approaches
Condevaux, Charles. "Méthodes d'apprentissage automatique pour l'analyse de corpus jurisprudentiels." Thesis, Nîmes, 2021. http://www.theses.fr/2021NIME0008.
Full textJudicial decisions contain deterministic information (whose content is recurrent from one decision to another) and random information (probabilistic). Both types of information come into play in a judge's decision-making process. The former can reinforce the decision insofar as deterministic information is a recurring and well-known element of case law (ie past business results). The latter, which are related to rare or exceptional characters, can make decision-making difficult, since they can modify the case law. The purpose of this thesis is to propose a deep learning model that would highlight these two types of information and study their impact (contribution) in the judge’s decision-making process. The objective is to analyze similar decisions in order to highlight random and deterministic information in a body of decisions and quantify their importance in the judgment process
Spinel, William. "Contribution au repérage précoce des troubles d'apprentissage de la lecture." La Réunion, 2006. http://elgebar.univ-reunion.fr/login?url=http://thesesenligne.univ.run/06_01-spinel.pdf.
Full textThe main purpose of this study was to put to the test a possible correlation between the level of phonological conscience evaluated in great section of nursery school and the performance in a transcription task one year later, at the end of the preparatory course. In this aim, we observed over three years a group of more than sixty pupils of a private school of the city of Saint-André (Réunion island) by proceeding particularly with an evaluation of the level of phonological conscience in great section of nursery school in november 2001 and february 2002, followed by a test evaluating the level of transcription involving the same population at the end of the preparatory course, in june 2003. Among other results, it appeared that the correlation between the two studied variables was statistically significant. Therefore, the score obtained at the test of total phonological conscience in the great section of nursery school appears to be a good predictor of the performance in transcription as measured with a test in preparatory course. The acceptability of the different tasks involved in this study was very good and then, the selected tests could be useful in the early detection and prevention of possible troubles of reading and spelling
Ghoumari, Asmaa. "Métaheuristiques adaptatives d'optimisation continue basées sur des méthodes d'apprentissage." Thesis, Paris Est, 2018. http://www.theses.fr/2018PESC1114/document.
Full textThe problems of continuous optimization are numerous, in economics, in signal processing, in neural networks, and so on. One of the best-known and most widely used solutions is the evolutionary algorithm, a metaheuristic algorithm based on evolutionary theories that borrows stochastic mechanisms and has shown good performance in solving problems of continuous optimization. The use of this family of algorithms is very popular, despite the many difficulties that can be encountered in their design. Indeed, these algorithms have several parameters to adjust and a lot of operators to set according to the problems to solve. In the literature, we find a plethora of operators described, and it becomes complicated for the user to know which one to select in order to have the best possible result. In this context, this thesis has the main objective to propose methods to solve the problems raised without deteriorating the performance of these algorithms. Thus we propose two algorithms:- a method based on the maximum a posteriori that uses diversity probabilities for the operators to apply, and which puts this choice regularly in play,- a method based on a dynamic graph of operators representing the probabilities of transitions between operators, and relying on a model of the objective function built by a neural network to regularly update these probabilities. These two methods are detailed, as well as analyzed via a continuous optimization benchmark
Benkaci, Mourad. "Surveillance des systèmes mécatronique d'automobile par des méthodes d'apprentissage." Toulouse 3, 2011. https://tel.archives-ouvertes.fr/tel-00647456.
Full textMechatronic systems monitoring, especially those built on today's vehicles, is increasingly complicated. The interconnections of these systems for increased performance and comfort of vehicles increases the complexity of information needed for decision-making in real time. This PhD thesis is devoted to the problem of detection and isolation (FDI Fault Detection & Isolation) of faults in automotive systems using algorithms based on research and evaluation of information by mono-criterion approaches. Relevant variables for rapid detection of faults are selected in an automatic manner by using two different approaches: I. The first is to introduce the notion of conflict between all the measurable variables of mechatronic system and to analyze these variables using their projections in hyper-rectangles spaces classification. II. The second approach is to use Kolmogorov complexity as a tool for classification of fault signatures. The estimate of the Kolmogorov complexity by compression algorithms, without loss of information, allows defining a dictionary of faults and giving a score of criticality with respect to the healthy functioning of the vehicle. The two proposed approaches have been successfully applied to many types of automotive data in the ANR-DIAP project
Atine, Jean-Charles. "Méthodes d'apprentissage flou : application à la segmentation d'images biologiques." Toulouse, INSA, 2005. http://eprint.insa-toulouse.fr/archive/00000272/.
Full textThe presented works have for objective to help the biologists in the diagnosis of the cellular viability by using some methods of classification. Our work announces a strategy of classification allowing to building partition of images of cells coming from an optical microscope. We classify automatically the cells by operating the segmentation on images using the developed algorithm T-LAMDA. A statement concerning the existing classification methods, the color space and the resistance to noise, allows to finding the structure the most adapted to our study. The comparative analysis of various methods (of which LAMDA and T-LAMDA methods), allows us to put in evidence the most appropriate for the classification of cells subjected to the blue of methylene solution. We propose some supervised algorithms based on LAMDA to show if the way of treating the data influence the result. The T-LAMDA algorithm, based on the decision trees, shows itself the best adapted for our study and so gives more precise results than other methods, with a shorter time of execution. We suggest learning by using the CELCA application, Cell Classification Application, which uses the developed T-LAMDA algorithm. The software takes care of calculations of the kinetics, according to the images which respect to a well defined protocol. Time for treating 117 images is 6 '47'' minutes, what is widely below the time taken by biologists to count the cells
Théveniaut, Hugo. "Méthodes d'apprentissage automatique et phases quantiques de la matière." Thesis, Toulouse 3, 2020. http://www.theses.fr/2020TOU30228.
Full textMy PhD thesis presents three applications of machine learning to condensed matter theory. Firstly, I will explain how the problem of detecting phase transitions can be rephrased as an image classification task, paving the way to the automatic mapping of phase diagrams. I tested the reliability of this approach and showed its limits for models exhibiting a many-body localized phase in 1 and 2 dimensions. Secondly, I will introduce a variational representation of quantum many-body ground-states in the form of neural-networks and show our results on a constrained model of hardcore bosons in 2d using variational and projection methods. In particular, we confirmed the phase diagram obtained independently earlier and extends its validity to larger system sizes. Moreover we also established the ability of neural-network quantum states to approximate accurately solid and liquid bosonic phases of matter. Finally, I will present a new approach to quantum error correction based on the same techniques used to conceive the best Go game engine. We showed that efficient correction strategies can be uncovered with evolutionary optimization algorithms, competitive with gradient-based optimization techniques. In particular, we found that shallow neural-networks are competitive with deep neural-networks
Playe, Benoit. "Méthodes d'apprentissage statistique pour le criblage virtuel de médicament." Thesis, Paris Sciences et Lettres (ComUE), 2019. http://www.theses.fr/2019PSLEM010/document.
Full textThe rational drug discovery process has limited success despite all the advances in understanding diseases, and technological breakthroughs. Indeed, the process of drug development is currently estimated to require about 1.8 billion US dollars over about 13 years on average. Computational approaches are promising ways to facilitate the tedious task of drug discovery. We focus in this thesis on statistical approaches which virtually screen a large set of compounds against a large set of proteins, which can help to identify drug candidates for known therapeutic targets, anticipate potential side effects or to suggest new therapeutic indications of known drugs. This thesis is conceived following two lines of approaches to perform drug virtual screening : data-blinded feature-based approaches (in which molecules and proteins are numerically described based on experts' knowledge), and data-driven feature-based approaches (in which compounds and proteins numerical descriptors are learned automatically from the chemical graph and the protein sequence). We discuss these approaches, and also propose applications of virtual screening to guide the drug discovery process
Robbiano, Sylvain. "Méthodes d'apprentissage statistique pour le ranking : théorie, algorithmes et applications." Phd thesis, Telecom ParisTech, 2013. http://tel.archives-ouvertes.fr/tel-00936092.
Full textLaumonier, Julien. "Méthodes d'apprentissage de la coordination multiagent : application au transport intelligent." Thesis, Université Laval, 2008. http://www.theses.ulaval.ca/2008/25482/25482.pdf.
Full textAugustin, Lefèvre. "Méthodes d'apprentissage appliquées à la séparation de sources mono-canal." Phd thesis, École normale supérieure de Cachan - ENS Cachan, 2012. http://tel.archives-ouvertes.fr/tel-00764546.
Full textMohammed, Omar. "Méthodes d'apprentissage approfondi pour l'extraction et le transfert de style." Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAT035.
Full textOne aspect of a successful human-machine interface (e.g. human-robot interaction, chatbots, speech, handwriting…,etc) is the ability to have a personalized interaction. This affects the overall human experience, and allow for a more fluent interaction. At the moment, there is a lot of work that uses machine learning in order to model such interactions. However, these models do not address the issue of personalized behavior: they try to average over the different examples from different people in the training set. Identifying the human styles (persona) opens the possibility of biasing the models output to take into account the human preference. In this thesis, we focused on the problem of styles in the context of handwriting.Defining and extracting handwriting styles is a challenging problem, since there is no formal definition for those styles (i.e., it is an ill-posed problem). Styles are both social - depending on the writer's training, especially in middle school - and idiosyncratic - depends on the writer's shaping (letter roundness, sharpness…,etc) and force distribution over time. As a consequence, there are no easy/generic metrics to measure the quality of style in a machine behavior.We may want to change the task or adapt to a new person. Collecting data in the human-machine interface domain can be quite expensive and time consuming. Although most of the time the new task has many things in common with the old task, traditional machine learning techniques fail to take advantage of this commonality, leading to a quick degradation in performance. Thus, one of the objectives of my thesis is to study and evaluate the idea of transferring knowledge about the styles between different tasks, within the machine learning paradigm.The objective of my thesis is to study these problems of styles, in the domain of handwriting. Available to us is IRONOFF dataset, an online handwriting datasets, with 410 writers, with ~25K examples of uppercase, lowercase letters and digits drawings. For transfer learning, we used an extra dataset, QuickDraw!, a sketch drawing dataset containing ~50 million drawing over 345 categories.Major contributions of my thesis are:1) Propose a work pipeline to study the problem of styles in handwriting. This involves proposing methodology, benchmarks and evaluation metrics.We choose temporal generative models paradigm in deep learning in order to generate drawings, and evaluate their proximity/relevance to the intended/ground truth drawings. We proposed two metrics, to evaluate the curvature and the length of the generated drawings. In order to ground those metics, we proposed multiple benchmarks - which we know their relative power in advance -, and then verified that the metrics actually respect the relative power relationship.2) Propose a framework to study and extract styles, and verify its advantage against the previously proposed benchmarks.We settled on the idea of using a deep conditioned-autoencoder in order to summarize and extract the style information, without the need to focus on the task identity (since it is given as a condition). We validate this framework to the previously proposed benchmark using our evaluation metrics. We also to visualize on the extracted styles, leading to some exciting outcomes!3) Using the proposed framework, propose a way to transfer the information about styles between different tasks, and a protocol in order to evaluate the quality of transfer.We leveraged the deep conditioned-autoencoder used earlier, by extract the encoder part in it - which we believe had the relevant information about the styles - and use it to in new models trained on new tasks. We extensively test this paradigm over a different range of tasks, on both IRONOFF and QuickDraw! datasets. We show that we can successfully transfer style information between different tasks
Jacques, Céline. "Méthodes d'apprentissage automatique pour la transcription automatique de la batterie." Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS150.
Full textThis thesis focuses on learning methods for automatic transcription of the battery. They are based on a transcription algorithm using a non-negative decomposition method, NMD. This thesis raises two main issues: the adaptation of methods to the analyzed signal and the use of deep learning. Taking into account the information of the signal analyzed in the model can be achieved by their introduction during the decomposition steps. A first approach is to reformulate the decomposition step in a probabilistic context to facilitate the introduction of a posteriori information with methods such as SI-PLCA and statistical NMD. A second approach is to implement an adaptation strategy directly in the NMD: the application of modelable filters to the patterns to model the recording conditions or the adaptation of the learned patterns directly to the signal by applying strong constraints to preserve their physical meaning. The second approach concerns the selection of the signal segments to be analyzed. It is best to analyze segments where at least one percussive event occurs. An onset detector based on a convolutional neural network (CNN) is adapted to detect only percussive onsets. The results obtained being very interesting, the detector is trained to detect only one instrument allowing the transcription of the three main drum instruments with three CNNs. Finally, the use of a CNN multi-output is studied to transcribe the part of battery with a single network
Manenti, Céline. "Découverte d'unités linguistiques à l'aide de méthodes d'apprentissage non supervisé." Thesis, Toulouse 3, 2019. http://www.theses.fr/2019TOU30074.
Full textThe discovery of elementary linguistic units (phonemes, words) only from sound recordings is an unresolved problem that arouses a strong interest from the community of automatic speech processing, as evidenced by the many recent contributions of the state of the art. During this thesis, we focused on using neural networks to answer the problem. We approached the problem using neural networks in a supervised, poorly supervised and multilingual manner. We have developed automatic phoneme segmentation and phonetic classification tools based on convolutional neural networks. The automatic segmentation tool obtained 79% F-measure on the BUCKEYE conversational speech corpus. This result is similar to a human annotator according to the inter-annotator agreement provided by the creators of the corpus. In addition, it does not need a lot of data (about ten minutes per speaker and 5 different speakers) to be effective. In addition, it is portable to other languages (especially for poorly endowed languages such as xitsonga). The phonetic classification system makes it possible to set the various parameters and hyperparameters that are useful for an unsupervised scenario. In the unsupervised context, the neural networks (Auto-Encoders) allowed us to generate new parametric representations, concentrating the information of the input frame and its neighboring frames. We studied their utility for audio compression from the raw signal, for which they were effective (low RMS, even at 99% compression). We also carried out an innovative pre-study on a different use of neural networks, to generate vectors of parameters not from the outputs of the layers but from the values of the weights of the layers. These parameters are designed to mimic Linear Predictive Coefficients (LPC). In the context of the unsupervised discovery of phoneme-like units (called pseudo-phones in this memory) and the generation of new phonetically discriminative parametric representations, we have coupled a neural network with a clustering tool (k-means ). The iterative alternation of these two tools allowed the generation of phonetically discriminating parameters for the same speaker: low rates of intra-speaker ABx error of 7.3% for English, 8.5% for French and 8 , 4% for Mandarin were obtained. These results allow an absolute gain of about 4% compared to the baseline (conventional parameters MFCC) and are close to the best current approaches (1% more than the winner of the Zero Resource Speech Challenge 2017). The inter-speaker results vary between 12% and 15% depending on the language, compared to 21% to 25% for MFCCs
Laumônier, Julien. "Méthodes d'apprentissage de la coordination multiagent : application au transport intelligent." Doctoral thesis, Université Laval, 2008. http://hdl.handle.net/20.500.11794/20000.
Full textMordelet, Fantine. "Méthodes d'apprentissage statistique à partir d'exemples positifs et indéterminés en biologie." Phd thesis, École Nationale Supérieure des Mines de Paris, 2010. http://pastel.archives-ouvertes.fr/pastel-00566401.
Full textGosselin, Philippe-Henri. "Méthodes d'apprentissage pour la recherche de catégories dans des bases d'images." Phd thesis, Université de Cergy Pontoise, 2005. http://tel.archives-ouvertes.fr/tel-00619222.
Full textVu, Hien Duc. "Adaptation des méthodes d'apprentissage automatique pour la détection de défauts d'arc électriques." Electronic Thesis or Diss., Université de Lorraine, 2019. http://docnum.univ-lorraine.fr/ulprive/DDOC_T_2019_0152_VU.pdf.
Full textThe detection of electric arcs occurring in an electrical network by machine learning approaches represents the heart of the work presented in this thesis. The problem was first considered as a classification of fixed-size time series with two classes: normal and default. This first part is based on the work of the literature where the detection algorithms are organized mainly on a step of the transformation of the signals acquired on the network, followed by a step of extraction of descriptive characteristics and finally a step of decision. The multi-criteria approach adopted here aims to respond to systematic classification errors. A methodology for selecting the best combinations, transformation, and descriptors has been proposed by using learning solutions. As the development of relevant descriptors is always difficult, differents solutions offered by deep learning has also been studied. In a second phase, the study focused on the variable aspects in time of the fault detection. Two statistical decision paths have been explored, one based on the sequential probabilistic test (SPRT) and the other based on artificial neural networks LSTM (Long Short Time Memory Network). Each of these two methods exploits in its way the duration a first classification step between 0 and 1 (normal, default). The decision by SPRT uses an integration of the initial classification. LSTM learns to classify data with variable time. The results of the LSTM network are very promising, but there are a few things to explore. All of this work is based on experiments with the most complete and broadest possible data on the field of 230V alternative networks in a domestic and industrial context. The accuracy obtained is close to 100% in the majority of situations
Fournier, Edouard. "Méthodes d'apprentissage statistique pour la prédiction de charges et de contraintes aéronautiques." Thesis, Toulouse 3, 2019. http://www.theses.fr/2019TOU30123.
Full textThis thesis focuses on Machine Learning and information extraction for aeronautical loads and stress data. In the first time, we carry out a study for the prediction of aeronautical loads curves. We compare regression trees based models and quantify the influence of dimension reduction techniques on regression performances in an extrapolation context. In the second time, we develop a deformation model acting simultaneously on the input and the output space of the curves. We study the asymptotic properties of the estimators of the deformation parameters. This deformation model is associated to the modeling and predicting process of aeronautical loads. Finally, we give a simple and efficient method for predicting critical loads
Saldana, Miranda Diego. "Méthodes d'apprentissage automatique pour l'aide à la formulation : Carburants Alternatifs pour l'Aéronautique." Paris 6, 2013. http://www.theses.fr/2013PA066346.
Full textAlternative fuels and biofuels are a viable and attractive answer to problems associated to the current widespread use of conventional fuels in vehicles. One interesting aspect of alternative fuels is that the range of possible chemical compounds is large due to their diverse biological origins. This aspect opens up the possibility of creating “designer fuels”, whose chemical compositions are tailored to the specifications of the fuel being replaced. In this regard, it would be interesting to develop accurate predictive methods capable of instantaneously estimating a fuel’s physico-chemical properties based solely on its chemical composition and structures of its components. In this PhD work, we have investigated the application of machine learning methods to estimate properties such as flash point, enthalpy of combustion, melting point, cetane number, density and viscosity for families of compounds and mixtures similar to those found in biofuels: hydrocarbons and oxygenated compounds. During the first part of this work, machine learning models of pure compound properties were developed. During the second part mixtures have been examinated, two types of approaches were investigated: (1) the direct application of machine learning methods to mixture property data; (2) the use of the previously developed pure compound property models in combination with theoretically based mixing rules. It was found that machine learning methods, especially support vector machine methods, were an effective way of creating accurate and robust models. It was further found that, in the absence of sufficiently large or representative datasets, the use of mixing rules in combination with machine learning is a viable option. Overall, a number of accurate, robust and fast property estimation methods have been developed as a means to guide the formulation of alternative fuels
Dubois, Rémi. "Application des nouvelles méthodes d'apprentissage à la détection précoce d'anomalies en électrocardiographie." Paris 6, 2004. https://pastel.archives-ouvertes.fr/pastel-00000571.
Full textDupas, Rémy. "Apport des méthodes d'apprentissage symbolique automatique pour l'aide à la maintenance industrielle." Valenciennes, 1990. https://ged.uphf.fr/nuxeo/site/esupversions/7ab53b01-cdfb-4932-ba60-cb5332e3925a.
Full textBrunie, Vincent. "Reconstruction documentaire pour la lecture des hypertextes : problèmes et méthodes." Compiègne, 1999. http://www.theses.fr/1999COMP1238.
Full textChatellier, Marc. "Paradoxes des difficultés d'apprentissage de la lecture aux cycles 2 et 3 de l'école élémentaire : les chemins du désir entre (dé)construction, détour et autonomisation." Nantes, 2000. http://www.theses.fr/2000NANT3029.
Full textDubois, R. "Application des nouvelles méthodes d'apprentissage à la détection précoce d'anomalies cardiaques en électrocardiographie." Phd thesis, Université Pierre et Marie Curie - Paris VI, 2004. http://pastel.archives-ouvertes.fr/pastel-00000571.
Full textTorossian, Léonard. "Méthodes d'apprentissage statistique pour la régression et l'optimisation globale de mesures de risque." Thesis, Toulouse 3, 2019. http://www.theses.fr/2019TOU30192.
Full textThis thesis presents methods for estimation and optimization of stochastic black box functions. Motivated by the necessity to take risk-averse decisions in medecine, agriculture or finance, in this study we focus our interest on indicators able to quantify some characteristics of the output distribution such as the variance or the size of the tails. These indicators also known as measure of risk have received a lot of attention during the last decades. Based on the existing literature on risk measures, we chose to focus this work on quantiles, CVaR and expectiles. First, we will compare the following approaches to perform quantile regression on stochastic black box functions: the K-nearest neighbors, the random forests, the RKHS regression, the neural network regression and the Gaussian process regression. Then a new regression model is proposed in this study that is based on chained Gaussian processes inferred by variational techniques. Though our approach has been initially designed to do quantile regression, we showed that it can be easily applied to expectile regression. Then, this study will focus on optimisation of risk measures. We propose a generic approach inspired from the X-armed bandit which enables the creation of an optimiser and an upper bound on the simple regret that can be adapted to any risk measure. The importance and relevance of this approach is illustrated by the optimization of quantiles and CVaR. Finally, some optimisation algorithms for the conditional quantile and expectile are developed based on Gaussian processes combined with UCB and Thompson sampling strategies
Gayraud, Nathalie. "Méthodes adaptatives d'apprentissage pour des interfaces cerveau-ordinateur basées sur les potentiels évoqués." Thesis, Université Côte d'Azur (ComUE), 2018. http://www.theses.fr/2018AZUR4231/document.
Full textNon-invasive Brain Computer Interfaces (BCIs) allow a user to control a machine using only their brain activity. The BCI system acquires electroencephalographic (EEG) signals, characterized by a low signal-to-noise ratio and an important variability both across sessions and across users. Typically, the BCI system is calibrated before each use, in a process during which the user has to perform a predefined task. This thesis studies of the sources of this variability, with the aim of exploring, designing, and implementing zero-calibration methods. We review the variability of the event related potentials (ERP), focusing mostly on a late component known as the P300. This allows us to quantify the sources of EEG signal variability. Our solution to tackle this variability is to focus on adaptive machine learning methods. We focus on three transfer learning methods: Riemannian Geometry, Optimal Transport, and Ensemble Learning. We propose a model of the EEG takes variability into account. The parameters resulting from our analyses allow us to calibrate this model in a set of simulations, which we use to evaluate the performance of the aforementioned transfer learning methods. These methods are combined and applied to experimental data. We first propose a classification method based on Optimal Transport. Then, we introduce a separability marker which we use to combine Riemannian Geometry, Optimal Transport and Ensemble Learning. Our results demonstrate that the combination of several transfer learning methods produces a classifier that efficiently handles multiple sources of EEG signal variability
Lim, Laurie Baumard Jean. "Difficultés de compréhension en lecture et métacognition étude de cas /." [S.l.] : [s.n.], 2008. http://castore.univ-nantes.fr/castore/GetOAIRef?idDoc=43551.
Full textCara, Michel. "Stratégies d'apprentissage de la lecture musicale à court-terme : mémoire de travail et oculométrie cognitive." Thesis, Dijon, 2013. http://www.theses.fr/2013DIJOL013.
Full textThroughout this thesis, evaluation of music performance is viewed as a latent object of study in order to provide tools for learning to read music. We have defined some variables from eye movements and music performance accounting for expert performance and interactions between skill groups when learning a new piece of music. In more details, we have observed the use of different strategies for music information intake, processes and information retrieval depending on musicians’ expertise and we have stressed the importance of learning through interaction. In the process of skill acquisition, when self-confidence is gained strategies are simultaneously adjusted (Bandura, 1997; McPherson and McCormick, 2006). In reference to the current debate about the nature of music reading, we have compared musical and verbal processing during comprehensive reading of texts and scores. On the whole, considering the model of Baddeley (1990), musicians’ cognitive resources during music reading would be mobilized depending on the expertise and the music style
Deslauriers, Renée. "Compréhension en lecture et imagerie mentale chez des élèves en difficulté grave d'apprentissage au primaire /." Thèse, Trois-Rivières : Université du Québec à Trois-Rivières, 1998. http://www.uqtr.ca/biblio/notice/resume/03-2180863R.htm.
Full textBibliographie : f. [126]-131. Le résumé et la table des matières sont disponibles en format électronique sur le site Web de la bibliothèque. CaQTU
Deslauriers, Renée. "Compréhension en lecture et imagerie mentale chez des élèves en difficulté grave d'apprentissage au primaire." Thèse, Université du Québec à Trois-Rivières, 1998. http://depot-e.uqtr.ca/4858/1/000640737.pdf.
Full textBailly, Kévin. "Méthodes d'apprentissage pour l'estimation de la pose de la tête dans des images monoculaires." Phd thesis, Université Pierre et Marie Curie - Paris VI, 2010. http://tel.archives-ouvertes.fr/tel-00560836.
Full textBuhot, Arnaud. "Etude de propriétés d'apprentissage supervisé et non supervisé par des méthodes de Physique Statistique." Phd thesis, Université Joseph Fourier (Grenoble), 1999. http://tel.archives-ouvertes.fr/tel-00001642.
Full textSokol, Marina. "Méthodes d'apprentissage semi-supervisé basé sur les graphes et détection rapide des nœuds centraux." Phd thesis, Université Nice Sophia Antipolis, 2014. http://tel.archives-ouvertes.fr/tel-00998394.
Full text