Dissertations / Theses on the topic 'Apprentissage de représentation d'état'
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 'Apprentissage de représentation d'état.'
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.
Merckling, Astrid. "Unsupervised pretraining of state representations in a rewardless environment." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS141.
Full textThis thesis seeks to extend the capabilities of state representation learning (SRL) to help scale deep reinforcement learning (DRL) algorithms to continuous control tasks with high-dimensional sensory observations (such as images). SRL allows to improve the performance of DRL by providing it with better inputs than the input embeddings learned from scratch with end-to-end strategies. Specifically, this thesis addresses the problem of performing state estimation in the manner of deep unsupervised pretraining of state representations without reward. These representations must verify certain properties to allow for the correct application of bootstrapping and other decision making mechanisms common to supervised learning, such as being low-dimensional and guaranteeing the local consistency and topology (or connectivity) of the environment, which we will seek to achieve through the models pretrained with the two SRL algorithms proposed in this thesis
Bigot, Damien. "Représentation et apprentissage de préférences." Thesis, Toulouse 3, 2015. http://www.theses.fr/2015TOU30031/document.
Full text--
Kurovszky, Monika. "Etude des systèmes dynamiques hybrides par représentation d'état discrète et automate hybride." Phd thesis, Université Joseph Fourier (Grenoble), 2002. http://tel.archives-ouvertes.fr/tel-00198326.
Full textTomasini, Linda. "Apprentissage d'une représentation statistique et topologique d'un environnement." Toulouse, ENSAE, 1993. http://www.theses.fr/1993ESAE0024.
Full textChabiron, Olivier. "Apprentissage d'arbres de convolutions pour la représentation parcimonieuse." Thesis, Toulouse 3, 2015. http://www.theses.fr/2015TOU30213/document.
Full textThe dictionary learning problem has received increasing attention for the last ten years. DL is an adaptive approach for sparse data representation. Many state-of-the-art DL methods provide good performances for problems such as approximation, denoising and inverse problems. However, their numerical complexity restricts their use to small image patches. Thus, dictionary learning does not capture large features and is not a viable option for many applications handling large images, such as those encountered in remote sensing. In this thesis, we propose and study a new model for dictionary learning, combining convolutional sparse coding and dictionaries defined by convolutional tree structures. The aim of this model is to provide efficient algorithms for large images, avoiding the decomposition of these images into patches. In the first part, we study the optimization of a composition of convolutions with sparse kernels, to reach a target atom (such as a cosine, wavelet or curvelet). This is a non-convex matrix factorization problem. We propose a resolution method based on a Gaus-Seidel scheme, which produces good approximations of target atoms and whose complexity is linear with respect to the image size. Moreover, numerical experiments show that it is possible to find a global minimum. In the second part, we introduce a dictionary structure based on convolutional trees. We propose a dictionary update algorithm adapted to this structure and which complexity remains linear with respect to the image size. Finally, a sparse coding step is added to the algorithm in the last part. For each evolution of the proposed method, we illustrate its approximation abilities with numerical experiments
Ternisien, Eric. "Caractérisation aveugle d'un système de dispersion en représentation d'état et localisation de source." Littoral, 2001. http://www.theses.fr/2001DUNK0067.
Full textThis study deals with the localization of a source which emits an unknown signal in a propagation medium thanks to a scattering model. In this model, the advection parameters are supposed to be known, but the diffusion ones are unknown and hard to measure. The source signal distorted by the propagation is provided by a set of spatially distributed sensors. These observations are disturbed by Gaussian iid noises. We show for some kind of model, the possibility to obtain a discrete state-space model using the finite differences, where the evolution matrix A describes the propagation. Some of the matrix A parameters needs to be identified. In the same way, the matrix B that characterizes the source placement is completely unknown. The matrix C describes the sensor array architecture. Each source-sensor channel is approximated by an unknown FIR filter. The blind identification consists in estimating  conditionnally to a source position. The subspace method, based on the decomposition in signal and noise subspaces, leads to the identification of the impulse responses of the channels. The localization is the reduced to an iterative process of blind identification and decision in order to maximize a localization criterion. A few temporal and frequential criterions have been developed. This approach depends on the size of the potential source positions set, but an initial localization method allows a size reduction of this set by means of observations crosscorrelations and numerical propagation scheme. The use of a propagation model in a real case of atmospheric pollution where the wind parameters are variable but known, leads to study the non stationary blind identification problem. We show that the difficulty is reduced to the search of a consistent estimator of the autocorrelation matrix
Boimond, Jean-Louis. "Commande à modèle interne en représentation d'état. : Problèmes de synthèse d'algorithme de commande." Lyon, INSA, 1990. http://www.theses.fr/1990ISAL0102.
Full text[The works presented in this thesis concern the Internal Model Control (I. M. C. ). The first part presents the main properties of this structure which combines the advantages of open-loop scheme (the controller is an approximate inverse of the model) and closed-loop structure (ability to cope with modelling errors and unmeasured disturbances). A comparison with the conventional closed-loop is briefly presented. In the second part, an asymptotic precision criterion is introduced; The conditions that are to be verified by the blocks of the I. M. C. , for zeroing the asymptotic error between the output and a polynomial input, are settled down. The controller is interpreted as an approximate inverse of the model. In discrete time, the use of F. I. R. (Finite Impulse Response) forms permits the synthesis of a stable and realisable controller. The third part deals with the problem of the model inversion in discrete time and in state space. It allows us to consider some vary linear or non-linear models, which are linear versus the control variable. The controller is decomposed in two parts: the first one generates the control variable in terms of model state and the reference objective, the second one generates the prediction of the reference signal. Asymptotic accuracy is guaranteed for reference inputs that are polynomial, with a given order, versus time. The last part presents the synthesis of an I. M. C. Based on the use of the above controller. The robustness filter becomes a predictor of the error between plant and model outputs, the dynamic of which is tuned according to the knowledge of the plant-model mismatch. Two approaches have been proposed to built in this filter. The first one uses the same technique as for the reference predictor. In the other, the usual notion of filtering is replaced by a measure of the prediction quality. ]
Poussevin, Mickael. "Apprentissage de représentation pour des données générées par des utilisateurs." Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066040/document.
Full textIn this thesis, we study how representation learning methods can be applied to user-generated data. Our contributions cover three different applications but share a common denominator: the extraction of relevant user representations. Our first application is the item recommendation task, where recommender systems build user and item profiles out of past ratings reflecting user preferences and item characteristics. Nowadays, textual information is often together with ratings available and we propose to use it to enrich the profiles extracted from the ratings. Our hope is to extract from the textual content shared opinions and preferences. The models we propose provide another opportunity: predicting the text a user would write on an item. Our second application is sentiment analysis and, in particular, polarity classification. Our idea is that recommender systems can be used for such a task. Recommender systems and traditional polarity classifiers operate on different time scales. We propose two hybridizations of these models: the former has better classification performance, the latter highlights a vocabulary of surprise in the texts of the reviews. The third and final application we consider is urban mobility. It takes place beyond the frontiers of the Internet, in the physical world. Using authentication logs of the subway users, logging the time and station at which users take the subway, we show that it is possible to extract robust temporal profiles
Poussevin, Mickael. "Apprentissage de représentation pour des données générées par des utilisateurs." Electronic Thesis or Diss., Paris 6, 2015. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2015PA066040.pdf.
Full textIn this thesis, we study how representation learning methods can be applied to user-generated data. Our contributions cover three different applications but share a common denominator: the extraction of relevant user representations. Our first application is the item recommendation task, where recommender systems build user and item profiles out of past ratings reflecting user preferences and item characteristics. Nowadays, textual information is often together with ratings available and we propose to use it to enrich the profiles extracted from the ratings. Our hope is to extract from the textual content shared opinions and preferences. The models we propose provide another opportunity: predicting the text a user would write on an item. Our second application is sentiment analysis and, in particular, polarity classification. Our idea is that recommender systems can be used for such a task. Recommender systems and traditional polarity classifiers operate on different time scales. We propose two hybridizations of these models: the former has better classification performance, the latter highlights a vocabulary of surprise in the texts of the reviews. The third and final application we consider is urban mobility. It takes place beyond the frontiers of the Internet, in the physical world. Using authentication logs of the subway users, logging the time and station at which users take the subway, we show that it is possible to extract robust temporal profiles
LERCH, CHRISTOPHE. "Une nouvelle représentation du contrôle organisationnel : le pilotage des processus." Université Louis Pasteur (Strasbourg) (1971-2008), 1998. http://www.theses.fr/1998STR1EC01.
Full textThe crisis of management instrumentation wich appeared in the 80's can be interpreted as a crisis of the representation modes of organization. Therfore this thesis offers some thoughts on the type of organization aimed at controlling, starting from a model based an activities. First, we use graphical representations in order to model the activities of organisations in applied cases. Our analysis identifies some limits the functional tools which are most frequently used. We then suggest some solutions by resorting to a cognitive representation of the activities. Secondly, we develop a typology which structures the diversity of the processes. We distinguish three categories : the structured process, the semi-structured process, the non structured process. Those configurations can in particular be differentiated by their strategies of environmental adaptation and their structure of management. The objective to provide a language so as to facilitate the diagnosis on the functioning of the processes. Our study resulted in devising a dashboard intended to drive the collective mechanisms of adaptation and knowledge creation. Our analysis emphasises both the parameters of control of these mechanisms and the impact of those parameters on the dynamic of the learning processes. Finally, managing the processes appears to be a way to mobilise the cognitive attention of the actors of the organisation. The point is especially important when the operators have to solve radically new problems of strategic importance for the organisation and thus need to explore new. Fields of knowledge. Conversely, managing the processes helps to save the cognitive resources of the organisation in situations where the members have to solve well-defined and well-known problems by exploiting available and explicit knowledge
Scherrer, Bruno. "Apprentissage de représentation et auto-organisation modulaire pour un agent autonome." Phd thesis, Université Henri Poincaré - Nancy I, 2003. http://tel.archives-ouvertes.fr/tel-00003377.
Full textNous avons considéré trois problèmes de complexité croissante et montré qu'ils admettaient des solutions algorithmiques connexionnistes : 1) L'apprentissage par renforcement dans un petit espace d'états : nous nous appuyons sur un algorithme de la littérature pour construire un réseau connexionniste ; les paramètres du problème sont stockés par les poids des unités et des connexions et le calcul du plan est le résultat d'une activité distribuée dans le réseau. 2) L'apprentissage d'une représentation pour approximer un problème d'apprentissage par renforcement ayant un grand espace d'états : nous automatisons le procédé consistant à construire une partition de l'espace d'états pour approximer un problème de grande taille. 3) L'auto-organisation en modules spécialisés pour approximer plusieurs problèmes d'apprentissage par renforcement ayant un grand espace d'états : nous proposons d'exploiter le principe "diviser pour régner" et montrons comment plusieurs tâches peuvent être réparties efficacement sur un petit nombre de modules fonctionnels spécialisés.
Delteil, Alexandre. "Représentation et apprentissage de concepts et d'ontologies pour le web sémantique." Nice, 2002. http://www.theses.fr/2002NICE5786.
Full textAldea, Emanuel. "Apprentissage de données structurées pour l'interprétation d'images." Paris, Télécom ParisTech, 2009. http://www.theses.fr/2009ENST0053.
Full textImage interpretation methods use primarily the visual features of low-level or high-level interest elements. However, spatial information concerning the relative positioning of these elements is equally beneficial, as it has been shown previously in segmentation and structure recognition. Fuzzy representations permit to assess at the same time the imprecision degree of a relation and the gradual transition between the satisfiability and the non-satisfiability of a relation. The objective of this work is to explore techniques of spatial information representation and their integration in the learning process, within the context of image classifiers that make use of graph kernels. We motivate our choice of labeled graphs for representing images, in the context of learning with SVM classifiers. Graph kernels have been studied intensively in computational chemistry and biology, but an adaptation for image related graphs is necessary, since image structures and properties of the information encoded in the labeling are fundamentally different. We illustrate the integration of spatial information within the graphical model by considering fuzzy adjacency measures between interest elements, and we define a family of graph representations determined by different thresholds applied to these spatial measures. Finally, we employ multiple kernel learning in order to build up classifiers that can take into account different graphical representations of the same image at once. Results show that spatial information complements the visual features of distinctive elements in images and that adapting the discriminative kernel functions for the fuzzy spatial representations is beneficial in terms of performance
Fusty-Raynaud, Sylvie. "Apprentissage et dysfonctionnement du langage écrit et représentation motrice de la parole." Paris 8, 2007. http://octaviana.fr/document/145514919#?c=0&m=0&s=0&cv=0.
Full textData about expert reader, reading learning and reading disabilities lead neither to a homogeneous definition of dyslexics nor a coherent methodology of remediation. This thesis aims to analyse reading learning difficulties in a new way. Rather than considering the good reader's behavior, we examine the constraints imposed and the resources required by alphabetic system. Rather than examine the dyslexic’s characteristics, we observe how the remediation is adapted to the subjects and influences them. The alphabetic system is based on grapheme / phoneme association. The phoneme is defined by articulatory more than acoustic features. Thus, reading is primarily based on speech-motor representation which actively connects visual and auditory representations. Learning disabilities remediation is based on oral realization, which is the active principle of each remediation program, as it enables readers to recognize speech gesture symbolised by graphemes. Thus it appears that the normal readers and not the dyslexics share a cognitive structure which corresponds to the alphabetic system mark, generating an audio-visuo-grapho-phonatory representation of speech
Ziat, Ali Yazid. "Apprentissage de représentation pour la prédiction et la classification de séries temporelles." Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066324/document.
Full textThis thesis deals with the development of time series analysis methods. Our contributions focus on two tasks: time series forecasting and classification. Our first contribution presents a method of prediction and completion of multivariate and relational time series. The aim is to be able to simultaneously predict the evolution of a group of time series connected to each other according to a graph, as well as to complete the missing values in these series (which may correspond for example to a failure of a sensor during a given time interval). We propose to use representation learning techniques to forecast the evolution of the series while completing the missing values and taking into account the relationships that may exist between them. Extensions of this model are proposed and described: first in the context of the prediction of heterogeneous time series and then in the case of the prediction of time series with an expressed uncertainty. A prediction model of spatio-temporal series is then proposed, in which the relations between the different series can be expressed more generally, and where these can be learned.Finally, we are interested in the classification of time series. A joint model of metric learning and time-series classification is proposed and an experimental comparison is conducted
Ziat, Ali Yazid. "Apprentissage de représentation pour la prédiction et la classification de séries temporelles." Electronic Thesis or Diss., Paris 6, 2017. http://www.theses.fr/2017PA066324.
Full textThis thesis deals with the development of time series analysis methods. Our contributions focus on two tasks: time series forecasting and classification. Our first contribution presents a method of prediction and completion of multivariate and relational time series. The aim is to be able to simultaneously predict the evolution of a group of time series connected to each other according to a graph, as well as to complete the missing values in these series (which may correspond for example to a failure of a sensor during a given time interval). We propose to use representation learning techniques to forecast the evolution of the series while completing the missing values and taking into account the relationships that may exist between them. Extensions of this model are proposed and described: first in the context of the prediction of heterogeneous time series and then in the case of the prediction of time series with an expressed uncertainty. A prediction model of spatio-temporal series is then proposed, in which the relations between the different series can be expressed more generally, and where these can be learned.Finally, we are interested in the classification of time series. A joint model of metric learning and time-series classification is proposed and an experimental comparison is conducted
Perez, Asher. "Développements diagrammatiques pour un plasma quantique dans la représentation de Feynman-Kac." Lyon 1, 1994. http://www.theses.fr/1994LYO10024.
Full textVidecoq, Etienne. "Problèmes inverses en diffusion thermique instationnaire : résolution par représentation d'état et apport de la réduction de modèle." Poitiers, 1999. http://www.theses.fr/1999POIT2355.
Full textPrudhomme, Elie. "Représentation et fouille de données volumineuses." Thesis, Lyon 2, 2009. http://www.theses.fr/2009LYO20048/document.
Full text/
Arneton, Mélissa. "Bilinguisme et apprentissage des mathématiques : études à la Martinique." Thesis, Nancy 2, 2010. http://www.theses.fr/2010NAN21009/document.
Full textIn this thesis, we try to explain why French overseas pupils have got, for many years, inferior performances to their mainland French school fellows at national academic evaluations. The most surprising is that the observed differences are stronger in mathematics than in French. Then, we focus on the cultural characteristics (bilingualism and collective beliefs) able to influence the school learning, in a French Overseas Department considered as a ?natural laboratory?: Martinique. We carry out four studies with two educational levels (in elementary school and first year of the secondary school). In the first study, we make side analysis of several years' national academic data. They acknowledge the observation as a reality and they invalidate two hypotheses, one to a specific difference in a particular field of mathematics (in geometry for example) and a second relative to an item differential functioning. In the second study, an experimental procedure allows 1) to measure social and cognitive bilingualism of Martinican pupils, 2) to evaluate with different procedures the children performances in mathematics and 3) to collect their scores at national evaluations. This second study refutes the hypothesis of the influence of bilingualism on academic learning. In the third study, we deal with the link between social beliefs (specifically the children?s beliefs of the school disciplines) and their performances. The results do not allow to conclude that the martinican children have worst beliefs of the mathematics than the French mainland children. In the last study, we compile data collected in the precedent analysis, in order to refute the bilingualism?s influence on the school learning. Finally, in the same time, we explain our observations and we submit considered perspectives relatives, for one part, to methodology and the instruments used in this research and, for the second part, to others cultural perspectives, which could be explore
Tremblay, Guillaume. "Optimisation d'ensembles de classifieurs non paramétriques avec apprentissage par représentation partielle de l'information." Mémoire, École de technologie supérieure, 2004. http://espace.etsmtl.ca/716/1/TREMBLAY_Guillaume.pdf.
Full textHay, Julien. "Apprentissage de la représentation du style écrit, application à la recommandation d’articles d’actualité." Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG010.
Full textUser modeling is an essential step when it comes to recommending products and offering services automatically. Social networks are a rich and abundant resource of user data (e.g. shared links, posted messages) that allow to model their interests and preferences. In this thesis, we propose to exploit news articles shared on social networks in order to enrich existing models with a new textual feature: the writing style. This thesis, at the intersection of the fields of natural language processing and recommender systems, focuses on the representation learning of writing style and its application to news recommendation. As a first step, we propose a new representation learning method that aims to project any document into a reference stylometric space. The hypothesis being tested is that such a space can be generalized by a sufficiently large set of reference authors, and that the vector projections of the writings of a "new" author will be stylistically close to the writings of a consistent subset of these reference authors. In a second step, we propose to exploit the stylometric representation for news recommendation by combining it with other representations (e.g. topical, lexical, semantic). We seek to identify the most relevant and complementary characteristics that can allow a more relevant and better quality recommendation of articles. The hypothesis that motivated this work is that the reading choices of individuals are not only influenced by the content (e.g. the theme of news articles, the entities mentioned), but also by the form (i.e. the style that can, for example, be descriptive, satirical, composed of personal anecdotes, interviews). The experiments conducted show that not only does writing style play a role in individuals' reading preferences, but also that, when combined with other textual features, it increases the accuracy and quality of recommendations in terms of diversity, novelty and serendipity
Chevaleyre, Yann. "Apprentissage de règles à partir de données multi-instances." Paris 6, 2001. http://www.theses.fr/2001PA066502.
Full textSoldano, Henry. "Apprentissage : Paradigmes, Structures et abstractions." Habilitation à diriger des recherches, Université Paris-Nord - Paris XIII, 2009. http://tel.archives-ouvertes.fr/tel-00514160.
Full textMuhlenbach, Fabrice. "Evaluation de la qualité de la représentation en fouille de données." Lyon 2, 2002. http://demeter.univ-lyon2.fr:8080/sdx/theses/lyon2/2002/muhlenbach_f.
Full textKnowledge discovery tries to produce novel and usable knowledge from the databases. In this whole process, data mining is the crucial machine learning step but we must asked some questions first: how can we have an a priori idea of the way of the labels of the class attribute are separable or not? How can we deal with databases where some examples are mislabeled? How can we transform continuous predictive attributes in discrete ones in a supervised way by taking into account the global information of the data ? We propose some responses to these problems. Our solutions take advantage of the properties of geometrical tools: the neighbourhood graphs. The neighbourhood between examples projected in a multidimensional space gives us a way of characterising the likeness between the examples to learn. We develop a statistical test based on the weight of edges that we must suppress from a neighbourhood graph for having only subgraphs of a unique class. This gives information about the a priori class separability. This work is carried on in the context of the detection of examples from a database that have doubtful labels: we propose a strategy for removing and relabeling these doubtful examples from the learning set to improve the quality of the resulting predictive model. These researches are extended in the special case of a continuous class to learn: we present a structure test to predict this kind of variable. Finally, we present a supervised polythetic discretization method based on the neighbourhood graphs and we show its performances by using it with a new supervised machine learning algorithm
Bouchard, Jacqueline. "Imagerie expérientielle, représentation de soi et éducation, la technologie au service de l'enseignement-apprentissage." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape3/PQDD_0015/MQ56393.pdf.
Full textBaere, Campos Neves José Alberto. "Contribution à la construction automatique de représentation 3D d'objets solides." Compiègne, 1989. http://www.theses.fr/1989COMPD171.
Full textGautheron, Léo. "Construction de Représentation de Données Adaptées dans le Cadre de Peu d'Exemples Étiquetés." Thesis, Lyon, 2020. http://www.theses.fr/2020LYSES044.
Full textMachine learning consists in the study and design of algorithms that build models able to handle non trivial tasks as well as or better than humans and hopefully at a lesser cost.These models are typically trained from a dataset where each example describes an instance of the same task and is represented by a set of characteristics and an expected outcome or label which we usually want to predict.An element required for the success of any machine learning algorithm is related to the quality of the set of characteristics describing the data, also referred as data representation or features.In supervised learning, the more the features describing the examples are correlated with the label, the more effective the model will be.There exist three main families of features: the ``observable'', the ``handcrafted'' and the ``latent'' features that are usually automatically learned from the training data.The contributions of this thesis fall into the scope of this last category. More precisely, we are interested in the specific setting of learning a discriminative representation when the number of data of interest is limited.A lack of data of interest can be found in different scenarios.First, we tackle the problem of imbalanced learning with a class of interest composed of a few examples by learning a metric that induces a new representation space where the learned models do not favor the majority examples.Second, we propose to handle a scenario with few available examples by learning at the same time a relevant data representation and a model that generalizes well through boosting models using kernels as base learners approximated by random Fourier features.Finally, to address the domain adaptation scenario where the target set contains no label while the source examples are acquired in different conditions, we propose to reduce the discrepancy between the two domains by keeping only the most similar features optimizing the solution of an optimal transport problem between the two domains
Zeng, Tieyong. "Études de Modèles Variationnels et Apprentissage de Dictionnaires." Phd thesis, Université Paris-Nord - Paris XIII, 2007. http://tel.archives-ouvertes.fr/tel-00178024.
Full textChampagne, Roger. "Simulation en temps réel à l'aide de la représentation d'état : application à un entraînement électrique basé sur une machine asynchrone." Mémoire, École de technologie supérieure, 2001. http://espace.etsmtl.ca/838/1/CHAMPAGNE_Roger.pdf.
Full textLienou, Marie Lauginie. "Apprentissage automatique des classes d'occupation du sol et représentation en mots visuels des images satellitaires." Phd thesis, Télécom ParisTech, 2009. http://pastel.archives-ouvertes.fr/pastel-00005585.
Full textLienou, Marie Lauginie. "Apprentissage automatique des classes d'occupation du sol et représentation en mots visuels des images satellitaires." Phd thesis, Paris, ENST, 2009. https://pastel.hal.science/pastel-00005585.
Full textLand cover recognition from automatic classifications is one of the important methodological researches in remote sensing. Besides, getting results corresponding to the user expectations requires approaching the classification from a semantic point of view. Within this frame, this work aims at the elaboration of automatic methods capable of learning classes defined by cartography experts, and of automatically annotating unknown images based on this classification. Using corine land cover maps, we first show that classical approaches in the state-of-the-art are able to well-identify homogeneous classes such as fields, but have difficulty in finding high-level semantic classes, also called mixed classes because they consist of various land cover categories. To detect such classes, we represent images into visual words, in order to use text analysis tools which showed their efficiency in the field of text mining. By means of supervised and not supervised approaches on one hand, we exploit the notion of semantic compositionality: image structures which are considered as mixtures of land cover types, are detected by bringing out the importance of spatial relations between the visual words. On the other hand, we propose a semantic annotation method using a statistical text analysis model: latent dirichlet allocation. We rely on this mixture model, which requires a bags-of-words representation of images, to properly model high-level semantic classes. The proposed approach and the comparative studies with gaussian and gmm models, as well as svm classifier, are assessed using spot and quickbird images among others
Gaujard, Chrystelle. "La représentation idéaltypique d'un nouveau repère organisationnel en formation : l'agencemen L." Littoral, 2008. http://www.theses.fr/2008DUNK0185.
Full textThis research focuses on the disclosure of a new organizational mark due to a favourable context. To this aim, we have first studied the organizational dynamic and then the method and the content in order to represent organizations. The coevolution offers a framework considering organizations, their populations and their environments as the interdependent outcomes of managerial actions, institutional influences and extra-institutional changes. This theory helps us to understand the evolution and the emergence of new organizational forms. Litterature has captured three different organizational idealtypes as three layout marks. In order to reveal this new idealtype the research methodology relies on an idealtype construction in a qualitative approach within start-ups. This research points out a playidealtype in construction which is promoting innovation and learning in the organization
Lienhardt, Denis. "Exploitation de la représentation d'état linéaire : modélisation et simulation des systèmes non-linéaires décrits par le langage des graphes à liens." Mulhouse, 1989. http://www.theses.fr/1989MULH0112.
Full textHe, Xiyan. "Sélection d'espaces de représentation pour la décision en environnement non-stationnaire : application à la segmentation d'images texturées." Troyes, 2009. http://www.theses.fr/2009TROY0027.
Full textThe objectif of this thesis is to improve or preserve the performance of a decision système in the presence of noise, loss of information or feature non-stationarity. The proposed method consists in first generating an ensemble of feature subspaces from the initial full-dimensional space, and then making the decision by usins only the subspaces which are supposed to be immune to the non-stationary disturbance (we call these subspaces as homogenous subspaces). Based on this idea, we propose three different approaches to make the system decision by using an ensemble of carefully constructed homogenous subspaces. The first approach uses an ensemble of NN classifiers, combined with a heuristic strategy targeting to select the so-called homogeneous feature subspaces among a large number of subspaces that are randomly generated from the initial space. The second approach follows the same principle; however, the geenration of the subspaces is no longer a random process, but is accomplished by using a modified and adaptive LASSO algorithm. Finally, in the third approach, the homogeneous feature subspace selection and the decision are realized by using one-class SVMs. The textured image segmentation constitutes an appropriate application for the evalution of the proposed approaches. The obtained experimental results demonstrate the effectiveness of the three decision systems that we have developed. Finally, it is worthwhile pointing out that all the work presented in this thesis is limited to the two-class classification problem
Lachiche, Nicolas. "De l'induction confirmatoire à la classification : contribution à l'apprentissage automatique." Nancy 1, 1997. http://docnum.univ-lorraine.fr/public/SCD_T_1997_0267_LACHICHE.pdf.
Full textConfirmatory generalisation consists in determining the most general laws confirmed by a set of observations. Confirmatory induction is based on the similarity assumption: unknown individuals behave like known individuals. We show that a circumscription of individuals is more appropriate to model this assumption than a circumscription of properties. Compared to existing approaches, the model we propose can produce more general clauses and avoids the production of unwanted generalisations. We specialise this model defined in first-order logic to attribute-value languages and show that it cornes down, in this case, to the calculation of prime implicates. Considering the problem of classification of objects from examples, we show that the minimal consistent and relevant rules are not, in general, confirmatory generalisations. We propose a new classification technique, called scope classification, which consists of building the set of examples from which a consistent and relevant rule can be built, so it is an instance-based approach of rule-based classification. We present several adaptations of the logical basements of the scope classification to better deal with real data. Scope classification is also extended to instances generalised into rules. The generalisation strategies we introduce, and especially the search of the neighbours, clearly differ from those of existing techniques. We show that, whereas hypotheses built by the scope classification and by the disjunctive version space differ, both techniques leads to the same classification. Though, in addition to a more efficient implementation, our original point of view allows us to propose sorne developments specifie to a rule-based approach. Our system obtains on average a better accuracy and a similar execution time to sorne of the most used instance-based or rule-based systems on an usual set of benchmarks
Renaud-Amsellem, Pascale. "Effets d’aides cognitives langagières sur quelques aspects de la représentation de soi et le processus d’autoévaluation." Caen, 2006. http://www.theses.fr/2006CAEN1465.
Full textDzogang, Fabon. "Représentation et apprentissage à partir de textes pour des informations émotionnelles et pour des informations dynamiques." Paris 6, 2013. http://www.theses.fr/2013PA066253.
Full textAutomatic knowledge extraction from texts consists in mapping lowlevel information, as carried by the words and phrases extracted fromdocuments, to higher level information. The choice of datarepresentation for describing documents is, thus, essential and thedefinition of a learning algorithm is subject to theirspecifics. This thesis addresses these two issues in the context ofemotional information on the one hand and dynamic information on theother. In the first part, we consider the task of emotion extraction forwhich the semantic gap is wider than it is with more traditionalthematic information. Therefore, we propose to study representationsaimed at modeling the many nuances of natural language used fordescribing emotional, hence subjective, information. Furthermore, wepropose to study the integration of semantic knowledge which provides,from a characterization perspective, support for extracting theemotional content of documents and, from a prediction perspective,assistance to the learning algorithm. In the second part, we study information dynamics: any corpus ofdocuments published over the Internet can be associated to sources inperpetual activity which exchange information in a continuousmovement. We explore three main lines of work: automaticallyidentified sources; the communities they form in a dynamic and verysparse description space; and the noteworthy themes they develop. Foreach we propose original extraction methods which we apply to a corpusof real data we have collected from information streams over the Internet
De, moura braga Elayne. "Enseignement apprentissage de la statistique, TICE et environnement numérique de travail : étude des effets de supports didactiques numériques, médiateurs dans la conceptualisation en statistique." Thesis, Lyon 2, 2009. http://www.theses.fr/2009LYO20021/document.
Full textDefining the Information and Communication Technologies for Education (TICE) as mediators in learning process, we carry out a research of the didactic support virtual “Quantitative Methods FORSE”, available to scholars students in Sciences of Education - Distance Learning (CNED) in order to propose complements to TICE in the way it becomes good mediators. Distance learning through TICE requires a new reading of education, practices and roles of the implied subjects (learning, contents, support, teacher). We show which are its roles, its advantages and its constraints, according to ergonomic analyses, observations of use, design questionnaires for gathering information from students and also analyses of their productions. Variables as attribution of causality, motivation and affective representations, sound suggested like essential points to complete the pedagogical-didactic triangle. These cognitive and emotional aspects are argued in this PhD thesis like rules of action for the learning of statistics concepts. Our hypothesis here is that a didactic support virtual can become a good mediator of conceptualization only if it holds the mentioned rules of action.According to our results, we observe that affective representations, attribution of causality and motivation influence significantly the learning of abstract concepts. By consequence, we propose that didactic support virtual can infer the affective state of users toward their performances and so, to be able to act in the direction to promote positive affective representations, which will bring back better conceptualizations from students
Chan, wai tim Stefen. "Apprentissage supervisé d’une représentation multi-couches à base de dictionnaires pour la classification d’images et de vidéos." Thesis, Université Grenoble Alpes (ComUE), 2016. http://www.theses.fr/2016GREAT089/document.
Full textIn the recent years, numerous works have been published on dictionary learning and sparse coding. They were initially used in image reconstruction and image restoration tasks. Recently, researches were interested in the use of dictionaries for classification tasks because of their capability to represent underlying patterns in images. Good results have been obtained in specific conditions: centered objects of interest, homogeneous sizes and points of view.However, without these constraints, the performances are dropping.In this thesis, we are interested in finding good dictionaries for classification.The learning methods classically used for dictionaries rely on unsupervised learning. Here, we are going to study how to perform supervised dictionary learning.In order to push the performances further, we introduce a multilayer architecture for dictionaries. The proposed architecture is based on the local description of an input image and its transformation thanks to a succession of encoding and processing steps. It outputs a vector of features effective for classification.The learning method we developed is based on the backpropagation algorithm which allows a joint learning of the different dictionaries and an optimization solely with respect to the classification cost.The proposed architecture has been tested on MNIST, CIFAR-10 and STL-10 datasets with good results compared to other dicitonary-based methods. The proposed architecture can be extended to video analysis
Auriol, Jean-Bernard. "Modélisation du sujet humain en situation de résolution de problème basée sur le couplage d'un formalisme logique et d'un formalisme d'opérateurs." Paris, ENST, 1999. http://www.theses.fr/1999ENST0049.
Full textLoutchmia, Dominique. "Une méthode d'analyse discriminante pour des concepts imprécis." Phd thesis, Université de la Réunion, 1998. http://tel.archives-ouvertes.fr/tel-00473292.
Full textGaudiello, Ilaria. "Learning robotics, with robotics, by robotics : a study on three paradigms of educational robotics, under the issues of robot representation, robot acceptance, and robot impact on learning." Thesis, Paris 8, 2015. http://www.theses.fr/2015PA080081.
Full textThrough a psychological perspective, the thesis concerns the three ER learning paradigms that are distinguished upon the different hardware, software, and correspondent modes of interaction allowed by the robot. Learning robotics was investigated under the issue of robot representation. By robot representation, we mean its ontological and pedagogical status and how such status change when users learn robotics. In order to answer this question, we carried out an experimental study based on pre- and post-inquiries, involving 79 participants. Learning with robotics was investigated under the issue of robot’s functional and social acceptance. Here, the underlying research questions were as follows: do students trust in robot’s functional and social savvy? Is trust in functional savvy a pre-requisite for trust in social savvy? Which individuals and contextual factors are more likely to influence this trust? In order to answer these questions, we have carried an experimental study with 56 participants and an iCub robot. Trust in the robot has been considered as a main indicator of acceptance in situations of perceptual and socio-cognitive uncertainty and was measured by participants’ conformation to answers given by iCub. Learning by robotics was investigated under the issue of robot’s impact on learning. The research questions were the following: to what extent the combined RBI & IBSE frame has a positive impact on cognitive, affective, social and meta-cognitive dimensions of learning? Does this combined educational frame improve both domain-specific and non-domain specific knowledge and competences of students? In order to answer these questions, we have carried a one-year RBI & IBSE experimental study in the frame of RObeeZ, a research made through the FP7 EU project Pri-Sci-Net. The longitudinal experiments involved 26 pupils and 2 teachers from a suburb parisian primary school
Courtine, Mélanie. "Changements de représentation pour la classification conceptuelle non supervisée de données complexes." Paris 6, 2002. http://www.theses.fr/2002PA066404.
Full textBel, Bernard. "Acquisition et représentation de connaissances en musique." Phd thesis, Aix-Marseille 3, 1990. http://tel.archives-ouvertes.fr/tel-00009692.
Full textBredèche, Nicolas. "Ancrage de lexique et perceptions : changements de représentation et apprentissage dans le contexte d'un agent situé et mobile." Paris 11, 2002. http://www.theses.fr/2002PA112225.
Full textIn Artificial Intelligence, the symbol grounding problem is considered as an important issue regarding the meaning of symbols used by an artificial agent. Our work is concerned with the grounding of symbols for a situated mobile robot that navigates through a real world environment. In this setting, the main problem the robot encounters is to ground symbols given by a human teacher that refers to physical entities (e. G. A door, a human, etc. ). Grounding such a lexicon is a difficult task because of the intrinsic nature of the environment: it is dynamic, complex and noisy. Moreover, one specific symbol (e. G. "door") may refer to different physical objects in size, shape or colour while the robot may acquire only a small number of examples for each symbol. Also, it is not possible to rely on ad-hoc physical models of symbols due to the great number of symbols that may be grounded. Thus, the problem is to define how to build a grounded representation in such a context. In order to address this problem, we have reformulated the symbol grounding problem as a supervised learning problem. We present an approach that relies on the use of abstraction operators. Thanks to these operators, information on granularity and structural configuration is extracted from the perceptions in order to case the building of an anchor. For each symbol, the appropriate definition for these operators is found out thanks to successive changes of representation that provide an efficient and adapted anchor. In order to implement our approach, we have developed PLIC and WMplic which are successfully used for long term symbol grounding by a PIONEER2 DX mobile robot in the corridors of the Computer Sciences Lab of the University of Paris 6
Lebatteux, Nicole. "Représentation sociale de l'entreprise et contexte scolaire en lycée professionnel tertiaire : obstacles et appuis pour un apprentissage citoyen." Aix-Marseille 1, 2005. http://www.theses.fr/2005AIX10100.
Full textJaillet, Simon. "Catégorisation automatique de documents textuels : D'une représentation basée sur les concepts aux motifs séquentiels." Montpellier 2, 2005. http://www.theses.fr/2005MON20030.
Full textMasset-Martin, Angélique. "Enquête sur la métalangue dans l'enseignement - apprentissage du FLE/S à des élèves non francophones scolarisés en France." Amiens, 2009. http://www.theses.fr/2009AMIE0002.
Full textThe study of metalanguage in classes of French as a Foreign or Second language relates to the intersection of two disciplines (linguistics and didactics) which are in interaction. We determined how and when metalanguage occurs in classes of French as a Foreign or Second language. What are its main characteristics? What do we learn on the metalinguistic vocabulary? We analysed a corpus obtained from observations in reception classes for students newly arrived in France. We present first the basic data in order to understand the context, the approach adopted and then the conclusions of this research. Then we focus on the metalinguistic discourse of teachers and students. Lastly, we review the metalinguistic vocabulary or vocabulary in a metalinguistic usage and put forward a classification. There is a switching backwards and forwards between specialised lexical items, associated with linguistics, and the words of everyday speech. The boundary is porous, according to how particular terms are used
Gaillard, Audrey. "Développement des représentations conceptuelles chez l'enfant : une approche transversale." Paris 8, 2011. http://www.theses.fr/2011PA083972.
Full textIn recent years, many studies in developmental psychology have focused on concept formation in children, i. E. Object categorization. This thesis aimed, first, to study the influence of several contextual factors (experimental instructions, number of repetitions, category membership) on representation stability studied with sorting task and property-generation production task with adult participants. In the second time, in order to study conceptual representations in children, we analyzed the categorical organization of various objects names and its temporal stability in children aged from 6 to 11 years old according to different factors: children's age, experimental tasks and category membership. The set of our results shows the influence of the task on temporal stability of representations, both in adults than in children. Therefore, it seems to be the type of task that induces variability, not the contextual factors tested (instructions, repetitions, category membership). In, children, our results show that stability representations depends on the age and the category membership of objects (natural objects or artifacts). We discuss results compared to theories of categorization and conceptual development