Tesis sobre el tema "Apprentissage de représentation des états"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores tesis para su investigación sobre el tema "Apprentissage de représentation des états".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
Castanet, Nicolas. "Automatic state representation and goal selection in unsupervised reinforcement learning". Electronic Thesis or Diss., Sorbonne université, 2025. http://www.theses.fr/2025SORUS005.
Texto completoIn the past few years, Reinforcement Learning (RL) achieved tremendous success by training specialized agents owning the ability to drastically exceed human performance in complex games like Chess or Go, or in robotics applications. These agents often lack versatility, requiring human engineering to design their behavior for specific tasks with predefined reward signal, limiting their ability to handle new circumstances. This agent's specialization results in poor generalization capabilities, which make them vulnerable to small variations of external factors and adversarial attacks. A long term objective in artificial intelligence research is to move beyond today's specialized RL agents toward more generalist systems endowed with the capability to adapt in real time to unpredictable external factors and to new downstream tasks. This work aims in this direction, tackling unsupervised reinforcement learning problems, a framework where agents are not provided with external rewards, and thus must autonomously learn new tasks throughout their lifespan, guided by intrinsic motivations. The concept of intrinsic motivation arise from our understanding of humans ability to exhibit certain self-sufficient behaviors during their development, such as playing or having curiosity. This ability allows individuals to design and solve their own tasks, and to build inner physical and social representations of their environments, acquiring an open-ended set of skills throughout their lifespan as a result. This thesis is part of the research effort to incorporate these essential features in artificial agents, leveraging goal-conditioned reinforcement learning to design agents able to discover and master every feasible goals in complex environments. In our first contribution, we investigate autonomous intrinsic goal setting, as a versatile agent should be able to determine its own goals and the order in which to learn these goals to enhance its performances. By leveraging a learned model of the agent's current goal reaching abilities, we show that we can shape an optimal difficulty goal distribution, enabling to sample goals in the Zone of Proximal Development (ZPD) of the agent, which is a psychological concept referring to the frontier between what a learner knows and what it does not, constituting the space of knowledge that is not mastered yet but have the potential to be acquired. We demonstrate that targeting the ZPD of the agent's result in a significant increase in performance for a great variety of goal-reaching tasks. Another core competence is to extract a relevant representation of what matters in the environment from observations coming from any available sensors. We address this question in our second contribution, by highlighting the difficulty to learn a correct representation of the environment in an online setting, where the agent acquires knowledge incrementally as it make progresses. In this context, recent achieved goals are outliers, as there are very few occurrences of this new skill in the agent's experiences, making their representations brittle. We leverage the adversarial setting of Distributionally Robust Optimization in order for the agent's representations of such outliers to be reliable. We show that our method leads to a virtuous circle, as learning accurate representations for new goals fosters the exploration of the environment
Bigot, Damien. "Représentation et apprentissage de préférences". Thesis, Toulouse 3, 2015. http://www.theses.fr/2015TOU30031/document.
Texto completo--
Tomasini, Linda. "Apprentissage d'une représentation statistique et topologique d'un environnement". Toulouse, ENSAE, 1993. http://www.theses.fr/1993ESAE0024.
Texto completoChabiron, Olivier. "Apprentissage d'arbres de convolutions pour la représentation parcimonieuse". Thesis, Toulouse 3, 2015. http://www.theses.fr/2015TOU30213/document.
Texto completoThe 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
Mandil, Guillaume. "Modèle de représentation géométrique intégrant les états physiques du produit". Phd thesis, Ecole Centrale Paris, 2011. http://tel.archives-ouvertes.fr/tel-00714559.
Texto completoPhilogène, Gina. "De "Black" à "African american" : l'élaboration d'une nouvelle représentation sociale". Paris, EHESS, 1997. http://www.theses.fr/1996EHES0019.
Texto completoHautot, Julien. "Représentation à base radiale pour l'apprentissage par renforcement visuel". Electronic Thesis or Diss., Université Clermont Auvergne (2021-...), 2024. http://www.theses.fr/2024UCFA0093.
Texto completoThis thesis work falls within the context of Reinforcement Learning (RL) from image data. Unlike supervised learning, which enables performing various tasks such as classification, regression, or segmentation from an annotated database, RL allows learning without a database through interactions with an environment. In these methods, an agent, such as a robot, performs different actions to explore its environment and gather training data. Training such an agent involves trial and error; the agent is penalized when it fails at its task and rewarded when it succeeds. The goal for the agent is to improve its behavior to obtain the most long-term rewards.We focus on visual extractions in RL scenarios using first-person view images. The use of visual data often involves deep convolutional networks that work directly on images. However, these networks have significant computational complexity, lack interpretability, and sometimes suffer from instability. To overcome these difficulties, we investigated the development of a network based on radial basis functions, which enable sparse and localized activations in the input space. Radial basis function networks (RBFNs) peaked in the 1990s but were later supplanted by convolutional networks due to their high computational cost on images. In this thesis, we developed a visual feature extractor inspired by RBFNs, simplifying the computational cost on images. We used our network for solving first-person visual tasks and compared its results with various state-of-the-art methods, including end-to-end learning methods, state representation learning methods, and extreme machine learning methods. Different scenarios were tested from the VizDoom simulator and the Pybullet robotics physics simulator. In addition to comparing the rewards obtained after learning, we conducted various tests on noise robustness, parameter generation of our network, and task transfer to reality.The proposed network achieves the best performance in reinforcement learning on the tested scenarios while being easier to use and interpret. Additionally, our network is robust to various noise types, paving the way for the effective transfer of knowledge acquired in simulation to reality
Poussevin, Mickael. "Apprentissage de représentation pour des données générées par des utilisateurs". Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066040/document.
Texto completoIn 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.
Texto completoIn 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
Ben-Fares, Maha. "Apprentissage de représentation non supervisé de flux de données textuelles". Electronic Thesis or Diss., CY Cergy Paris Université, 2024. http://www.theses.fr/2024CYUN1316.
Texto completoThis thesis presents an innovative methods for clustering text data streams and also introduces a system for identifying AI-generated text. This AI detection method can be used independently or as a preprocessing step to filter incoming documents, by removing AI-generated content, preserving the authenticity and validity of the information.Specifically, we develop a classification system that distinguishes between human-written and AI-generated text. This method employs a hierarchical fusion strategy that integrates representations from various layers of the BERT model. By focusing on syntactic features, our model classifies each token as either Human or AI, effectively capturing detailed text structures and ensuring robust performance across multiple languages using the XLM-RoBERTa-Large model.In the field of data stream clustering, particularly for textual data, we first introduce a method called OTTC (Online Topological Text Clustering). This approach leverages topological representation learning in combination with online clustering techniques. It effectively addresses the challenges in clustering textual data streams, such as data dynamism, sparsity, and the curse of dimensionality, which are issues that traditional clustering methods often struggle to manage.To further improve clustering results and address the limitations of OTTC, we propose the MVTStream algorithm, specifically designed for multi-view text data streams. This algorithm operates in three stages: First, it generates diverse text representations of incoming data, treating each representation as a separate view. Then, it employs micro-cluster data structures for real-time processing. Finally, it utilizes ensemble methods to aggregate clusters from the various views and get the final clusters
LERCH, CHRISTOPHE. "Une nouvelle représentation du contrôle organisationnel : le pilotage des processus". Université Louis Pasteur (Strasbourg) (1971-2008), 1998. http://www.theses.fr/1998STR1EC01.
Texto completoThe 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
Kermorvant, Christopher. "Apprentissage de modèles à états finis stochastiques pour les séquences". Saint-Etienne, 2003. http://www.theses.fr/2003STET4002.
Texto completoThis thesis deals with learning stochastic finite state automata for sequence modelling. We aimed at developing both their structural and probabilistic aspects, through the extension of the models and the design of new learning algorithms. On the one hand, we have developed statistical aspects of stochastic finite state automaton learning algorithms in order to deal with practical cases. We have designed a new learning algorithm based on statistical tests for sample comparison. This framework allows to take into account the size of the learning set in the inference process. On the other hand, we have developed syntactic aspects of finite state automaton and their ability to model the underlying structure of sequences. We have defined typed automata, an extension of classical finite state automata, which permits the introduction of a priori knowledge in the models. From a theoretical point of view, we have studied the search space for the typed automata. We have proposed a modified version of classical automata learning algorithms in the framework of typed automata. Finally, we have applied these models and algorithms to a language modelling task. The obtained automata were competitive with state of the art models on a classical corpus
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.
Texto completoNous 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.
Texto completoLacoue-Labarthe, Mathieu. "La représentation des Indiens dans le western américain, des années 1930 à nos jours". Paris 8, 2009. http://www.theses.fr/2009PA083144.
Texto completoThe study of a sample of 600 American western movies realized between 1930 and 2005 shows the evolution of the Native Americans' portrayal. Till the mid-50s, he is mostly absent and almost always depicted in a negative way. These prejudices are due to the roots of the western movie, inspired by different literary and artistic forms used between the XVIIth and the beginning of the XXth century. From 1945 on, the way Native Americans are shown becomes more positive because of the consequences of World War II. Nevertheless, it's not before the mid-50s that we can see a deep change in the way they are treated on the screen. Sometimes the bloodthirsty savage becomes the noble red man, but all the stereotypes, positive or negative, about the Indians are questioned in some movies. This new image of the Native American is due to the success of the civil rights movement and to the protest against productivism, consumerism, and the Vietnam war ; it is also due to the growing care for environment, the change and the new blood injected into the American society
Goualle, Laurent. "Le drame judiciaire ou la représentation du procès dans le cinéma américain". Paris 3, 2001. http://www.theses.fr/2001PA030049.
Texto completoLetort, Delphine. "Du film noir au néo-noir : mythes et stéréotypes en représentation : (1941-2001)". Rennes 2, 2002. http://www.theses.fr/2002REN20020.
Texto completoClassical Hollywood narratives are characterized by a set of conventions which film noir shattered as it emerged in the 1940s. Not only did the newly born genre disrespect the realist effect that ruled representation in classical films while playing upon mise en scene, but it also proved quite subversive as far as content is concerned. It relied on a series of stereotypes (the femme is fatale while the hero is hardboiled) that need to be recognized and analyzed in order to understand why film noir was closely watched by censorship. No doubt the political power of film noir was enhanced by its narrative structure and its mode of representation, implicitly referring to mythological narratives and figures, which the film industry also endowed with a commercial purpose. Film noir plays on the expressionist quality of black and white in order to express the ambiguity of desires leading individuals to the margins of crime, thus emphasizing that instabilities of gender were already incipient in the forties. Violence has pervaded the genre while laying stress on the urban crisis and expressing the psychological conflicts undermining the individual's sense of identity. The study of crime and violence in film noir and neo-film noir allows us to understand how modernity and postmodernity have affected the relationship of the individual to his environment and to himself. Film noir echoes the troubles caused by the transformation of society into a modern world whereas neo-film reflects the social and identity crisis triggered by a postmodern state and a new cultural and economic order. Postmodern aesthetics questions the rules of cinematic representation while deconstructing the genre, thus demystifying the American set of values vulgarized by Hollywood films and cinema itself
Gonzalez, Eric. ""Signifyin(g) jazzmen" : statut et représentation du musicien de jazz afro-américain des années 1920 à nos jours". Bordeaux 3, 1997. http://www.theses.fr/1997BOR30061.
Texto completoAfro-american jazz musicians stand at the intersection of primitivism and modernity. Originally regarded as entertainers, jazzmen have claimed and gained the status of artists in an ideological battle over the ownership and the blackness of jazz. In the black community, jazz musicians are regarded and depicted as spokesmen whose articulateness enables them to interpret and translate musically the black experience. The mediational function of afro-american jazzmen between the dominant society and the black minority is also studied in order to bring out the interactions of their aesthetic praxis and their political and social involvement, as well as their mythical dimension. The achievements of black jazz musicians and the obstacles they have had to overcome exemplify the necessity and the difficulties for afro-americans to assert their difference in an economic, political, social and cultural context where they remain a minority
Boyer, Laurent. "Apprentissage probabiliste de similarités d'édition". Phd thesis, Université Jean Monnet - Saint-Etienne, 2011. http://tel.archives-ouvertes.fr/tel-00718835.
Texto completoFusty-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.
Texto completoData 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.
Texto completoThis 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.
Texto completoThis 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
Aldea, Emanuel. "Apprentissage de données structurées pour l'interprétation d'images". Paris, Télécom ParisTech, 2009. http://www.theses.fr/2009ENST0053.
Texto completoImage 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
Prudhomme, Elie. "Représentation et fouille de données volumineuses". Thesis, Lyon 2, 2009. http://www.theses.fr/2009LYO20048/document.
Texto completo/
Sarreau, Jérôme. "Le sublime et la représentation photographique de l'ouest américain au XIXè siècle [(1840-1912)]". Pau, 2008. http://www.theses.fr/2008PAUU1013.
Texto completoDuring the 19th century, the territory occupied by the United States was significantly enlarged. The Western part of the American continent was progressively populated and industrialized. While towns and factories were built, the place of nature inexorably decreased. At that time, some photographers left for the West in order to represent the landscapes which were still in their pristine condition but also the technological wonders which were invading this area. Their undertaking shows the ambivalent attitude of 19th century Americans, who were both dazed by the beauty of the wilderness and lured by technical progress. It is thus significant that they considered as sublime not only the wild landscapes created by God but also the works of the engineers. We can really speak about a transfer of values during the century. Nature, which had been a pillar in the building of a genuine national identity, was associated with the sublime straightaway, but later, its characteristics were transferred to Man and the idea of sublime was then associated with the machines. A new form of sublime appeared in America : the technological sublime. This study analyzes the part played by photographers in this evolution, which could be seen as a popularization of the sublime, thus put within the reach of every American citizen. The corpus consists mainly of photographs taken by William Henry Jackson and Carleton E. Watkins. The analysis of these pictures emphasizes the typical characteristics of the sublime. These photographs represent all the aspects of the American West in the second half of the 19th century : the wilderness as well as the Indian tribes and the industrialization of the region
Cislaru, Georgeta. "Étude sémantique et discursive du nom de pays dans la presse française avec référence à l'anglais, au roumain et au russe". Paris 3, 2005. http://www.theses.fr/2005PA030106.
Texto completoThe present research aims at elaborating the linguistic category of country-names as a specific unit of the proper name class; a semantic and discursive approach is proposed. The contextualized analysis of country-name use in French newspapers points out the semantic and referential complexity of these appellative items, a complexity determined by the nature of their reference domain. It appears that any country-name contains two referential potentialities, place (in France) and institution (Liberia calls). The same complexity is revealed by country-name behaviour in English, Romanian and Russian newspapers' discourse. It appears that both place and collective-institutional aspects reflect social and cultural representations of the reference domain, produced by discourse. Due to their representational charge, the two referential potentialities enable a systematised dynamics of meaning construction
Dossou, Aristide. "La représentation politique des minorités historiquement défavorisées comme une exigence du droit d'être traité avec respect égal : le cas de la minorité afro-américaine". Paris 1, 2010. http://www.theses.fr/2010PA010570.
Texto completoArneton, Mélissa. "Bilinguisme et apprentissage des mathématiques : études à la Martinique". Thesis, Nancy 2, 2010. http://www.theses.fr/2010NAN21009/document.
Texto completoIn 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.
Texto completoHay, 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.
Texto completoUser 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.
Texto completoSim, Gérald. "La représentation diplomatique et consulaire française aux États-Unis (1815-1904) : réseaux, acteurs, pratiques, regards". Thesis, Nantes, 2017. http://www.theses.fr/2017NANT2015.
Texto completoThe study of the French diplomatic and consular presence in the United States is a mirror of the ambitions and the limits of the French diplomacy in North America during the 19th century. This research draws up an overall picture of the French diplomatic network through its actors. As mainstays of foreign politics, diplomats and consuls supported and influenced the political decisions made in Paris. Following the end of the Atlantic revolutions, the diplomatic network organized itself in a commercial logic way. During the whole century, this axis of the French diplomacy is deeply intertwined with a geopolitical logic way. The latter oscillated between two ways: bringing France and the United States together in order to limit the British commercial and maritime hegemony in the Atlantic area ; and coming to an agreement with London to thwart the American territorial expansion towards the West. As actors and witnesses of the political recombining which affects North America, diplomats are the relays of a policy aiming at restoring a French influence in this part of the New World, with no regard for the Monroe doctrine. The failures of the French diplomacy and the advent of the United States as the imperial power made the Quai d’Orsay readjust its policy. Implicitly recognizing the principles of the Monroe doctrine, the diplomatic actors are to support the creation of a French-American official memory reviving the fight shared for the cause of freedom during the War of Independence. This will to create memory took part in the building of the myth of La Fayette as a hero of the two worlds. This myth was in fact being used as window dressing on reality of the bilateral relations of the 19th century marked by the assertion of two political messianisms on both sides of the Atlantic
Soldano, Henry. "Apprentissage : Paradigmes, Structures et abstractions". Habilitation à diriger des recherches, Université Paris-Nord - Paris XIII, 2009. http://tel.archives-ouvertes.fr/tel-00514160.
Texto completoMuhlenbach, 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.
Texto completoKnowledge 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.
Texto completoBallion, Frédérique. "La représentation de l'ennemi dans le cinéma étasunien : de l'après guerre à la chute du mur de Berlin". Thesis, Bordeaux, 2014. http://www.theses.fr/2014BORD0073/document.
Texto completoIn order to study the various representations of the enemy conveyed during the ColdWar, we preferred to adopt a crossed-analysis of both the political andcinematographic discourses. The concept of enemy, which was inherent to theforeign policy at that time, took part in the process of legitimization of the actionscarried out by the American government. Its cinematographic representationscontribute to this process, cinema becoming a medium of diffusion of therepresentations of the enemy. However, it can also be the place where society'sinterrogations crystallize, thus attacking the dominant political discourse. Thecinematographic discourse can be comprehended at the same time as an ideologicalweapon, part of the designating and of the demonizing of the enemy, but also, in thetroubled context of the sixties and the seventies, as a contestation tool, saying a lotabout the social tensions
Ammar, Abdallah. "Représentation des états du continuum par des gaussiennes complexes : application aux processus d’ionisation atomiques et moléculaires". Electronic Thesis or Diss., Université de Lorraine, 2020. http://www.theses.fr/2020LORR0173.
Texto completoThis theoretical work lies at the border between molecular physics and quantum chemistry. It deals with a methodological and numerical development whose scope is to represent continuum wavefunctions by complex Gaussians. The ultimate goal is to apply these optimized Gaussians in the description of ionization processes involving molecules, where the multicenter integrals required to evaluate cross sections would be calculated analytically. For that purpose, we have developed an efficient numerical code to fit a set of arbitrary functions over finite radial distances, with either real or complex Gaussians. We have demonstrated the superiority of complex over real Gaussians in the representation of oscillating functions such as Coulomb functions or generalized Sturmian functions of positive energy. We have first validated the proposed approach to describe the ionization of the hydrogen atom by electron impact (in the first Born approximation) or photon impact (in the dipolar approximation). We have then applied the optimized complex Gaussians to describe molecular photoionization in a one-center approach. The results confirm the reliability of complex Gaussians in this kind of applications. Finally, we have considered the possibility of extending the approach to multicenter gaussian wavefunctions for the initial state. Similarly to the one-center case, we have shown that the multicenter integrals appearing in transition matrix elements can be performed analytically, also in the case of complex Gaussians
Baere, Campos Neves José Alberto. "Contribution à la construction automatique de représentation 3D d'objets solides". Compiègne, 1989. http://www.theses.fr/1989COMPD171.
Texto completoGautheron, Léo. "Construction de Représentation de Données Adaptées dans le Cadre de Peu d'Exemples Étiquetés". Thesis, Lyon, 2020. http://www.theses.fr/2020LYSES044.
Texto completoMachine 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.
Texto completoLienou, 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.
Texto completoLand 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
Lienou, 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.
Texto completoChristoffel, Quentin. "Apprentissage de représentation différenciées dans des modèles d’apprentissage profond : détection de classes inconnues et interprétabilité". Electronic Thesis or Diss., Strasbourg, 2024. http://www.theses.fr/2024STRAD027.
Texto completoDeep learning, and particularly convolutional neural networks, has revolutionized numerous fields such as computer vision. However, these models remain limited when encountering data from unknown classes (never seen during training) and often suffer from a lack of interpretability. We proposed a method aimed at directly optimizing the representation space learned by the model. Each dimension of the representation is associated with a known class. A dimension is activated with a specific value when the model faces the associated class, meaning that certain features have been detected in the image. This allows the model to detect unknown data by their distinct representation from known data, as they should not share the same features. Our approach also promotes semantic relationships within the representation space by allocating a subspace to each known class. Moreover, a degree of interpretability is achieved by analysing the activated dimensions for a given image, enabling an understanding of which features of which class are detected. This thesis details the development and evaluation of our method across multiple iterations, each aimed at improving performance and addressing identified limitations through interpretability, such as the correlation of extracted features. The results obtained on an unknown class detection benchmark show a notable improvement in performance between our versions, although they remain below the state-of-the-art
Vandermeulen, Eric. "La Machine Séquentielle Interprétée : un modèle à états pour la représentation discrète et la vérification de systèmes". Montpellier 2, 1996. http://www.theses.fr/1996MON20070.
Texto completoGaujard, Chrystelle. "La représentation idéaltypique d'un nouveau repère organisationnel en formation : l'agencemen L". Littoral, 2008. http://www.theses.fr/2008DUNK0185.
Texto completoThis 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
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.
Texto completoConfirmatory 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
He, 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.
Texto completoThe 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
Kozlova, Olga. "Apprentissage par renforcement hiérarchique et factorisé". Phd thesis, Université Pierre et Marie Curie - Paris VI, 2010. http://tel.archives-ouvertes.fr/tel-00632968.
Texto completoRenaud-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.
Texto completoDzogang, 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.
Texto completoAutomatic 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