Rozprawy doktorskie na temat „Apprentissage par représentation”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych rozpraw doktorskich naukowych na temat „Apprentissage par représentation”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj rozprawy doktorskie z różnych dziedzin i twórz odpowiednie bibliografie.
Poussevin, Mickael. "Apprentissage de représentation pour des données générées par des utilisateurs". Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066040/document.
Pełny tekst źródłaIn 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.
Pełny tekst źródłaIn 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
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.
Pełny tekst źródłaScherrer, 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.
Pełny tekst źródłaNous 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.
Filippi, Sarah. "Stratégies optimistes en apprentissage par renforcement". Phd thesis, Ecole nationale supérieure des telecommunications - ENST, 2010. http://tel.archives-ouvertes.fr/tel-00551401.
Pełny tekst źródłaPingand, Philippe. "Etude d'un environnement permettant l'acquisition de connaissance par apprentissage : application à l'analyse structurelle des protéines". Montpellier 2, 1990. http://www.theses.fr/1990MON20028.
Pełny tekst źródłaRobbes, Bruno. "Du mythe de l'autorité naturelle à l'autorité éducative de l'enseignant : des savoirs à construire entre représentation et action". Paris 10, 2007. http://www.theses.fr/2007PA100049.
Pełny tekst źródłaThe paradigm of educative authority dealt with in this thesis is trying to reanalyse a question which teachers come up against : how can they use their authority ? Agreeing about a new definition of educative authority, based on its socio-psychogenesis and its etymology, is essential. Clinic interviews led to clear up unconscious meanings of authority, according to personal stories. Clarifying interviews enabled to reveal acting knowledge used by the very same teachers when practising authority in specified situations. Verbal interventions are overshadowing in the transmission of messages, but knowledge linked to the body often turns to be more efficient. Eventually, links are being created between the aware meaning of actions and some of their unconscious significances. Thus, teachers’ authority is not “natural” but it is the result of a construction of knowledge within action
Mountassir, Mahjoub El. "Surveillance d'intégrité des structures par apprentissage statistique : application aux structures tubulaires". Electronic Thesis or Diss., Université de Lorraine, 2019. http://docnum.univ-lorraine.fr/ulprive/DDOC_T_2019_0047_EL_MOUNTASSIR.pdf.
Pełny tekst źródłaTo ensure better working conditions of civil and engineering structures, inspections must be made on a regular basis. However, these inspections could be labor-intensive and cost-consuming. In this context, structural health monitoring (SHM) systems using permanently attached transducers were proposed to ensure continuous damage diagnostic of these structures. In SHM, damage detection is generally based on comparison between the healthy state signals and the current signals. Nevertheless, the environmental and operational conditions will have an effect on the healthy state signals. If these effects are not taken into account they would result in false indication of damage (false alarm). In this thesis, classical machine learning methods used for damage detection have been applied in the case of pipelines. The effects of some measurements parameters on the robustness of these methods have been investigated. Afterthat, two approaches were proposed for damage diagnostic depending on the database of reference signals. If this database contains large variation of these EOCs, a sparse estimation of the current signal is calculated. Then, the estimation error is used as an indication of the presence of damage. Otherwise, if this database is acquired at limited range of EOCs, moving window PCA can be applied to update the model of the healthy state provided that the EOCs show slow and continuous variation. In both approaches, damage localization was ensured using a sliding window over the damaged pipe signal
Gaudiello, 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.
Pełny tekst źródłaThrough 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
Magnan, Jean-Christophe. "Représentations graphiques de fonctions et processus décisionnels Markoviens factorisés". Thesis, Paris 6, 2016. http://www.theses.fr/2016PA066042/document.
Pełny tekst źródłaIn decision theoretic planning, the factored framework (Factored Markovian Decision Process, FMDP) has produced several efficient algorithms in order to resolve large sequential decision making under uncertainty problems. The efficiency of this algorithms relies on data structures such as decision trees or algebraïc decision diagrams (ADDs). These planification technics are exploited in Reinforcement Learning by the architecture SDyna in order to resolve large and unknown problems. However, state-of-the-art learning and planning algorithms used in SDyna require the problem to be specified uniquely using binary variables and/or to use improvable data structure in term of compactness. In this book, we present our research works that seek to elaborate and to use a new data structure more efficient and less restrictive, and to integrate it in a new instance of the SDyna architecture. In a first part, we present the state-of-the-art modeling tools used in the algorithms that tackle large sequential decision making under uncertainty problems. We detail the modeling using decision trees and ADDs. Then we introduce the Ordered and Reduced Graphical Representation of Function, a new data structure that we propose in this thesis to deal with the various problems concerning the ADDs. We demonstrate that ORGRFs improve on ADDs to model large problems. In a second part, we go over the resolution of large sequential decision under uncertainty problems using Dynamic Programming. After the introduction of the main algorithms, we see in details the factored alternative. We indicate the improvable points of these factored versions. We describe our new algorithm that improve on these points and exploit the ORGRFs previously introduced. In a last part, we speak about the use of FMDPs in Reinforcement Learning. Then we introduce a new algorithm to learn the new datastrcture we propose. Thanks to this new algorithm, a new instance of the SDyna architecture is proposed, based on the ORGRFs : the SPIMDDI instance. We test its efficiency on several standard problems from the litterature. Finally, we present some works around this new instance. We detail a new algorithm for efficient exploration-exploitation compromise management, aiming to simplify F-RMax. Then we speak about an application of SPIMDDI to the managements of units in a strategic real time video game
Barbano, Carlo Alberto Maria. "Collateral-Free Learning of Deep Representations : From Natural Images to Biomedical Applications". Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAT038.
Pełny tekst źródłaDeep Learning (DL) has become one of the predominant tools for solving a variety of tasks, often with superior performance compared to previous state-of-the-art methods. DL models are often able to learn meaningful and abstract representations of the underlying data. However, it has been shown that they might also learn additional features, which are not necessarily relevant or required for the desired task. This could pose a number of issues, as this additional information can contain bias, noise, or sensitive information, that should not be taken into account (e.g. gender, race, age, etc.) by the model. We refer to this information as collateral. The presence of collateral information translates into practical issues when deploying DL-based pipelines, especially if they involve private users' data. Learning robust representations that are free of collateral information can be highly relevant for a variety of fields and applications, like medical applications and decision support systems.In this thesis, we introduce the concept of Collateral Learning, which refers to all those instances in which a model learns more information than intended. The aim of Collateral Learning is to bridge the gap between different fields in DL, such as robustness, debiasing, generalization in medical imaging, and privacy preservation. We propose different methods for achieving robust representations free of collateral information. Some of our contributions are based on regularization techniques, while others are represented by novel loss functions.In the first part of the thesis, we lay the foundations of our work, by developing techniques for robust representation learning on natural images. We focus on one of the most important instances of Collateral Learning, namely biased data. Specifically, we focus on Contrastive Learning (CL), and we propose a unified metric learning framework that allows us to both easily analyze existing loss functions, and derive novel ones. Here, we propose a novel supervised contrastive loss function, ε-SupInfoNCE, and two debiasing regularization techniques, EnD and FairKL, that achieve state-of-the-art performance on a number of standard vision classification and debiasing benchmarks.In the second part of the thesis, we focus on Collateral Learning in medical imaging, specifically on neuroimaging and chest X-ray images. For neuroimaging, we present a novel contrastive learning approach for brain age estimation. Our approach achieves state-of-the-art results on the OpenBHB dataset for age regression and shows increased robustness to the site effect. We also leverage this method to detect unhealthy brain aging patterns, showing promising results in the classification of brain conditions such as Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD). For chest X-ray images (CXR), we will target Covid-19 classification, showing how Collateral Learning can effectively hinder the reliability of such models. To tackle such issue, we propose a transfer learning approach that, combined with our regularization techniques, shows promising results on an original multi-site CXRs dataset.Finally, we provide some hints about Collateral Learning and privacy preservation in DL models. We show that some of our proposed methods can be effective in preventing certain information from being learned by the model, thus avoiding potential data leakage
Bourget, Annick. "De la formation préclinique à la formation clinique : explicitation du développement du raisonnement clinique chez des étudiantes et des étudiants en médecine ayant suivi un programme basé sur l'apprentissage par problèmes". Thèse, Université de Sherbrooke, 2013. http://hdl.handle.net/11143/6383.
Pełny tekst źródłaGaudiello, 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". Electronic Thesis or Diss., Paris 8, 2015. http://www.theses.fr/2015PA080081.
Pełny tekst źródłaThrough 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
Wynen, Daan. "Une représentation archétypale de style artistique : résumer et manipuler des stylesartistiques d'une façon interprétable". Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM066.
Pełny tekst źródłaIn this thesis we study the representations used to describe and manipulate artistic style of visual arts.In the neural style transfer literature and related strains of research, different representations have been proposed, but in recent years the by far dominant representations of artistic style in the computer vision community have been those learned by deep neural networks, trained on natural images.We build on these representations with the dual goal of summarizing the artistic styles present in large collections of digitized artworks, as well as manipulating the styles of images both natural and artistic.To this end, we propose a concise and intuitive representation based on archetypal analysis, a classic unsupervised learning method with properties that make it especially suitable for the task. We demonstrate how this archetypal representation of style can be used to discover and describe, in an interpretable way, which styles are present in a large collection.This enables the exploration of styles present in a collection from different angles; different ways of visualizing the information allow for different questions to be asked.These can be about a style that was identified across artworks, about the style of a particular artwork, or more broadly about how the styles that were identified relate to one another.We apply our analysis to a collection of artworks obtained from WikiArt, an online collection effort of visual arts driven by volunteers. This dataset also includes metadata such as artist identies, genre, and style of the artworks. We use this metadata for further analysis of the archetypal style representation along biographic lines of artists and with an eye on the relationships within groups of artists
Magnan, Jean-Christophe. "Représentations graphiques de fonctions et processus décisionnels Markoviens factorisés". Electronic Thesis or Diss., Paris 6, 2016. http://www.theses.fr/2016PA066042.
Pełny tekst źródłaIn decision theoretic planning, the factored framework (Factored Markovian Decision Process, FMDP) has produced several efficient algorithms in order to resolve large sequential decision making under uncertainty problems. The efficiency of this algorithms relies on data structures such as decision trees or algebraïc decision diagrams (ADDs). These planification technics are exploited in Reinforcement Learning by the architecture SDyna in order to resolve large and unknown problems. However, state-of-the-art learning and planning algorithms used in SDyna require the problem to be specified uniquely using binary variables and/or to use improvable data structure in term of compactness. In this book, we present our research works that seek to elaborate and to use a new data structure more efficient and less restrictive, and to integrate it in a new instance of the SDyna architecture. In a first part, we present the state-of-the-art modeling tools used in the algorithms that tackle large sequential decision making under uncertainty problems. We detail the modeling using decision trees and ADDs. Then we introduce the Ordered and Reduced Graphical Representation of Function, a new data structure that we propose in this thesis to deal with the various problems concerning the ADDs. We demonstrate that ORGRFs improve on ADDs to model large problems. In a second part, we go over the resolution of large sequential decision under uncertainty problems using Dynamic Programming. After the introduction of the main algorithms, we see in details the factored alternative. We indicate the improvable points of these factored versions. We describe our new algorithm that improve on these points and exploit the ORGRFs previously introduced. In a last part, we speak about the use of FMDPs in Reinforcement Learning. Then we introduce a new algorithm to learn the new datastrcture we propose. Thanks to this new algorithm, a new instance of the SDyna architecture is proposed, based on the ORGRFs : the SPIMDDI instance. We test its efficiency on several standard problems from the litterature. Finally, we present some works around this new instance. We detail a new algorithm for efficient exploration-exploitation compromise management, aiming to simplify F-RMax. Then we speak about an application of SPIMDDI to the managements of units in a strategic real time video game
Mountassir, Mahjoub El. "Surveillance d'intégrité des structures par apprentissage statistique : application aux structures tubulaires". Thesis, Université de Lorraine, 2019. http://www.theses.fr/2019LORR0047.
Pełny tekst źródłaTo ensure better working conditions of civil and engineering structures, inspections must be made on a regular basis. However, these inspections could be labor-intensive and cost-consuming. In this context, structural health monitoring (SHM) systems using permanently attached transducers were proposed to ensure continuous damage diagnostic of these structures. In SHM, damage detection is generally based on comparison between the healthy state signals and the current signals. Nevertheless, the environmental and operational conditions will have an effect on the healthy state signals. If these effects are not taken into account they would result in false indication of damage (false alarm). In this thesis, classical machine learning methods used for damage detection have been applied in the case of pipelines. The effects of some measurements parameters on the robustness of these methods have been investigated. Afterthat, two approaches were proposed for damage diagnostic depending on the database of reference signals. If this database contains large variation of these EOCs, a sparse estimation of the current signal is calculated. Then, the estimation error is used as an indication of the presence of damage. Otherwise, if this database is acquired at limited range of EOCs, moving window PCA can be applied to update the model of the healthy state provided that the EOCs show slow and continuous variation. In both approaches, damage localization was ensured using a sliding window over the damaged pipe signal
Ji, Hyungsuk. "Étude d'un modèle computationnel pour la représentation du sens des mots par intégration des relations de contexte". Phd thesis, Grenoble INPG, 2004. http://tel.archives-ouvertes.fr/tel-00008384.
Pełny tekst źródłaZribi, Abir. "Apprentissage par noyaux multiples : application à la classification automatique des images biomédicales microscopiques". Thesis, Rouen, INSA, 2016. http://www.theses.fr/2016ISAM0001.
Pełny tekst źródłaThis thesis arises in the context of computer aided analysis for subcellular protein localization in microscopic images. The aim is the establishment of an automatic classification system allowing to identify the cellular compartment in which a protein of interest exerts its biological activity. In order to overcome the difficulties in attempting to discern the cellular compartments in microscopic images, the existing state-of-art systems use several descriptors to train an ensemble of classifiers. In this thesis, we propose a different classification scheme wich better cope with the requirement of genericity and flexibility to treat various image datasets. Aiming to provide an efficient image characterization of microscopic images, a new feature system combining local, frequency-domain, global, and region-based features is proposed. Then, we formulate the problem of heterogeneous feature fusion as a kernel selection problem. Using multiple kernel learning, the problems of optimal feature sets selection and classifier training are simultaneously resolved. The proposed combination scheme leads to a simple and a generic framework capable of providing a high performance for microscopy image classification. Extensive experiments were carried out using widely-used and best known datasets. When compared with the state-of-the-art systems, our framework is more generic and outperforms other classification systems. To further expand our study on multiple kernel learning, we introduce a new formalism for learning with multiple kernels performed in two steps. This contribution consists in proposing three regularized terms with in the minimization of kernels weights problem, formulated as a classification problem using Separators with Vast Margin on the space of pairs of data. The first term ensures that kernels selection leads to a sparse representation. While the second and the third terms introduce the concept of kernels similarity by using a correlation measure. Experiments on various biomedical image datasets show a promising performance of our method compared to states of art methods
Smaïl-Tabbone, Malika. "Raisonnement à base de cas pour une recherche évolutive d'information : prototype cabri-n : vers la définition d'un cadre d'acquisition de connaissances". Nancy 1, 1994. http://www.theses.fr/1994NAN10409.
Pełny tekst źródłaDeshpande, Hrishikesh. "Dictionary learning for pattern classification in medical imaging". Thesis, Rennes 1, 2016. http://www.theses.fr/2016REN1S032/document.
Pełny tekst źródłaMost natural signals can be approximated by a linear combination of a few atoms in a dictionary. Such sparse representations of signals and dictionary learning (DL) methods have received a special attention over the past few years. While standard DL approaches are effective in applications such as image denoising or compression, several discriminative DL methods have been proposed to achieve better image classification. In this thesis, we have shown that the dictionary size for each class is an important factor in the pattern recognition applications where there exist variability difference between classes, in the case of both the standard and discriminative DL methods. We validated the proposition of using different dictionary size based on complexity of the class data in a computer vision application such as lips detection in face images, followed by more complex medical imaging application such as classification of multiple sclerosis (MS) lesions using MR images. The class specific dictionaries are learned for the lesions and individual healthy brain tissues, and the size of the dictionary for each class is adapted according to the complexity of the underlying data. The algorithm is validated using 52 multi-sequence MR images acquired from 13 MS patients
Nguyen, Thanh Tuan. "Représentations efficaces des textures dynamiques". Electronic Thesis or Diss., Toulon, 2020. https://bu.univ-tln.fr/files/userfiles/file/intranet/travuniv/theses/sciences/2020/2020_Nguyen_ThanhTuan.pdf.
Pełny tekst źródłaRepresentation of dynamic textures (DTs), well-known as a sequence of moving textures, is a challenge in video analysis for various computer vision applications. It is partly due to disorientation of motions, the negative impacts of the well-known issues on capturing turbulent features: noise, changes of environment, illumination, similarity transformations, etc. In this work, we introduce significant solutions in order to deal with above problems. Accordingly, three streams of those are proposed for encoding DTs: i) based on dense trajectories extracted from a given video; ii) based on robust responses extracted by moment models; iii) based on filtered outcomes which are computed by variants of Gaussian-filtering kernels. In parallel, we also propose several discriminative descriptors to capture spatio-temporal features for above DT encodings. For DT representation based on dense trajectories, we firstly extract dense trajectories from a given video. Motion points along the paths of dense trajectories are then encoded by our xLVP operator, an important extension of Local Vector Patterns (LVP) in a completed encoding context, in order to capture directional dense-trajectory-based features for DT representation.For DT description based on moment models, motivated by the moment-image model, we propose a novel model of moment volumes based on statistical information of spherical supporting regions centered at a voxel. Two these models are then taken into account video analysis to point out moment-based images/volumes. In order to encode the moment-based images, we address CLSP operator, a variant of completed local binary patterns (CLBP). In the meanwhile, our xLDP, an important extension of Local Derivative Patterns (LDP) in a completed encoding context, is introduced to capture spatio-temporal features of the moment-volume-based outcomes. For DT representation based on the Gaussian-based filterings, we will investigate many kinds of filterings as pre-processing analysis of a video to point out its filtered outcomes. After that, these outputs are encoded by discriminative operators to structure DT descriptors correspondingly. More concretely, we exploit the Gaussian-based kernel and variants of high-order Gaussian gradients for the filtering analysis. Particularly, we introduce a novel filtering kernel (DoDG) in consideration of the difference of Gaussian gradients, which allows to point out robust DoDG-filtered components to construct prominent DoDG-based descriptors in small dimension. In parallel to the Gaussian-based filterings, some novel operators will be introduced to meet different contexts of the local DT encoding: CAIP, an adaptation of CLBP to fix the close-to-zero problem caused by separately bipolar features; LRP, based on a concept of a square cube of local neighbors sampled at a center voxel; CHILOP, a generalized formulation of CLBP to adequately investigate local relationships of hierarchical supporting regions. Experiments for DT recognition have validated that our proposals significantly perform in comparison with state of the art. Some of which have performance being very close to deep-learning approaches, expected as one of appreciated solutions for mobile applications due to their simplicity in computation and their DT descriptors in a small number of bins
Castillo-Navetty, Oswaldo. "Csao : méthode pour la construction d'un système d'apprentissage opérationnel à partir d'une mémoire métier". Troyes, 2006. http://www.theses.fr/2006TROY0007.
Pełny tekst źródłaNowadays, most companies develop and apply strategies of knowledge management. In enterprises this knowledge is more and more seen in the form of “Corporate Memory”. My area of interest is centered around a kind of corporate memory known as “Professional Memory”. My thesis is based on knowledge appropriation taken from a professional memory. It involves supporting a novice employee by providing them with the expert knowledge of the domain, the “know how” so that he can perform tasks needed by the company. The goal is to use the principles of knowledge engineering, to transfer this knowledge to the employee. The alliance of these two approaches allows the development of a practical, performant, system of learning
Pierre, Denis. "Formulation et maintenance d'une théorie hypothétique par un agent apprenant". Montpellier 2, 1997. http://www.theses.fr/1997MON20082.
Pełny tekst źródłaMerckling, Astrid. "Unsupervised pretraining of state representations in a rewardless environment". Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS141.
Pełny tekst źródłaThis 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
Mantilla, Jauregui Juan José. "Caractérisation de pathologies cardiaques en Imagerie par Résonance Magnétique par approches parcimonieuses". Thesis, Rennes 1, 2015. http://www.theses.fr/2015REN1S073/document.
Pełny tekst źródłaThis work concerns the use of sparse representation and Dictionary Learning (DL) in order to get insights about the diseased heart in the context of Cardiovascular Diseases (CVDs). Specifically, this work focuses on 1) assessment of Left Ventricle (LV) wall motion in patients with heart failure and 2) fibrosis detection in patients with hypertrophic cardiomyopathy (HCM). In the context of heart failure (HF) patients, the work focuses on LV wall motion analysis in cardiac cine-MRI. The first contribution in this topic is a feature extraction method that exploits the partial information obtained from all temporal cardiac phases and anatomical segments in a spatio-temporal representation from sequences cine-MRI in short-axis view. These features correspond to spatio-temporal profiles in different anatomical segments of the LV. The proposed representations exploit information of the LV wall motion without segmentation needs. Three representations are proposed : 1) diametrical spatio-temporal profiles where radial motions of LV’s walls are observed at the same time in opposite anatomical segments 2) radial spatiotemporal profiles where motion of LV’s walls is observed for each segment of the LV cavity and 3) quantitative parameters extracted from the radial spatio-temporal profiles. A second contribution involves the use of these features as input atoms in the training of discriminative dictionaries to classify normal or abnormal regional LV motion. We propose two levels of evaluation, a first one where the global status of the subject (normal/pathologic) is used as ground truth to label the proposed spatio-temporal representations, and a second one where local strain information obtained from 2D Speckle Tracking Echocardiography (STE), is taken as ground truth to label the proposed features, where a profile is classified as normal or abnormal (akinetic or hypokinetic cases). In the context of Hypertrophic cardiomyopathy (HCM), we address the problem of fibrosis detection in Late Gadolinium Enhanced LGE-Short axis (SAX) images by using a sparse-based clustering approach and DL. In this framework, random image patches are taken as input atoms in order to train a classifier based on the sparse coefficients obtained with a DL approach based on kernels. For a new test LG-SAX image, the label of each pixel is predicted by using the trained classifier allowing the detection of fibrosis. A subsequent postprocessing step allows the spatial localization of fibrosis that is represented according to the American Heart Association (AHA) 17-segment model and a quantification of fibrosis in the LV myocardium
Solomonidou, Christine. "Comment se représenter les substances et leurs interactions ? : étude chez de jeunes élèves du collège". Paris 7, 1991. http://www.theses.fr/1991PA077298.
Pełny tekst źródłaZhu, Ruifeng. "Contribution to graph-based manifold learning with application to image categorization". Thesis, Bourgogne Franche-Comté, 2020. http://www.theses.fr/2020UBFCA015.
Pełny tekst źródłaGraph-based Manifold Learning algorithms are regarded as a powerful technique for feature extraction and dimensionality reduction in Pattern Recogniton, Computer Vision and Machine Learning fields. These algorithms utilize sample information contained in the item-item similarity and weighted matrix to reveal the intrinstic geometric structure of manifold. It exhibits the low dimensional structure in the high dimensional data. This motivates me to develop Graph-based Manifold Learning techniques on Pattern Recognition, specially, application to image categorization. The experimental datasets of thesis correspond to several categories of public image datasets such as face datasets, indoor and outdoor scene datasets, objects datasets and so on. Several approaches are proposed in this thesis: 1) A novel nonlinear method called Flexible Discriminant graph-based Embedding with feature selection (FDEFS) is proposed. We seek a non-linear and a linear representation of the data that can be suitable for generic learning tasks such as classification and clustering. Besides, a byproduct of the proposed embedding framework is the feature selection of the original features, where the estimated linear transformation matrix can be used for feature ranking and selection. 2) We investigate strategies and related algorithms to develop a joint graph-based embedding and an explicit feature weighting for getting a flexible and inductive nonlinear data representation on manifolds. The proposed criterion explicitly estimates the feature weights together with the projected data and the linear transformation such that data smoothness and large margins are achieved in the projection space. Moreover, this chapter introduces a kernel variant of the model in order to get an inductive nonlinear embedding that is close to a real nonlinear subspace for a good approximation of the embedded data. 3) We propose the graph convolution based semi-supervised Embedding (GCSE). It provides a new perspective to non-linear data embedding research, and makes a link to signal processing on graph methods. The proposed method utilizes and exploits graphs in two ways. First, it deploys data smoothness over graphs. Second, its regression model is built on the joint use of the data and their graph in the sense that the regression model works with convolved data. The convolved data are obtained by feature propagation. 4) A flexible deep learning that can overcome the limitations and weaknesses of single-layer learning models is introduced. We call this strategy an Elastic graph-based embedding with deep architecture which deeply explores the structural information of the data. The resulting framework can be used for semi-supervised and supervised settings. Besides, the resulting optimization problems can be solved efficiently
Qiu, Mingming. "Designing smart home services using machine learning and knowledge-based approaches". Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAT014.
Pełny tekst źródłaThe intelligence of a smart home is realized by creating various services. Eachservice tries to adjust one monitored state by controlling related actuators after consideringenvironment states detected by sensors. However, the design of the logic of the services deployedin a smart home faces limitations of either dynamic adaptability (predefined rules) orexplicability (learning techniques). Four proposals that are parts of a hybrid approach combiningpredefined rules and learning techniques aim at mitigating these limitations.The first proposal is to use reinforcement learning to create a dynamic service. The deploymentof this single service includes two phases : pretraining in the simulation and continuous trainingin the real world. Our study only focuses on the simulation part. Extending the first proposal,the second proposal proposes several architectures to create multiple dynamic and conflictfreeservices. However, the created data-driven services are not explicable. Therefore, the thirdproposal aims to extract explicable knowledgebased services from dynamic data-driven services.The fourth proposal attempts to combine the second and third proposals to create dynamicand explicable services. These proposals are evaluated in a simulated environment ontemperature control, light intensity, and air quality services adapted to the activities of the inhabitant.They can be extended according to several perspectives, such as the co-simulation ofphysical phenomena, the dynamic adaptation to various inhabitant profiles, and the energy efficiencyof the deployed services
Ollmann, Michaël. "De la représentation des risques professionnels aux pratiques de prévention : quelle dynamique pour quelle formation : le cas du risque routier et des troubles musculosquelettiques en question". Vandoeuvre-les-Nancy, INPL, 2005. http://docnum.univ-lorraine.fr/public/INPL/2005_OLLMAN_M_1.pdf.
Pełny tekst źródłaMany cultural, technical and scientific upheavals are going through our modern societies. However, parallely to the progress they generate, these upheavals also create undesirable effects which we name risks. The domain of risks on the places of work is not spared by this phenomenon and we are presently noticing the emergence of risks that do not exactly correspond to usual criteria of risks on these places. We may ask ourselves what sort of representation of these risks prevention actors have? What sort of knowledge and competences are necessary to these prevention? What sort of training can we propose to prevention actors? In order to give appropriate answers to these questions, we have been interested in two risks: the risks on roads and the risk on musculoskeletal disorders. In order to achieve our goal we carried out a series of semi-directive interviews next to the “CRAM” prevention actors and the actors of the prevention inside firms who have been confronted with these risks. Thanks to this study, we can thus understand the dynamic of representations, the nature of prevention practices and the learning and training mode process of the prevention actors. From these results, we make recommendations to adapt the training of the prevention actors to the peculiar characteristics of these risks
Nguyen, Nhu Van. "Représentations visuelles de concepts textuels pour la recherche et l'annotation interactives d'images". Phd thesis, Université de La Rochelle, 2011. http://tel.archives-ouvertes.fr/tel-00730707.
Pełny tekst źródłaDang, Hong-Phuong. "Approches bayésiennes non paramétriques et apprentissage de dictionnaire pour les problèmes inverses en traitement d'image". Thesis, Ecole centrale de Lille, 2016. http://www.theses.fr/2016ECLI0019/document.
Pełny tekst źródłaDictionary learning for sparse representation has been widely advocated for solving inverse problems. Optimization methods and parametric approaches towards dictionary learning have been particularly explored. These methods meet some limitations, particularly related to the choice of parameters. In general, the dictionary size is fixed in advance, and sparsity or noise level may also be needed. In this thesis, we show how to perform jointly dictionary and parameter learning, with an emphasis on image processing. We propose and study the Indian Buffet Process for Dictionary Learning (IBP-DL) method, using a bayesian nonparametric approach.A primer on bayesian nonparametrics is first presented. Dirichlet and Beta processes and their respective derivatives, the Chinese restaurant and Indian Buffet processes are described. The proposed model for dictionary learning relies on an Indian Buffet prior, which permits to learn an adaptive size dictionary. The Monte-Carlo method for inference is detailed. Noise and sparsity levels are also inferred, so that in practice no parameter tuning is required. Numerical experiments illustrate the performances of the approach in different settings: image denoising, inpainting and compressed sensing. Results are compared with state-of-the art methods is made. Matlab and C sources are available for sake of reproducibility
Piette, Eric. "Une nouvelle approche au General Game Playing dirigée par les contraintes". Thesis, Artois, 2016. http://www.theses.fr/2016ARTO0401/document.
Pełny tekst źródłaThe ability for a computer program to effectively play any strategic game, often referred to General Game Playing (GGP), is a key challenge in AI. The GGP competitions, where any game is represented according to a set of logical rules in the Game Description Language (GDL), have led researches to compare various approaches, including Monte Carlo methods, automatic constructions of evaluation functions, logic programming, and answer set programming through some general game players. In this thesis, we offer a new approach driven by stochastic constraints. We first focus on a translation process from GDL to stochastic constraint networks (SCSP) in order to provide compact representations of strategic games and to model strategies. In a second part, we exploit a fragment of SCSP through an algorithm called MAC-UCB by coupling the MAC (Maintaining Arc Consistency) algorithm, used to solve each stage of the SCSP in turn, together with the UCB (Upper Confidence Bound) policy for approximating the values of those strategies obtained by the last stage in the sequence. The efficiency of this technical on the others GGP approaches is confirmed by WoodStock, implementing MAC-UCB, the actual leader on the GGP Continuous Tournament. Finally, in the last part, we propose an alternative approach to symmetry detection in stochastic games, inspired from constraint programming techniques. We demonstrate experimentally that MAC-UCB, coupled with our constranit-based symmetry detection approach, significantly outperforms the best approaches and made WoodStock the GGP champion 2016
Risser-Maroix, Olivier. "Similarité visuelle et apprentissage de représentations". Electronic Thesis or Diss., Université Paris Cité, 2022. http://www.theses.fr/2022UNIP7327.
Pełny tekst źródłaThe objective of this CIFRE thesis is to develop an image search engine, based on computer vision, to assist customs officers. Indeed, we observe, paradoxically, an increase in security threats (terrorism, trafficking, etc.) coupled with a decrease in the number of customs officers. The images of cargoes acquired by X-ray scanners already allow the inspection of a load without requiring the opening and complete search of a controlled load. By automatically proposing similar images, such a search engine would help the customs officer in his decision making when faced with infrequent or suspicious visual signatures of products. Thanks to the development of modern artificial intelligence (AI) techniques, our era is undergoing great changes: AI is transforming all sectors of the economy. Some see this advent of "robotization" as the dehumanization of the workforce, or even its replacement. However, reducing the use of AI to the simple search for productivity gains would be reductive. In reality, AI could allow to increase the work capacity of humans and not to compete with them in order to replace them. It is in this context, the birth of Augmented Intelligence, that this thesis takes place. This manuscript devoted to the question of visual similarity is divided into two parts. Two practical cases where the collaboration between Man and AI is beneficial are proposed. In the first part, the problem of learning representations for the retrieval of similar images is still under investigation. After implementing a first system similar to those proposed by the state of the art, one of the main limitations is pointed out: the semantic bias. Indeed, the main contemporary methods use image datasets coupled with semantic labels only. The literature considers that two images are similar if they share the same label. This vision of the notion of similarity, however fundamental in AI, is reductive. It will therefore be questioned in the light of work in cognitive psychology in order to propose an improvement: the taking into account of visual similarity. This new definition allows a better synergy between the customs officer and the machine. This work is the subject of scientific publications and a patent. In the second part, after having identified the key components allowing to improve the performances of thepreviously proposed system, an approach mixing empirical and theoretical research is proposed. This secondcase, augmented intelligence, is inspired by recent developments in mathematics and physics. First applied tothe understanding of an important hyperparameter (temperature), then to a larger task (classification), theproposed method provides an intuition on the importance and role of factors correlated to the studied variable(e.g. hyperparameter, score, etc.). The processing chain thus set up has demonstrated its efficiency byproviding a highly explainable solution in line with decades of research in machine learning. These findings willallow the improvement of previously developed solutions
Cordier, Virginie. "Influence de la simulation mentale guidée sur l'apprentissage du mouvement en danse". Thesis, La Réunion, 2010. http://www.theses.fr/2010LARE0003/document.
Pełny tekst źródłaThis study aims to highlight the effects of mental simulation of guided learning, performance and image of the movement in dance. In the literature review, we present the main theories of cognitive and socio-cognitive, and implementations of learning methods from these two theoretical fields. Then, from the specifics of the dance "didactical" transformations referred by schools and universities, and the place of mental images in dance, we consider the mental simulation guided by rhythmic and metaphorical instructions. Afterwards, we present a preliminary study for the tool construction for assessing performance in dance, and two experimental studies conducted with novice adult subjects on learning tasks during reproduction of form and improvisation-composition. The results in their essence show (1) that mental simulation is a more effective method of learning than observation, from the moment it is guided 2) that the rhythmic instructions are fundamental in dance learning because they help to organize and structure the movement, (3) that the metaphorical instructions seem particularly suited to the expressive and artistic dimensions of dancing. Taken together, these findings emphasize the importance of guided mental simulation with instructions to ensure its effectiveness in learning
Ben-Younes, Hedi. "Multi-modal representation learning towards visual reasoning". Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS173.
Pełny tekst źródłaThe quantity of images that populate the Internet is dramatically increasing. It becomes of critical importance to develop the technology for a precise and automatic understanding of visual contents. As image recognition systems are becoming more and more relevant, researchers in artificial intelligence now seek for the next generation vision systems that can perform high-level scene understanding. In this thesis, we are interested in Visual Question Answering (VQA), which consists in building models that answer any natural language question about any image. Because of its nature and complexity, VQA is often considered as a proxy for visual reasoning. Classically, VQA architectures are designed as trainable systems that are provided with images, questions about them and their answers. To tackle this problem, typical approaches involve modern Deep Learning (DL) techniques. In the first part, we focus on developping multi-modal fusion strategies to model the interactions between image and question representations. More specifically, we explore bilinear fusion models and exploit concepts from tensor analysis to provide tractable and expressive factorizations of parameters. These fusion mechanisms are studied under the widely used visual attention framework: the answer to the question is provided by focusing only on the relevant image regions. In the last part, we move away from the attention mechanism and build a more advanced scene understanding architecture where we consider objects and their spatial and semantic relations. All models are thoroughly experimentally evaluated on standard datasets and the results are competitive with the literature
Holgado, Otilia. "Analyse didactique de l'activité en formation professionnelle : le cas de l'apprentissage des Systèmes d'Information Géographique". Phd thesis, Université de Bourgogne, 2011. http://tel.archives-ouvertes.fr/tel-00732890.
Pełny tekst źródłaShim, Kyung-Eun. "L'assimilation du tour-pivot en danse classique la Pirouette en dehors par la danse coréenne Hanbaldeuleodolgi : une étude comparative de la manière dont la danse classique et la danse coréenne maîtrisent les principes fonctionnels du tour-pivot à partir d'une analyse de leur apprentissage". Paris, EHESS, 2016. http://www.theses.fr/2016EHES0010.
Pełny tekst źródłaFrom the cultural exchange between the West and Asia since the beginning of the 20th century, the Korean dance has integrated quite a few aspects of classical dance while transforming its figures. The transformation itself is what we are interested in. We focused on a central figure in ballet la pirouette en dehors, which in the Korean dance is known as the Hanbaldeuleodolgi. Our research aims to understand how a dance movement which comes under similar mechanical stresses (producing rotational forces) is expressed in both cultures (France, Korea). To complete this project we believe that an overall approach between different academic fields was necessary. We propose two ways to describe the pivot turn qualitatively, a detailed description of the dance figures with the theory of Laban and semi-structured interviews of how high level teachers from both cultures perceive the pivot turn properties and how they view the learning process. In addition, a biomechanical analysis of the pivot turn has enabled to show how each culture finely tune motion parameters to give both dance its cultural artistic dimension. These analyzes set in perspective with some aspect of Korean philosophy of the person enables us to capture, at least partially, the process of transformation and therefore assimilation of ballet dance movements by Korean dance
Munzer, Thibaut. "Représentations relationnelles et apprentissage interactif pour l'apprentissage efficace du comportement coopératif". Thesis, Bordeaux, 2017. http://www.theses.fr/2017BORD0574/document.
Pełny tekst źródłaThis thesis presents new approaches toward efficient and intuitive high-level plan learning for cooperative robots. More specifically this work study Learning from Demonstration algorithm for relational domains. Using relational representation to model the world, simplify representing concurrentand cooperative behavior.We have first developed and studied the first algorithm for Inverse ReinforcementLearning in relational domains. We have then presented how one can use the RAP formalism to represent Cooperative Tasks involving a robot and a human operator. RAP is an extension of the Relational MDP framework that allows modeling concurrent activities. Using RAP allow us to represent both the human and the robot in the same process but also to model concurrent robot activities. Under this formalism, we have demonstrated that it is possible to learn behavior, as policy and as reward, of a cooperative team. Prior knowledge about the task can also be used to only learn preferences of the operator.We have shown that, using relational representation, it is possible to learn cooperative behaviors from a small number of demonstration. That these behaviors are robust to noise, can generalize to new states and can transfer to different domain (for example adding objects). We have also introduced an interactive training architecture that allows the system to make fewer mistakes while requiring less effort from the human operator. By estimating its confidence the robot is able to ask for instructions when the correct activity to dois unsure. Lastly, we have implemented these approaches on a real robot and showed their potential impact on an ecological scenario
Mairal, Julien. "Sparse coding for machine learning, image processing and computer vision". Phd thesis, École normale supérieure de Cachan - ENS Cachan, 2010. http://tel.archives-ouvertes.fr/tel-00595312.
Pełny tekst źródłaSarker, Bishnu. "On Graph-Based Approaches for Protein Function Annotation and Knowledge Discovery". Electronic Thesis or Diss., Université de Lorraine, 2021. http://www.theses.fr/2021LORR0094.
Pełny tekst źródłaDue to the recent advancement in genomic sequencing technologies, the number of protein entries in public databases is growing exponentially. It is important to harness this huge amount of data to describe living things at the molecular level, which is essential for understanding human disease processes and accelerating drug discovery. A prerequisite, however, is that all of these proteins be annotated with functional properties such as Enzyme Commission (EC) numbers and Gene Ontology (GO) terms. Today, only a small fraction of the proteins is functionally annotated and reviewed by expert curators because it is expensive, slow and time-consuming. Developing automatic protein function annotation tools is the way forward to reduce the gap between the annotated and unannotated proteins and to predict reliable annotations for unknown proteins. Many tools of this type already exist, but none of them are fully satisfactory. We observed that only few consider graph-based approaches and the domain composition of proteins. Indeed, domains are conserved regions across protein sequences of the same family. In this thesis, we design and evaluate graph-based approaches to perform automatic protein function annotation and we explore the impact of domain architecture on protein functions. The first part is dedicated to protein function annotation using domain similarity graph and neighborhood-based label propagation technique. We present GrAPFI (Graph-based Automatic Protein Function Inference) for automatically annotating proteins with enzymatic functions (EC numbers) and GO terms from a protein-domain similarity graph. We validate the performance of GrAPFI using six reference proteomes from UniprotKB/SwissProt and compare GrAPFI results with state-of-the-art EC prediction approaches. We find that GrAPFI achieves better accuracy and comparable or better coverage. The second part of the dissertation deals with learning representation for biological entities. At the beginning, we focus on neural network-based word embedding technique. We formulate the annotation task as a text classification task. We build a corpus of proteins as sentences composed of respective domains and learn fixed dimensional vector representation for proteins. Then, we focus on learning representation from heterogeneous biological network. We build knowledge graph integrating different sources of information related to proteins and their functions. We formulate the problem of function annotation as a link prediction task between proteins and GO terms. We propose Prot-A-GAN, a machine-learning model inspired by Generative Adversarial Network (GAN) to learn vector representation of biological entities from protein knowledge graph. We observe that Prot-A-GAN works with promising results to associate ap- propriate functions with query proteins. In conclusion, this thesis revisits the crucial problem of large-scale automatic protein function annotation in the light of innovative techniques of artificial intelligence. It opens up wide perspectives, in particular for the use of knowledge graphs, which are today available in many fields other than protein annotation thanks to the progress of data science
Senoussi, Medhi. "Flexibilité temporelle et spatiale des représentations neurales d'objets visuels lors d'apprentissages". Thesis, Toulouse 3, 2016. http://www.theses.fr/2016TOU30162.
Pełny tekst źródłaThe work presented in this thesis deals with the effect of short- and long-term learning on the visual system. We first demonstrated through electroencephalographic recordings that learning a sequence of visual stimuli induced spontaneous and selective cerebral activity to the next-to-appear stimulus and that this selective activity was expressed in the alpha and beta bands of cerebral electrical activity. Subsequently, we showed through functional magnetic resonance imaging that during long learning (three weeks) the neural representations of associated visual categories were modulated and became more similar due to learning. The work presented in this thesis has thus made it possible to better characterize the impact of learning at different time scales on the neural representations of visual objects
El-Zakhem, Imad. "Modélisation et apprentissage des perceptions humaines à travers des représentations floues : le cas de la couleur". Reims, 2009. http://theses.univ-reims.fr/exl-doc/GED00001090.pdf.
Pełny tekst źródłaThe target of this thesis is to implement an interactive modeling of the user perception and a creation of an appropriate profile. We present two methods to build the profile representing the perception of the user through fuzzy subsets. The first method is a descriptive method used by an expert user and the second one is a constructive method used by a none-expert user. For the descriptive method, we propose a questioning procedure allowing the user to define completely his profile. For the constructive method, the user will be able to define his perception while comparing and selecting some profiles reflecting the perception of other expert users. We present a procedure of aggregation allowing building the profile of the user starting from the selected expert profiles and the rates of satisfaction. As a case study, we describe an application to model the color perception. Thereafter, we exploit the profiles already built for image classification. We propose a procedure that allows building the profile of an image according to the user perception, by using the standard profile of the image and the user’s profile representing his perception. In this method we use new definitions for the notions of comparability and compatibility of two fuzzy subsets. At the end, we present an implementation of the all procedure, the structure of the database as some examples and results
Laugier, Catherine. "Apprentissage par observation en danse : rôle des processus représentatifs dans la reproduction de mouvements". Montpellier 1, 1995. http://www.theses.fr/1995MON14002.
Pełny tekst źródłaBucher, Maxime. "Apprentissage et exploitation de représentations sémantiques pour la classification et la recherche d'images". Thesis, Normandie, 2018. http://www.theses.fr/2018NORMC250/document.
Pełny tekst źródłaIn this thesis, we examine some practical difficulties of deep learning models.Indeed, despite the promising results in computer vision, implementing them in some situations raises some questions. For example, in classification tasks where thousands of categories have to be recognised, it is sometimes difficult to gather enough training data for each category.We propose two new approaches for this learning scenario, called <>. We use semantic information to model classes which allows us to define models by description, as opposed to modelling from a set of examples.In the first chapter we propose to optimize a metric in order to transform the distribution of the original data and to obtain an optimal attribute distribution. In the following chapter, unlike the standard approaches of the literature that rely on the learning of a common integration space, we propose to generate visual features from a conditional generator. The artificial examples can be used in addition to real data for learning a discriminant classifier. In the second part of this thesis, we address the question of computational intelligibility for computer vision tasks. Due to the many and complex transformations of deep learning algorithms, it is difficult for a user to interpret the returned prediction. Our proposition is to introduce what we call a <> in the processing pipeline, which is a crossing point in which the representation of the image is entirely expressed with natural language, while retaining the efficiency of numerical representations. This semantic bottleneck allows to detect failure cases in the prediction process so as to accept or reject the decision
Poittevin, Luc. "Un outil générique de conception et de révision coopérative de Bases de Connaissances s'appuyant sur la notion de situation". Phd thesis, Université Paris Sud - Paris XI, 1998. http://tel.archives-ouvertes.fr/tel-00941692.
Pełny tekst źródłaGoh, Hanlin. "Apprentissage de Représentations Visuelles Profondes". Phd thesis, Université Pierre et Marie Curie - Paris VI, 2013. http://tel.archives-ouvertes.fr/tel-00948376.
Pełny tekst źródłaPoplimont, Christine. "Représentations sociales des formateurs dans la formation par alternance : approche intensive et étude clinique de cas". Aix-Marseille 1, 2000. http://www.theses.fr/2000AIX10028.
Pełny tekst źródłaFernandes, Hilaire. "iSTOA, modèle notionnel de guidage macroscopique de l'apprentissage". Phd thesis, Université des Sciences et Technologie de Lille - Lille I, 2010. http://tel.archives-ouvertes.fr/tel-00498599.
Pełny tekst źródłaGlady, Yannick. "Raisonnement par analogie et son développement : rôle des fonctions exécutives et du but de la tâche". Thesis, Dijon, 2013. http://www.theses.fr/2013DIJOL036/document.
Pełny tekst źródłaThis manuscript develops an issue related to the involvement of goal management capabilities and executive functions in this type of reasoning and its development. The first three experiments examine this issue in two tasks of analogical reasoning, the scene analogy task and the A:B::C:? task, through the study of visual strategies used by adults, and children aged 6-to-7. The results show differences in visual patterns related to goals, and to the inhibition of irrelevant information for the solution of the problems, between the different tasks, and between children and adults. The following two experiments study the visual strategies, always in relation to executive functioning and goal management, in an A:B::C:? task whose difficulty is manipulated to highlight the difference in involvement of monitoring and evaluation processes. The results do show an effect of the difficulty of the test and the type of distractor in the visual strategies employed. Finally, the last three experiments investigate the involvement of cognitive flexibility, one of the executive functions, in the analogical reasoning of preschool children (5-6-year-olds), limited in their flexibility. The results show that their early anchoring in a type of representation, relevant or not to the solution of the problem, is related to their ability to solve the problem later, and thus suggest a difficulty in shifting their representation during the resolution of the problems. These results are finally discussed in relation to models of analogical reasoning and of the development of this ability, especially those integrating goal management and executive functions
Xie, Bingqing. "Image-domain material decomposition in spectral photon-counting CT for medical applications". Thesis, Lyon, 2020. http://www.theses.fr/2020LYSEI021.
Pełny tekst źródłaMaterial decomposition is a fundamental and primordial problem in spectral photon-counting X-ray CT (sCT). The present thesis focuses on the development of material decomposition methods using spectral and morphological information embedded in multi-energy sCT images. In this framework, three methods were developed. For the first method, by using bounded mass density, local joint sparsity and structural low-rank (DSR) in image domain, we achieve highly accurate decomposition of materials such as gadolinium, iodine and iron. The results on both numerical phantom and physical data demonstrated that the proposed DSR method leads to more accurate decomposition than usual pseudo-inverse method with singular value decomposition (SVD) and current popular sparse regularization method with L1-norm constraint. The second method works in a region-wise manner. It consists in optimizing basis materials based on spatio-energy segmentation of regions-of-interests (ROIs) in sCT images, reducing noise by averaging multi-energy spatial images, and performing a fine material decomposition involving optimized decomposition matrix, denoising regularization and sparsity regularization. The results on both digital and physical data showed that the proposed ROI-wise material decomposition method presents clearly higher reliability and accuracy compared to common decomposition methods based on total variation (TV) or L1-norm (lasso) regularization. In the third method, we propose the notion of super-energy-resolution (SER) sCT imaging, which is realized through establishing the relationship between simulation and physical phantoms by means of coupled dictionary learning in a pixel-wise way. The effectiveness of the proposed methods was validated on digital phantom, physical phantoms and in vivo data. The results showed that for the same decomposition method using lasso regularization, the proposed super-energy-resolution imaging presents much higher decomposition accuracy and detection ability compared to what can be provided by current sCT machine