Rozprawy doktorskie na temat „Apprentissage auto-supervisé (intelligence artificielle)”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych rozpraw doktorskich naukowych na temat „Apprentissage auto-supervisé (intelligence artificielle)”.
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.
Niquil, Yves. "Acquisition d'exemples en discrimination : spécification des exemples par génération de scenarios". Paris 9, 1993. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1993PA090063.
Pełny tekst źródłaSarazin, Tugdual. "Apprentissage massivement distribué dans un environnement Big Data". Thesis, Sorbonne Paris Cité, 2018. http://www.theses.fr/2018USPCD050.
Pełny tekst źródłaIn recent years, the amount of data analysed by companies and research laboratories increased strongly, opening the era of BigData. However, these raw data are frequently non-categorized and uneasy to use. This thesis aims to improve and ease the pre-treatment and comprehension of these big amount of data by using unsupervised machine learning algorithms.The first part of this thesis is dedicated to a state-of-the-art of clustering and biclustering algorithms and to an introduction to big data technologies. The first part introduces the conception of clustering Self-Organizing Map algorithm [Kohonen,2001] in big data environment. Our algorithm (SOM-MR) provides the same advantages as the original algorithm, namely the creation of data visualisation map based on data clusters. Moreover, it uses the Spark platform that makes it able to treat a big amount of data in a short time. Thanks to the popularity of this platform, it easily fits in many data mining environments. This is what we demonstrated it in our project \Square Predict" carried out in partnership with Axa insurance. The aim of this project was to provide a real-time data analysing platform in order to estimate the severity of natural disasters or improve residential risks knowledge. Throughout this project, we proved the efficiency of our algorithm through its capacity to analyse and create visualisation out of a big volume of data coming from social networks and open data.The second part of this work is dedicated to a new bi-clustering algorithm. BiClustering consists in making a cluster of observations and variables at the same time. In this contribution we put forward a new approach of bi-clustering based on the self-organizing maps algorithm that can scale on big amounts of data (BiTM-MR). To reach this goal, this algorithm is also based on a the Spark platform. It brings out more information than the SOM-MR algorithm because besides producing observation groups, it also associates variables to these groups,thus creating bi-clusters of variables and observations
Fakeri, Tabrizi Ali. "Semi-supervised multi-view learning : an application to image annotation and multi-lingual document classification". Paris 6, 2013. http://www.theses.fr/2013PA066336.
Pełny tekst źródłaIn this thesis, we introduce two multiview learning approaches. In a first approach, we describe a self-training multiview strategy which trains different voting classifiers on different views. The margin distributions over the unlabeled training data, obtained with each view-specific classifier are then used to estimate an upper-bound on their transductive Bayes error. Minimizing this upper-bound provides an automatic margin-threshold which is used to assign pseudo-labels to unlabeled examples. Final class labels are then assigned to these examples, by taking a vote on the pool of the previous pseudo-labels. New view-specific classifiers are then trained using the original labeled and the pseudo-labeled training data. We consider applications to image-text and to multilingual document classification. In second approach, we propose a multiview semi-supervised bipartite ranking model which allows us to leverage the information contained in unlabeled sets of images to improve the prediction performance, using multiple descriptions, or views of images. For each topic class, our approach first learns as many view-specific rankers as there are available views using the labeled data only. These rankers are then improved iteratively by adding pseudo-labeled pairs of examples on which all view-specific rankers agree over the ranking of examples within these pairs
Augier, Sébastien. "Apprentissage Supervisé Relationnel par Algorithmes d'Évolution". Phd thesis, Université Paris Sud - Paris XI, 2000. http://tel.archives-ouvertes.fr/tel-00947322.
Pełny tekst źródłaBaillard, Anthony. "Détermination automatique des paramètres morphologiques des galaxies". Paris, ENST, 2008. http://www.theses.fr/2008ENST0070.
Pełny tekst źródłaImages data is key to modern astrophysics, especially while trying to define galaxies. Galaxy morphological classification is an enthralling but difficult task. This is particularly true while dealing with distant galaxies convolved by a point-spread function and suffering from a poor signal-to-noise ratio. This thesis proposes an automatic system to classify images of galaxies with varying resolution. Being at the intersection of three disciplines: astronomy (properties of galaxies), signal processing (image analysis), and artificial intelligence (supervised learning), the work has been realized as part of the project EFIGI (http://www. Efigi. Org), a collaboration of French research laboratories (IAP, LTCI, LRDE, LAM, OMP and CRAL). The first two chapters, dedicated to astronomy, show how a robust set of morphological data was put together. Chapters three to five, on computer science, clarify the acquisition and usage of the input data for the classifiers. Chapter 1 introduces extragalactic astronomy and galactic morphology. Chapter 2 describes the catalogue of galaxies called CFIGI, which contains detailed morphological information. CFIGI is the result of fruitful work collaboration with seven astronomers. Chapter 3 introduces the tool NFIGI, which was written to clean images of galaxies from contaminating sources (like stars). Chapter 4 proposes a technique of dimensional reduction using SExFIGI, a software to decompose images of galaxies on a basis of concentric “rings”. Chapter 5 concludes with the supervised systems that automatically determine a set of morphological parameters (bulge/total ratio, arm curvature, bar strength, and others)
Bilodeau, Anthony. "Apprentissage faiblement supervisé appliqué à la segmentation d'images de protéines neuronales". Master's thesis, Université Laval, 2020. http://hdl.handle.net/20.500.11794/39752.
Pełny tekst źródłaThèse ou mémoire avec insertion d'articles
Tableau d'honneur de la Faculté des études supérieures et postdoctorales, 2020-2021
En biologie cellulaire, la microscopie optique est couramment utilisée pour visualiser et caractériser la présence et la morphologie des structures biologiques. Suite à l’acquisition, un expert devra effectuer l’annotation des structures pour quantification. Cette tâche est ardue, requiert de nombreuses heures de travail, parfois répétitif, qui peut résulter en erreurs d’annotations causées par la fatigue d’étiquetage. L’apprentissage machine promet l’automatisation de tâches complexes à partir d’un grand lot de données exemples annotés. Mon projet de maîtrise propose d’utiliser des techniques faiblement supervisées, où les annotations requises pour l’entraînement sont réduites et/ou moins précises, pour la segmentation de structures neuronales. J’ai d’abord testé l’utilisation de polygones délimitant la structure d’intérêt pour la tâche complexe de segmentation de la protéine neuronale F-actine dans des images de microscopie à super-résolution. La complexité de la tâche est supportée par la morphologie hétérogène des neurones, le nombre élevé d’instances à segmenter dans une image et la présence de nombreux distracteurs. Malgré ces difficultés, l’utilisation d’annotations faibles a permis de quantifier un changement novateur de la conformation de la protéine F-actine en fonction de l’activité neuronale. J’ai simplifié davantage la tâche d’annotation en requérant seulement des étiquettes binaires renseignant sur la présence des structures dans l’image réduisant d’un facteur 30 le temps d’annotation. De cette façon, l’algorithme est entraîné à prédire le contenu d’une image et extrait ensuite les caractéristiques sémantiques importantes pour la reconnaissance de la structure d’intérêt à l’aide de mécanismes d’attention. La précision de segmentation obtenue sur les images de F-actine est supérieure à celle des annotations polygonales et équivalente à celle des annotations précises d’un expert. Cette nouvelle approche devrait faciliter la quantification des changements dynamiques qui se produisent sous le microscope dans des cellules vivantes et réduire les erreurs causées par l’inattention ou le biais de sélection des régions d’intérêt dans les images de microscopie.
In cell biology, optical microscopy is commonly used to visualize and characterize the presenceand morphology of biological structures. Following the acquisition, an expert will have toannotate the structures for quantification. This is a difficult task, requiring many hours ofwork, sometimes repetitive, which can result in annotation errors caused by labelling fatigue.Machine learning promises to automate complex tasks from a large set of annotated sampledata. My master’s project consists of using weakly supervised techniques, where the anno-tations required for training are reduced and/or less precise, for the segmentation of neuralstructures.I first tested the use of polygons delimiting the structure of interest for the complex taskof segmentation of the neuronal protein F-actin in super-resolution microscopy images. Thecomplexity of the task is supported by the heterogeneous morphology of neurons, the highnumber of instances to segment in an image and the presence of many distractors. Despitethese difficulties, the use of weak annotations has made it possible to quantify an innovativechange in the conformation of the F-actin protein as a function of neuronal activity. I furthersimplified the annotation task by requiring only binary labels that indicate the presence ofstructures in the image, reducing annotation time by a factor of 30. In this way, the algorithmis trained to predict the content of an image and then extract the semantic characteristicsimportant for recognizing the structure of interest using attention mechanisms. The segmen-tation accuracy obtained on F-actin images is higher than that of polygonal annotations andequivalent to that of an expert’s precise annotations. This new approach should facilitate thequantification of dynamic changes that occur under the microscope in living cells and reduceerrors caused by inattention or bias in the selection of regions of interest in microscopy images.
Laumônier, Julien. "Méthodes d'apprentissage de la coordination multiagent : application au transport intelligent". Doctoral thesis, Université Laval, 2008. http://hdl.handle.net/20.500.11794/20000.
Pełny tekst źródłaSiblini, Wissam. "Apprentissage multi label extrême : comparaisons d'approches et nouvelles propositions". Thesis, Nantes, 2018. http://www.theses.fr/2018NANT4083/document.
Pełny tekst źródłaStimulated by many applications such as documents or images annotation, multilabel learning have gained a strong interest during the last decade. But, standard algorithms cannot cope with the volumes of the recent extreme multi-label data (XML) where the number of labels can reach millions. This thesis explores three directions to address the complexity in time and memory of the problem: multi-label dimension reduction, optimization and implementation tricks, and tree-based methods. It proposes to unify the reduction approaches through a typology and two generic formulations and to identify the most efficient ones with an original meta-analysis of the results of the literature. A new approach is developed to analyze the interest of coupling the reduction problem and the classification problem. To reduce the memory complexity of a classical one-vs-rest regression model while maintaining its predictive performances, we also propose an algorithm for estimating the largest useful parameters that follows a strategy inspired by data stream analysis. Finally, we present a new algorithm called CRAFTML that learns an ensemble of diversified decision trees. Each tree performs a joint random reduction of the feature and the label spaces and implements a very fast recursive partitioning strategy. CRAFTML performs better than other XML tree-based methods and is competitive with the most accurate methods that require supercomputers. The contributions of the thesis are completed by the presentation of a software called VIPE that is developed with Orange Labs for multilabel opinion analysis
Chareyre, Maxime. "Apprentissage non-supervisé pour la découverte de propriétés d'objets par découplage entre interaction et interprétation". Electronic Thesis or Diss., Université Clermont Auvergne (2021-...), 2023. http://www.theses.fr/2023UCFA0122.
Pełny tekst źródłaRobots are increasingly used to achieve tasks in controlled environments. However, their use in open environments is still fraught with difficulties. Robotic agents are likely to encounter objects whose behaviour and function they are unaware of. In some cases, it must interact with these elements to carry out its mission by collecting or moving them, but without knowledge of their dynamic properties it is not possible to implement an effective strategy for resolving the mission.In this thesis, we present a method for teaching an autonomous robot a physical interaction strategy with unknown objects, without any a priori knowledge, the aim being to extract information about as many of the object's physical properties as possible from the interactions observed by its sensors. Existing methods for characterising objects through physical interactions do not fully satisfy these criteria. Indeed, the interactions established only provide an implicit representation of the object's dynamics, requiring supervision to identify their properties. Furthermore, the proposed solution is based on unrealistic scenarios without an agent. Our approach differs from the state of the art by proposing a generic method for learning interaction that is independent of the object and its properties, and can therefore be decoupled from the prediction phase. In particular, this leads to a completely unsupervised global pipeline.In the first phase, we propose to learn an interaction strategy with the object via an unsupervised reinforcement learning method, using an intrinsic motivation signal based on the idea of maximising variations in a state vector of the object. The aim is to obtain a set of interactions containing information that is highly correlated with the object's physical properties. This method has been tested on a simulated robot interacting by pushing and has enabled properties such as the object's mass, shape and friction to be accurately identified.In a second phase, we make the assumption that the true physical properties define a latent space that explains the object's behaviours and that this space can be identified from observations collected through the agent's interactions. We set up a self-supervised prediction task in which we adapt a state-of-the-art architecture to create this latent space. Our simulations confirm that combining the behavioural model with this architecture leads to the emergence of a representation of the object's properties whose principal components are shown to be strongly correlated with the object's physical properties.Once the properties of the objects have been extracted, the agent can use them to improve its efficiency in tasks involving these objects. We conclude this study by highlighting the performance gains achieved by the agent through training via reinforcement learning on a simplified object repositioning task where the properties are perfectly known.All the work carried out in simulation confirms the effectiveness of an innovative method aimed at autonomously discovering the physical properties of an object through the physical interactions of a robot. The prospects for extending this work involve transferring it to a real robot in a cluttered environment
Yin, Hao. "Étude des réseaux de neurones en mode non supervisé : application à la reconnaissance des formes". Compiègne, 1992. http://www.theses.fr/1992COMPD524.
Pełny tekst źródłaBeaudoin, Mathieu. "Découverte de règles de classification pour un système d’aide à la décision pour la surveillance de l'usage des antimicrobiens". Thèse, Université de Sherbrooke, 2015. http://hdl.handle.net/11143/7591.
Pełny tekst źródłaGillard, Tristan. "Auto-organisation multi-échelle pour l’émergence de comportements sensorimoteurs coordonnés". Electronic Thesis or Diss., Université de Lorraine, 2022. http://www.theses.fr/2022LORR0353.
Pełny tekst źródłaNon-associative learning is widely observed throughout phylogeny and appears to be fundamental for the adaptation and, thus, the survival of living organisms. This thesis explores adaptation mechanisms inspired by these non-associative learnings. We propose three computational models of habituation, three models of site-specific sensitization and one model of pseudo-conditioning. We develop these models within the framework of the Iterant Deformable Sensorimotor Medium (IDSM), a recently developed abstract model of sensorimotor behavior formation. The characteristics of the presented models are studied and analyzed in light of our long-term goal of investigating new unsupervised learning mechanisms for autonomous artificial agents
Yang, Gen. "Modèles prudents en apprentissage statistique supervisé". Thesis, Compiègne, 2016. http://www.theses.fr/2016COMP2263/document.
Pełny tekst źródłaIn some areas of supervised machine learning (e.g. medical diagnostics, computer vision), predictive models are not only evaluated on their accuracy but also on their ability to obtain more reliable representation of the data and the induced knowledge, in order to allow for cautious decision making. This is the problem we studied in this thesis. Specifically, we examined two existing approaches of the literature to make models and predictions more cautious and more reliable: the framework of imprecise probabilities and the one of cost-sensitive learning. These two areas are both used to make models and inferences more reliable and cautious. Yet few existing studies have attempted to bridge these two frameworks due to both theoretical and practical problems. Our contributions are to clarify and to resolve these problems. Theoretically, few existing studies have addressed how to quantify the different classification errors when set-valued predictions are produced and when the costs of mistakes are not equal (in terms of consequences). Our first contribution has been to establish general properties and guidelines for quantifying the misclassification costs for set-valued predictions. These properties have led us to derive a general formula, that we call the generalized discounted cost (GDC), which allow the comparison of classifiers whatever the form of their predictions (singleton or set-valued) in the light of a risk aversion parameter. Practically, most classifiers basing on imprecise probabilities fail to integrate generic misclassification costs efficiently because the computational complexity increases by an order (or more) of magnitude when non unitary costs are used. This problem has led to our second contribution, the implementation of a classifier that can manage the probability intervals produced by imprecise probabilities and the generic error costs with the same order of complexity as in the case where standard probabilities and unitary costs are used. This is to use a binary decomposition technique, the nested dichotomies. The properties and prerequisites of this technique have been studied in detail. In particular, we saw that the nested dichotomies are applicable to all imprecise probabilistic models and they reduce the imprecision level of imprecise models without loss of predictive power. Various experiments were conducted throughout the thesis to illustrate and support our contributions. We characterized the behavior of the GDC using ordinal data sets. These experiences have highlighted the differences between a model based on standard probability framework to produce indeterminate predictions and a model based on imprecise probabilities. The latter is generally more competent because it distinguishes two sources of uncertainty (ambiguity and the lack of information), even if the combined use of these two types of models is also of particular interest as it can assist the decision-maker to improve the data quality or the classifiers. In addition, experiments conducted on a wide variety of data sets showed that the use of nested dichotomies significantly improves the predictive power of an indeterminate model with generic costs
Frery, Jordan. "Ensemble Learning for Extremely Imbalced Data Flows". Thesis, Lyon, 2019. http://www.theses.fr/2019LYSES034.
Pełny tekst źródłaMachine learning is the study of designing algorithms that learn from trainingdata to achieve a specific task. The resulting model is then used to predict overnew (unseen) data points without any outside help. This data can be of manyforms such as images (matrix of pixels), signals (sounds,...), transactions (age,amount, merchant,...), logs (time, alerts, ...). Datasets may be defined to addressa specific task such as object recognition, voice identification, anomaly detection,etc. In these tasks, the knowledge of the expected outputs encourages a supervisedlearning approach where every single observed data is assigned to a label thatdefines what the model predictions should be. For example, in object recognition,an image could be associated with the label "car" which suggests that the learningalgorithm has to learn that a car is contained in this picture, somewhere. This is incontrast with unsupervised learning where the task at hand does not have explicitlabels. For example, one popular topic in unsupervised learning is to discoverunderlying structures contained in visual data (images) such as geometric formsof objects, lines, depth, before learning a specific task. This kind of learning isobviously much harder as there might be potentially an infinite number of conceptsto grasp in the data. In this thesis, we focus on a specific scenario of thesupervised learning setting: 1) the label of interest is under represented (e.g.anomalies) and 2) the dataset increases with time as we receive data from real-lifeevents (e.g. credit card transactions). In fact, these settings are very common inthe industrial domain in which this thesis takes place
Ayassi, Reda. "Artificial intelligence techniques to improve quality of transmission estimation in optical networks". Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAS016.
Pełny tekst źródłaEstimating lightpath Quality of Transmission (QoT) is crucial in network design and service provisioning. Recent studies have turned to artificial intelligence (AI) techniques to improve the accuracy of QoT estimation using the data generated by the operational network. We distinguish four categories of solutions. The first category consists of building AI models to check the feasibility of a lightpath. The second category aims to predict the exact QoT performance in order to compete with analytical models. The third category uses AI to improve the performance of QoT estimation models by reducing the uncertainty on input parameters. The last category consists of improving the performance and generalization ability of AI-based solutions by retraining the models using the least amount of training samples through transfer learning techniques.QoT models can act as part of the digital twin of the operational network by simulating the impact of new network configurations before deploying them. However, they require a perfect knowledge of the network state, consisting of a set of optical parameters that have different levels of uncertainty. Using the QoT measurements collected by the network controller, we can have a feedback about the QoT estimation inaccuracy, which can potentially be addressed using ML based techniques. In this thesis, we study this issue of uncertainty in network parameters and consider three approaches that can improve the QoT estimation in this case. We propose different learning processes in each approach, and test their performance using simulation and real data.The first approach relies on optimizing the network parameters using the QoT estimation error as an objective function. We apply this approach through two learning processes to target QoT estimation tools based respectively on analytical model (GNPy) and Machine Learning (neural network). This approach can minimize the SNR estimation error to close to 0~dB on already trained network configuration, and reaches 0.3~dB estimation error on unseen network configurations.In the second approach, we retrain a neural network based model to adapt it to changes in QoT due to parameters uncertainty through Transfer Learning. We show how the model can relearn the new behavior of the network without searching for the correct values of the network parameters. We can reach up to 0.5~dB in validation error with only ten new training samples.The last approach consists of detecting parameter changes in response to failure events using reinforcement learning techniques. We consider two types of failure events. We show that the model can correctly classify the events with up to 93% of accuracy in small network topologies.Finally, we apply the first approach based on Bayesian Optimization algorithm to refine network parameters using data collected from a live network. We use data extracted from the north-bound interface of the network controller to build a network state based on the input data model of GNPy. Then, we apply our learning process on two transmission lines, which led to SNR estimation improvement up to 1.7~dB for the monitored services
Rouleau, Christian. "Perceptron sous forme duale tronquée et variantes". Thesis, Université Laval, 2007. http://www.theses.ulaval.ca/2007/24492/24492.pdf.
Pełny tekst źródłaMachine Learning is a part of the artificial intelligence and is used in many fields in science. It is divided into three categories : supervised, not supervised and by reinforcement. This master’s paper will relate only the supervised learning and more precisely the classification of datas. One of the first algorithms in classification, the perceptron, was proposed in the Sixties. We propose an alternative of this algorithm, which we call the truncated dual perceptron, which allows the stop of the algorithm according to a new criterion. We will compare this new alternative with other alternatives of the perceptron. Moreover, we will use the truncated dual perceptron to build more complex classifiers like the «Bayes Point Machines».
Zaiem, Mohamed Salah. "Informed Speech Self-supervised Representation Learning". Electronic Thesis or Diss., Institut polytechnique de Paris, 2024. http://www.theses.fr/2024IPPAT009.
Pełny tekst źródłaFeature learning has been driving machine learning advancement with the recently proposed methods getting progressively rid of handcrafted parts within the transformations from inputs to desired labels. Self-supervised learning has emerged within this context, allowing the processing of unlabeled data towards better performance on low-labeled tasks. The first part of my doctoral work is aimed towards motivating the choices in the speech selfsupervised pipelines learning the unsupervised representations. In this thesis, I first show how conditional-independence-based scoring can be used to efficiently and optimally select pretraining tasks tailored for the best performance on a target task. The second part of my doctoral work studies the evaluation and usage of pretrained self-supervised representations. I explore, first, the robustness of current speech self-supervision benchmarks to changes in the downstream modeling choices. I propose, second, fine-tuning approaches for better efficicency and generalization
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.
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.
Durand, Thibaut. "Weakly supervised learning for visual recognition". Electronic Thesis or Diss., Paris 6, 2017. http://www.theses.fr/2017PA066142.
Pełny tekst źródłaThis thesis studies the problem of classification of images, where the goal is to predict if a semantic category is present in the image, based on its visual content. To analyze complex scenes, it is important to learn localized representations. To limit the cost of annotation during training, we have focused on weakly supervised learning approaches. In this thesis, we propose several models that simultaneously classify and localize objects, using only global labels during training. The weak supervision significantly reduces the cost of full annotation, but it makes learning more challenging. The key issue is how to aggregate local scores - e.g. regions - into global score - e.g. image. The main contribution of this thesis is the design of new pooling functions for weakly supervised learning. In particular, we propose a “max + min” pooling function, which unifies many pooling functions. We describe how to use this pooling in the Latent Structured SVM framework as well as in convolutional networks. To solve the optimization problems, we present several solvers, some of which allow to optimize a ranking metric such as Average Precision. We experimentally show the interest of our models with respect to state-of-the-art methods, on ten standard image classification datasets, including the large-scale dataset ImageNet
Wolley, Chirine. "Apprentissage supervisé à partir des multiples annotateurs incertains". Thesis, Aix-Marseille, 2014. http://www.theses.fr/2014AIXM4070/document.
Pełny tekst źródłaIn supervised learning tasks, obtaining the ground truth label for each instance of the training dataset can be difficult, time-consuming and/or expensive. With the advent of infrastructures such as the Internet, an increasing number of web services propose crowdsourcing as a way to collect a large enough set of labels from internet users. The use of these services provides an exceptional facility to collect labels from anonymous annotators, and thus, it considerably simplifies the process of building labels datasets. Nonetheless, the main drawback of crowdsourcing services is their lack of control over the annotators and their inability to verify and control the accuracy of the labels and the level of expertise for each labeler. Hence, managing the annotators' uncertainty is a clue for learning from imperfect annotations. This thesis provides three algorithms when learning from multiple uncertain annotators. IGNORE generates a classifier that predict the label of a new instance and evaluate the performance of each annotator according to their level of uncertainty. X-Ignore, considers that the performance of the annotators both depends on their uncertainty and on the quality of the initial dataset to be annotated. Finally, ExpertS deals with the problem of annotators' selection when generating the classifier. It identifies experts annotators, and learn the classifier based only on their labels. We conducted in this thesis a large set of experiments in order to evaluate our models, both using experimental and real world medical data. The results prove the performance and accuracy of our models compared to previous state of the art solutions in this context
Santoni, Williams Alexius. "Apprentissage par mémorisation d'expériences dans la résolution des problèmes". Compiègne, 1989. http://www.theses.fr/1989COMPD160.
Pełny tekst źródłaBoussik, Amine. "Apprentissage profond non-supervisé : Application à la détection de situations anormales dans l’environnement du train autonome". Electronic Thesis or Diss., Valenciennes, Université Polytechnique Hauts-de-France, 2023. http://www.theses.fr/2023UPHF0040.
Pełny tekst źródłaThe thesis addresses the challenges of monitoring the environment and detecting anomalies, especially obstacles, for an autonomous freight train. Although traditionally, rail transport was under human supervision, autonomous trains offer potential advantages in terms of costs, time, and safety. However, their operation in complex environments poses significant safety concerns. Instead of a supervised approach that requires costly and limited annotated data, this research adopts an unsupervised technique, using unlabeled data to detect anomalies based on methods capable of identifying atypical behaviors.Two environmental surveillance models are presented : the first, based on a convolutional autoencoder (CAE), is dedicated to identifying obstacles on the main track; the second, an advanced version incorporating the vision transformer (ViT), focuses on overall environmental surveillance. Both employ unsupervised learning techniques for anomaly detection.The results show that the highlighted method offers relevant insights for monitoring the environment of the autonomous freight train, holding potential to enhance its reliability and safety. The use of unsupervised techniques thus showcases the utility and relevance of their adoption in an application context for the autonomous train
Boucheron, Stéphane. "Apprentissage et calculs". Montpellier 2, 1988. http://www.theses.fr/1988MON20251.
Pełny tekst źródłaTrenquier, Henri. "Analyse et explication par des techniques d'argumentation de modèles d'intelligence artificielle basés sur des données". Electronic Thesis or Diss., Toulouse 3, 2023. http://www.theses.fr/2023TOU30355.
Pełny tekst źródłaClassification is a very common task in Machine Learning (ML) and the ML models created to perform this task tend to reach human comparable accuracy, at the cost of transparency. The surge of such AI-based systems in the public's daily life has created a need for explainability. Abductive explanations are one of the most popular types of explanations that are provided for the purpose of explaining the behavior of complex ML models sometimes considered as black-boxes. They highlight feature-values that are sufficient for the model to make a prediction. In the literature, they are generated by exploring the whole feature space, which is unreasonable in practice. This thesis tackles this problem by introducing explanation functions that generate abductive explanations from a sample of instances. It shows that such functions should be defined with great care since they cannot satisfy two desirable properties at the same time, namely existence of explanations for every individual decision (success) and correctness of explanations (coherence). This thesis provides a parameterized family of argumentation-based explanation functions, each of which satisfies one of the two properties. It studies their formal properties and their experimental behaviour on different datasets
Tokmakov, Pavel. "Apprentissage à partir du mouvement". Thesis, Université Grenoble Alpes (ComUE), 2018. http://www.theses.fr/2018GREAM031/document.
Pełny tekst źródłaWeakly-supervised learning studies the problem of minimizing the amount of human effort required for training state-of-the-art models. This allows to leverage a large amount of data. However, in practice weakly-supervised methods perform significantly worse than their fully-supervised counterparts. This is also the case in deep learning, where the top-performing computer vision approaches remain fully-supervised, which limits their usage in real world applications. This thesis attempts to bridge the gap between weakly-supervised and fully-supervised methods by utilizing motion information. It also studies the problem of moving object segmentation itself, proposing one of the first learning-based methods for this task.We focus on the problem of weakly-supervised semantic segmentation. This is especially challenging due to the need to precisely capture object boundaries and avoid local optima, as for example segmenting the most discriminative parts. In contrast to most of the state-of-the-art approaches, which rely on static images, we leverage video data with object motion as a strong cue. In particular, our method uses a state-of-the-art video segmentation approach to segment moving objects in videos. The approximate object masks produced by this method are then fused with the semantic segmentation model learned in an EM-like framework to infer pixel-level semantic labels for video frames. Thus, as learning progresses, the quality of the labels improves automatically. We then integrate this architecture with our learning-based approach for video segmentation to obtain a fully trainable framework for weakly-supervised learning from videos.In the second part of the thesis we study unsupervised video segmentation, the task of segmenting all the objects in a video that move independently from the camera. This task presents challenges such as strong camera motion, inaccuracies in optical flow estimation and motion discontinuity. We address the camera motion problem by proposing a learning-based method for motion segmentation: a convolutional neural network that takes optical flow as input and is trained to segment objects that move independently from the camera. It is then extended with an appearance stream and a visual memory module to improve temporal continuity. The appearance stream capitalizes on the semantic information which is complementary to the motion information. The visual memory module is the key component of our approach: it combines the outputs of the motion and appearance streams and aggregates a spatio-temporal representation of the moving objects. The final segmentation is then produced based on this aggregated representation. The resulting approach obtains state-of-the-art performance on several benchmark datasets, outperforming the concurrent deep learning and heuristic-based methods
Luce-Vayrac, Pierre. "Open-Ended Affordance Discovery in Robotics Using Pertinent Visual Features". Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS670.
Pełny tekst źródłaScene understanding is a challenging problem in computer vision and robotics. It is traditionally addressed as an observation only process, in which the robot acquires data on its environment through its exteroceptive sensors, and processes it with specific algorithms (using for example Deep Neural Nets in modern approaches), to produce an interpretation: 'This is a chair because this looks like a chair'. For a robot to properly operate in its environment it needs to understand it. It needs to make sense of it in relation to its motivations and to its action capacities. We believe that scene understanding requires interaction with the environment, wherein perception, action and proprioception are integrated. The work described in this thesis explores this avenue which is inspired by work in Psychology and Neuroscience showing the strong link between action and perception. The concept of affordance has been introduced by James J. Gibson in 1977. It states that animals tend to perceive their environment through what they can accomplish with it (what it affords them), rather than solely through its intrinsic properties: 'This is a chair because I can sit on it.'. There is a variety of approaches studying affordances in robotics, largely agreeing on representing an affordance as a triplet (effect, (action, entity)), such that the effect effect is generated when action action is exerted on entity entity. However most authors use predefined features to describe the environment. We argue that building affordances on predefined features is actually defeating their purpose, by limiting them to the perceptual subspace generated by these features. Furthermore we affirm the impracticability of predefining a set of features general enough to describe entities in open-ended environments. In this thesis, we propose and develop an approach to enable a robot to learn affordances while simultaneously building relevant features describing the environment. To bootstrap affordance discovery we use a classical interaction loop. The robot executes a sequence of motor controls (action a) on a part of the environment ('object' o) described using a predefined set of initial features (color and size) and observes the result (effect e). By repeating this process, a dataset of (e, (a, o)) instances is built. This dataset is then used to train a predictive model of the affordance. To learn a new feature, the same loop is used, but instead of using a predefined set of descriptors of o we use a deep convolutional neural network (CNN). The raw data (2D images) of o is used as input and the effect e as expected output. The action is implicit as a different CNN is trained for each specific action. The training is self-supervised as the interaction data is produced by the robot itself. In order to correctly predict the affordance, the network must extract features which are directly relevant to the environment and the motor capabilities of the robot. Any feature learned by the method can then be added to the initial descriptors set. To achieve open-ended learning, whenever the agent executes the same action on two apparently similar objects (regarding a currently used set of features), but does not observe the same effect, it has to assume that it does not possess the relevant features to distinguish those objects in regard to this action, hence it needs to discover and learn these new features to reduce ambiguity. The robot will use the same approach to enrich its descriptor set. Several experiments on a real robotic setup showed that we can reach predictive performance similar to classical approaches which use predefined descriptors, while avoiding their limitation
Doquet, Guillaume. "Agnostic Feature Selection". Electronic Thesis or Diss., Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLS486.
Pełny tekst źródłaWith the advent of Big Data, databases whose size far exceed the human scale are becoming increasingly common. The resulting overabundance of monitored variables (friends on a social network, movies watched, nucleotides coding the DNA, monetary transactions...) has motivated the development of Dimensionality Reduction (DR) techniques. A DR algorithm such as Principal Component Analysis (PCA) or an AutoEncoder typically combines the original variables into new features fewer in number, such that most of the information in the dataset is conveyed by the extracted feature set.A particular subcategory of DR is formed by Feature Selection (FS) methods, which directly retain the most important initial variables. How to select the best candidates is a hot topic at the crossroad of statistics and Machine Learning. Feature importance is usually inferred in a supervised context, where variables are ranked according to their usefulness for predicting a specific target feature.The present thesis focuses on the unsupervised context in FS, i.e. the challenging situation where no prediction goal is available to help assess feature relevance. Instead, unsupervised FS algorithms usually build an artificial classification goal and rank features based on their helpfulness for predicting this new target, thus falling back on the supervised context. Additionally, the efficiency of unsupervised FS approaches is typically also assessed in a supervised setting.In this work, we propose an alternate model combining unsupervised FS with data compression. Our Agnostic Feature Selection (AgnoS) algorithm does not rely on creating an artificial target and aims to retain a feature subset sufficient to recover the whole original dataset, rather than a specific variable. As a result, AgnoS does not suffer from the selection bias inherent to clustering-based techniques.The second contribution of this work( Agnostic Feature Selection, G. Doquet & M. Sebag, ECML PKDD 2019) is to establish both the brittleness of the standard supervised evaluation of unsupervised FS, and the stability of the new proposed AgnoS
Geiler, Louis. "Deep learning for churn prediction". Electronic Thesis or Diss., Université Paris Cité, 2022. http://www.theses.fr/2022UNIP7333.
Pełny tekst źródłaThe problem of churn prediction has been traditionally a field of study for marketing. However, in the wake of the technological advancements, more and more data can be collected to analyze the customers behaviors. This manuscript has been built in this frame, with a particular focus on machine learning. Thus, we first looked at the supervised learning problem. We have demonstrated that logistic regression, random forest and XGBoost taken as an ensemble offer the best results in terms of Area Under the Curve (AUC) among a wide range of traditional machine learning approaches. We also have showcased that the re-sampling approaches are solely efficient in a local setting and not a global one. Subsequently, we aimed at fine-tuning our prediction by relying on customer segmentation. Indeed,some customers can leave a service because of a cost that they deem to high, and other customers due to a problem with the customer’s service. Our approach was enriched with a novel deep neural network architecture, which operates with both the auto-encoders and the k-means approach. Going further, we focused on self-supervised learning in the tabular domain. More precisely, the proposed architecture was inspired by the work on the SimCLR approach, where we altered the architecture with the Mean-Teacher model from semi-supervised learning. We showcased through the win matrix the superiority of our approach with respect to the state of the art. Ultimately, we have proposed to apply what we have built in this manuscript in an industrial setting, the one of Brigad. We have alleviated the company churn problem with a random forest that we optimized through grid-search and threshold optimization. We also proposed to interpret the results with SHAP (SHapley Additive exPlanations)
Gharroudi, Ouadie. "Ensemble multi-label learning in supervised and semi-supervised settings". Thesis, Lyon, 2017. http://www.theses.fr/2017LYSE1333/document.
Pełny tekst źródłaMulti-label learning is a specific supervised learning problem where each instance can be associated with multiple target labels simultaneously. Multi-label learning is ubiquitous in machine learning and arises naturally in many real-world applications such as document classification, automatic music tagging and image annotation. In this thesis, we formulate the multi-label learning as an ensemble learning problem in order to provide satisfactory solutions for both the multi-label classification and the feature selection tasks, while being consistent with respect to any type of objective loss function. We first discuss why the state-of-the art single multi-label algorithms using an effective committee of multi-label models suffer from certain practical drawbacks. We then propose a novel strategy to build and aggregate k-labelsets based committee in the context of ensemble multi-label classification. We then analyze the effect of the aggregation step within ensemble multi-label approaches in depth and investigate how this aggregation impacts the prediction performances with respect to the objective multi-label loss metric. We then address the specific problem of identifying relevant subsets of features - among potentially irrelevant and redundant features - in the multi-label context based on the ensemble paradigm. Three wrapper multi-label feature selection methods based on the Random Forest paradigm are proposed. These methods differ in the way they consider label dependence within the feature selection process. Finally, we extend the multi-label classification and feature selection problems to the semi-supervised setting and consider the situation where only few labelled instances are available. We propose a new semi-supervised multi-label feature selection approach based on the ensemble paradigm. The proposed model combines ideas from co-training and multi-label k-labelsets committee construction in tandem with an inner out-of-bag label feature importance evaluation. Satisfactorily tested on several benchmark data, the approaches developed in this thesis show promise for a variety of applications in supervised and semi-supervised multi-label learning
Sokolovska, Nataliya. "Contributions à l'estimation de modèles probabilistes discriminants : apprentissage semi-supervisé et sélection de caractéristiques". Phd thesis, Paris, Télécom ParisTech, 2010. https://pastel.hal.science/pastel-00006257.
Pełny tekst źródłaIn this thesis, we investigate the use of parametric probabilistic models for classification tasks in the domain of natural lang uage processing. We focus in particular on discriminative models, such as logistic regression and its generalization, conditional random fields (CRFs). Discriminative probabilistic models design directly conditional probability of a class given an observation. The logistic regression has been widely used due to its simplicity and effectiveness. Conditional random fields allow to take structural dependencies into consideration and therefore are used for structured output prediction. In this study, we address two aspects of modern machine learning, namely , semi-supervised learning and model selection, in the context of CRFs. The contribution of this thesis is twofold. First, we consider the framework of semi -supervised learning and propose a novel semi-supervised estimator and show that it is preferable to the standard logistic regression. Second, we study model selection approaches for discriminative models, in particular for CRFs and propose to penalize the CRFs with the elastic net. Since the penalty term is not differentiable in zero, we consider coordinate-wise optimization. The comparison with the performances of other methods demonstrates competitiveness of the CRFs penalized by the elastic net
Sokolovska, Nataliya. "Contributions à l'estimation de modèles probabilistes discriminants : apprentissage semi-supervisé et sélection de caractéristiques". Phd thesis, Ecole nationale supérieure des telecommunications - ENST, 2010. http://tel.archives-ouvertes.fr/tel-00557662.
Pełny tekst źródłaDenize, Julien. "Self-supervised representation learning and applications to image and video analysis". Electronic Thesis or Diss., Normandie, 2023. http://www.theses.fr/2023NORMIR37.
Pełny tekst źródłaIn this thesis, we develop approaches to perform self-supervised learning for image and video analysis. Self-supervised representation learning allows to pretrain neural networks to learn general concepts without labels before specializing in downstream tasks faster and with few annotations. We present three contributions to self-supervised image and video representation learning. First, we introduce the theoretical paradigm of soft contrastive learning and its practical implementation called Similarity Contrastive Estimation (SCE) connecting contrastive and relational learning for image representation. Second, SCE is extended to global temporal video representation learning. Lastly, we propose COMEDIAN a pipeline for local-temporal video representation learning for transformers. These contributions achieved state-of-the-art results on multiple benchmarks and led to several academic and technical published contributions
Jouffroy, Emma. "Développement de modèles non supervisés pour l'obtention de représentations latentes interprétables d'images". Electronic Thesis or Diss., Bordeaux, 2024. http://www.theses.fr/2024BORD0050.
Pełny tekst źródłaThe Laser Megajoule (LMJ) is a large research device that simulates pressure and temperature conditions similar to those found in stars. During experiments, diagnostics are guided into an experimental chamber for precise positioning. To minimize the risks associated with human error in such an experimental context, the automation of an anti-collision system is envisaged. This involves the design of machine learning tools offering reliable decision levels based on the interpretation of images from cameras positioned in the chamber. Our research focuses on probabilistic generative neural methods, in particular variational auto-encoders (VAEs). The choice of this class of models is linked to the fact that it potentially enables access to a latent space directly linked to the properties of the objects making up the observed scene. The major challenge is to study the design of deep network models that effectively enable access to such a fully informative and interpretable representation, with a view to system reliability. The probabilistic formalism intrinsic to VAE allows us, if we can trace back to such a representation, to access an analysis of the uncertainties of the encoded information
Durand, Thibaut. "Weakly supervised learning for visual recognition". Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066142/document.
Pełny tekst źródłaThis thesis studies the problem of classification of images, where the goal is to predict if a semantic category is present in the image, based on its visual content. To analyze complex scenes, it is important to learn localized representations. To limit the cost of annotation during training, we have focused on weakly supervised learning approaches. In this thesis, we propose several models that simultaneously classify and localize objects, using only global labels during training. The weak supervision significantly reduces the cost of full annotation, but it makes learning more challenging. The key issue is how to aggregate local scores - e.g. regions - into global score - e.g. image. The main contribution of this thesis is the design of new pooling functions for weakly supervised learning. In particular, we propose a “max + min” pooling function, which unifies many pooling functions. We describe how to use this pooling in the Latent Structured SVM framework as well as in convolutional networks. To solve the optimization problems, we present several solvers, some of which allow to optimize a ranking metric such as Average Precision. We experimentally show the interest of our models with respect to state-of-the-art methods, on ten standard image classification datasets, including the large-scale dataset ImageNet
Gal, Jocelyn. "Application d’algorithmes de machine learning pour l’exploitation de données omiques en oncologie". Electronic Thesis or Diss., Université Côte d'Azur (ComUE), 2019. http://theses.univ-cotedazur.fr/2019AZUR6026.
Pełny tekst źródłaThe development of computer science in medicine and biology has generated a large volume of data. The complexity and the amount of information to be integrated for optimal decision-making in medicine have largely exceeded human capacities. These data includes demographic, clinical and radiological variables, but also biological variables and particularly omics (genomics, proteomics, transcriptomics and metabolomics) characterized by a large number of measured variables relatively to a generally small number of patients. Their analysis represents a real challenge as they are frequently "noisy" and associated with situations of multi-colinearity. Nowadays, computational power makes it possible to identify clinically relevant models within these sets of data by using machine learning algorithms. Through this thesis, our goal is to apply supervised and unsupervised learning methods, to large biological data, in order to participate in the optimization of the classification and therapeutic management of patients with various types of cancer. In the first part of this work a supervised learning method is applied to germline immunogenetic data to predict the efficacy and toxicity of immune checkpoint inhibitor therapy. In the second part, different unsupervised learning methods are compared to evaluate the contribution of metabolomics in the diagnosis and management of breast cancer. Finally, the third part of this work aims to expose the contribution that simulated therapeutic trials can make in biomedical research. The application of machine learning methods in oncology offers new perspectives to clinicians allowing them to make diagnostics faster and more accurately, or to optimize therapeutic management in terms of efficacy and toxicity
Tamaazousti, Youssef. "Vers l’universalité des représentations visuelle et multimodales". Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLC038/document.
Pełny tekst źródłaBecause of its key societal, economic and cultural stakes, Artificial Intelligence (AI) is a hot topic. One of its main goal, is to develop systems that facilitates the daily life of humans, with applications such as household robots, industrial robots, autonomous vehicle and much more. The rise of AI is highly due to the emergence of tools based on deep neural-networks which make it possible to simultaneously learn, the representation of the data (which were traditionally hand-crafted), and the task to solve (traditionally learned with statistical models). This resulted from the conjunction of theoretical advances, the growing computational capacity as well as the availability of many annotated data. A long standing goal of AI is to design machines inspired humans, capable of perceiving the world, interacting with humans, in an evolutionary way. We categorize, in this Thesis, the works around AI, in the two following learning-approaches: (i) Specialization: learn representations from few specific tasks with the goal to be able to carry out very specific tasks (specialized in a certain field) with a very good level of performance; (ii) Universality: learn representations from several general tasks with the goal to perform as many tasks as possible in different contexts. While specialization was extensively explored by the deep-learning community, only a few implicit attempts were made towards universality. Thus, the goal of this Thesis is to explicitly address the problem of improving universality with deep-learning methods, for image and text data. We have addressed this topic of universality in two different forms: through the implementation of methods to improve universality (“universalizing methods”); and through the establishment of a protocol to quantify its universality. Concerning universalizing methods, we proposed three technical contributions: (i) in a context of large semantic representations, we proposed a method to reduce redundancy between the detectors through, an adaptive thresholding and the relations between concepts; (ii) in the context of neural-network representations, we proposed an approach that increases the number of detectors without increasing the amount of annotated data; (iii) in a context of multimodal representations, we proposed a method to preserve the semantics of unimodal representations in multimodal ones. Regarding the quantification of universality, we proposed to evaluate universalizing methods in a Transferlearning scheme. Indeed, this technical scheme is relevant to assess the universal ability of representations. This also led us to propose a new framework as well as new quantitative evaluation criteria for universalizing methods
Cherfi, Zohra Leila. "Diagnostic de systèmes complexes en contextes non supervisé et partiellement supervisé : application au circuit de voie ferroviaire". Phd thesis, UNIVERSITE DE TECHNOLOGIE DE COMPIEGNE, 2011. http://tel.archives-ouvertes.fr/tel-01006538.
Pełny tekst źródłaBannour, Sondes. "Apprentissage interactif de règles d'extraction d'information textuelle". Thesis, Sorbonne Paris Cité, 2015. http://www.theses.fr/2015USPCD113/document.
Pełny tekst źródłaNon communiqué
Aversano, Gianmarco. "Development of physics-based reduced-order models for reacting flow applications". Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLC095/document.
Pełny tekst źródłaWith the final objective being to developreduced-order models for combustion applications,unsupervised and supervised machine learningtechniques were tested and combined in the workof the present Thesis for feature extraction and theconstruction of reduced-order models. Thus, the applicationof data-driven techniques for the detection offeatures from turbulent combustion data sets (directnumerical simulation) was investigated on two H2/COflames: a spatially-evolving (DNS1) and a temporallyevolvingjet (DNS2). Methods such as Principal ComponentAnalysis (PCA), Local Principal ComponentAnalysis (LPCA), Non-negative Matrix Factorization(NMF) and Autoencoders were explored for this purpose.It was shown that various factors could affectthe performance of these methods, such as the criteriaemployed for the centering and the scaling of theoriginal data or the choice of the number of dimensionsin the low-rank approximations. A set of guidelineswas presented that can aid the process ofidentifying meaningful physical features from turbulentreactive flows data. Data compression methods suchas Principal Component Analysis (PCA) and variationswere combined with interpolation methods suchas Kriging, for the construction of computationally affordablereduced-order models for the prediction ofthe state of a combustion system for unseen operatingconditions or combinations of model input parametervalues. The methodology was first tested forthe prediction of 1D flames with an increasing numberof input parameters (equivalence ratio, fuel compositionand inlet temperature), with variations of the classicPCA approach, namely constrained PCA and localPCA, being applied to combustion cases for the firsttime in combination with an interpolation technique.The positive outcome of the study led to the applicationof the proposed methodology to 2D flames withtwo input parameters, namely fuel composition andinlet velocity, which produced satisfactory results. Alternativesto the chosen unsupervised and supervisedmethods were also tested on the same 2D data.The use of non-negative matrix factorization (NMF) forlow-rank approximation was investigated because ofthe ability of the method to represent positive-valueddata, which helps the non-violation of important physicallaws such as positivity of chemical species massfractions, and compared to PCA. As alternative supervisedmethods, the combination of polynomial chaosexpansion (PCE) and Kriging and the use of artificialneural networks (ANNs) were tested. Results from thementioned work paved the way for the developmentof a digital twin of a combustion furnace from a setof 3D simulations. The combination of PCA and Krigingwas also employed in the context of uncertaintyquantification (UQ), specifically in the bound-to-bounddata collaboration framework (B2B-DC), which led tothe introduction of the reduced-order B2B-DC procedureas for the first time the B2B-DC was developedin terms of latent variables and not in terms of originalphysical variables
Ghesmoune, Mohammed. "Apprentissage non supervisé de flux de données massives : application aux Big Data d'assurance". Thesis, Sorbonne Paris Cité, 2016. http://www.theses.fr/2016USPCD061/document.
Pełny tekst źródłaThe research outlined in this thesis concerns the development of approaches based on growing neural gas (GNG) for clustering of data streams. We propose three algorithmic extensions of the GNG approaches: sequential, distributed and parallel, and hierarchical; as well as a model for scalability using MapReduce and its application to learn clusters from the real insurance Big Data in the form of a data stream. We firstly propose the G-Stream method. G-Stream, as a “sequential" clustering method, is a one-pass data stream clustering algorithm that allows us to discover clusters of arbitrary shapes without any assumptions on the number of clusters. G-Stream uses an exponential fading function to reduce the impact of old data whose relevance diminishes over time. The links between the nodes are also weighted. A reservoir is used to hold temporarily the distant observations in order to reduce the movements of the nearest nodes to the observations. The batchStream algorithm is a micro-batch based method for clustering data streams which defines a new cost function taking into account that subsets of observations arrive in discrete batches. The minimization of this function, which leads to a topological clustering, is carried out using dynamic clusters in two steps: an assignment step which assigns each observation to a cluster, followed by an optimization step which computes the prototype for each node. A scalable model using MapReduce is then proposed. It consists of decomposing the data stream clustering problem into the elementary functions, Map and Reduce. The observations received in each sub-dataset (within a time interval) are processed through deterministic parallel operations (Map and Reduce) to produce the intermediate states or the final clusters. The batchStream algorithm is validated on the insurance Big Data. A predictive and analysis system is proposed by combining the clustering results of batchStream with decision trees. The architecture and these different modules from the computational core of our Big Data project, called Square Predict. GH-Stream for both visualization and clustering tasks is our third extension. The presented approach uses a hierarchical and topological structure for both of these tasks
Dalsasso, Emanuele. "Deep learning for SAR imagery : from denoising to scene understanding". Electronic Thesis or Diss., Institut polytechnique de Paris, 2022. http://www.theses.fr/2022IPPAT008.
Pełny tekst źródłaSynthetic Aperture Radars (SARs) can collect data for Earth Observation purposes regardless of the daylight or cloud cover. Nowadays, thanks to the Copernicus program of the European Space Agency, a huge amount of SAR data is freely available. However, the exploitation of satellite SAR images is limited by the presence of strong fluctuations in the backscattered signal. Indeed, SAR images are corrupted by speckle, a phenomenon inherent to coherent imaging systems. In this Ph.D thesis, we aim to improve the interpretation of SAR images by resorting to speckle reduction techniques. Existing approaches are based on Goodman’s model, which describes the speckle component as a spatially uncorrelated multiplicative noise. In the computer vision field, denoising methods relying on Convolutional Neural Networks (deep learning approaches) have led to great improvements and provide nowadays state-of-the-art results. We propose to use deep learning-based denoising techniques to reduce speckle from SAR images (despeckling methods). At first, we study the adaptation of supervised techniques that minimize a certain distance between the estimation provided by the CNN and a reference image, also called “groundtruth”. We propose to create a dataset of reference images by averaging multi-temporal images acquired over the same area. Pairs of reference and corrupted images can be generated by synthetizing speckle following Goodman’s model. However, in real images the speckle component is spatially correlated which typically requires subsampling these images by a factor 2 to reduce the spatial correlations, which also degrades the spatial resolution. Given the limits of supervised approaches and inspired by noise2noise, a self-supervised denoising method, we propose to train our networks directly on actual SAR images. The principle of self-supervised denoising methods is the following: if a signal contains a deterministic component and a random component, then a network trained to predict a new signal realization from a first independent signal realization will only predict the deterministic component, i.e., the underlying scene, thereby suppressing the speckle. In the method we have developed, SAR2SAR, we leverage multi-temporal SAR series to obtain independent realizations of the same scene, under the hypothesis of temporally decorrelated speckle. Changes are compensated by devising an iterative training strategy. SAR2SAR is thus trained directly on images with spatially correlated speckle and can readily be applied on SAR images without subsampling, providing high-quality results. The training of SAR2SAR is quite heavy: it is articulated in several steps to compensate changes and a dataset comprising stacks of images must be built. With our approach “MERLIN”, we alleviate the training by proposing a single-image learning strategy. Indeed, in single-look-complex SAR images, real and imaginary parts are mutually independent and can benaturally exploited to train CNNs with self-supervision. We show the potential of this training framework for three imaging modalities, different in terms of spatial resolution, textures, and speckle spatial correlation. For the sake of open science, the code associated to each algorithm developed is made freely available
Liu, Jingshu. "Unsupervised cross-lingual representation modeling for variable length phrases". Thesis, Nantes, 2020. http://www.theses.fr/2020NANT4009.
Pełny tekst źródłaSignificant advances have been achieved in bilingual word-level alignment from comparable corpora, yet the challenge remains for phrase-level alignment. Traditional methods to phrase alignment can only handle phrase of equal length, while word embedding based approaches learn phrase embeddings as individual vocabulary entries suffer from the data sparsity and cannot handle out of vocabulary phrases. Since bilingual alignment is a vector comparison task, phrase representation plays a key role. In this thesis, we study the approaches for unified phrase modeling and cross-lingual phrase alignment, ranging from co-occurrence models to most recent neural state-of-the-art approaches. We review supervised and unsupervised frameworks for modeling cross-lingual phrase representations. Two contributions are proposed in this work. First, a new architecture called tree-free recursive neural network (TF-RNN) for modeling phrases of variable length which, combined with a wrapped context prediction training objective, outperforms the state-of-the-art approaches on monolingual phrase synonymy task with only plain text training data. Second, for cross-lingual modeling, we propose to incorporate an architecture derived from TF-RNN in an encoder-decoder model with a pseudo back translation mechanism inspired by unsupervised neural machine translation. Our proposition improves significantly bilingual alignment of different length phrases
Ebadzadeh, Mohamad Mehdi. "Modélisation des voies réflexes et cérébelleuses, permettant le calcul des fonctions inverses : application à la commande d'un actionneur à deux muscles pneumatiques". Paris, ENST, 2004. http://www.theses.fr/2004ENST0046.
Pełny tekst źródłaBoniol, Paul. "Detection of anomalies and identification of their precursors in large data series collections". Electronic Thesis or Diss., Université Paris Cité, 2021. http://www.theses.fr/2021UNIP5206.
Pełny tekst źródłaExtensive collections of data series are becoming a reality in a large number of scientific and social domains. There is, therefore, a growing interest and need to elaborate efficient techniques to analyze and process these data, such as in finance, environmental sciences, astrophysics, neurosciences, engineering. Informally, a data series is an ordered sequence of points or values. Once these series are collected and available, users often need to query them. These queries can be simple, such as the selection of time interval, but also complex, such as the similarities search or the detection of anomalies, often synonymous with malfunctioning of the system under study, or sudden and unusual evolution likely undesired. This last type of analysis represents a crucial problem for applications in a wide range of domains, all sharing the same objective: to detect anomalies as soon as possible to avoid critical events. Therefore, in this thesis, we address the following three objectives: (i) retrospective unsupervised subsequence anomaly detection in data series. (ii) unsupervised detection of anomalies in data streams. (iii) classification explanation of known anomalies in data series in order to identify possible precursors. This manuscript first presents the industrial context that motivated this thesis, fundamental definitions, a taxonomy of data series, and state-of-the-art anomaly detection methods. We then present our contributions along the three axes mentioned above. First, we describe two original solutions, NormA (that aims to build a weighted set of subsequences that represent the different behaviors of the data series) and Series2Graph (that transform the data series in a directed graph), for the task of unsupervised detection of anomalous subsequences in static data series. Secondly, we present the SAND (inspired from NormA) method for unsupervised detection of anomalous subsequences in data streams. Thirdly, we address the problem of the supervised identification of precursors. We subdivide this task into two generic problems: the supervised classification of time series and the explanation of this classification’s results by identifying discriminative subsequences. Finally, we illustrate the applicability and interest of our developments through an application concerning the identification of undesirable vibration precursors occurring in water supply pumps in the French nuclear power plants of EDF
Albardan, Mahmoud. "Combinaison robuste à la dépendance entre classifieurs dans un contexte d’apprentissage décentralisé". Thesis, Lille 1, 2018. http://www.theses.fr/2018LIL1I050/document.
Pełny tekst źródłaMachine learning is a rapidly growing field of science concerning both the number of methods used and the amount of data available for users. Classification is thus affected by these changes. The presence of a large number of classification algorithms thus encourages the creation of global systems that are based on classifier ensembles, in the purpose of providing efficient solutions to complex classification problems. This is the main motivation behind our thesis whose subject is the study of multi-classifiers systems. A multi-classifiers system is a set of classifiers whose decisions is aggregated according to a specific architecture and using a combination rule. There are different types architectures such as parallel, sequential or hybrid architectures. In this thesis, we are only interested in classifier ensembles having a parallel architecture. Briefly, the purpose of my research is then the design of multi-classifiers systems to improve classification performance and to offer certain level of robustness. However, the design of such systems, that can be seen as a fusion of different sources of information and which will be trained on correlated learning examples, generates dependence in the individual decisions of classifiers and consequently impose the creation of classifier ensembles that are adapted to dependency between individual classifiers. Thus, we propose two approaches that are the main contributions of this thesis. The first one is a possibilistic approach based on a well-known combination rule in fuzzy logic, the t-norm, while the second is a probabilistic approach based on a copula function which are models of dependence between random variables
Thépaut, Solène. "Problèmes de clustering liés à la synchronie en écologie : estimation de rang effectif et détection de ruptures sur les arbres". Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLS477/document.
Pełny tekst źródłaIn the view of actual global changes widely caused by human activities, it becomes urgent to understand the drivers of communities' stability. Synchrony between time series of abundances is one of the most important mechanisms. This thesis offers three different angles in order to answer different questions linked to interspecific and spatial synchrony. The works presented find applications beyond the ecological frame. A first chapter is dedicated to the estimation of effective rank of matrices in ℝ or ℂ. We offer tools allowing to measure the synchronisation rate of observations matrices. In the second chapter, we base on the existing work on change-points detection problem on chains in order to offer algorithms which detects change-points on trees. The methods can be used with most data that have to be represented as a tree. In order to study the link between interspecific synchrony and long term tendencies or traits of butterflies species, we offer in the last chapter adaptation of clustering and supervised machine learning methods, such as Random Forest or Artificial Neural Networks to ecological data
Othmani-Guibourg, Mehdi. "Supervised learning for distribution of centralised multiagent patrolling strategies". Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS534.
Pełny tekst źródłaFor nearly two decades, patrolling has received significant attention from the multiagent community. Multiagent patrolling (MAP) consists in modelling a patrol task to optimise as a multiagent system. The problem of optimising a patrol task is to distribute the most efficiently agents over the area to patrol in space and time, which constitutes a decision-making problem. A range of algorithms based on reactive, cognitive, reinforcement learning, centralised and decentralised strategies, amongst others, have been developed to make such a task ever more efficient. However, the existing patrolling-specific approaches based on supervised learning were still at preliminary stages, although a few works addressed this issue. Central to supervised learning, which is a set of methods and tools that allow inferring new knowledge, is the idea of learning a function mapping any input to an output from a sample of data composed of input-output pairs; learning, in this case, enables the system to generalise to new data never observed before. Until now, the best online MAP strategy, namely without precalculation, has turned out to be a centralised strategy with a coordinator. However, as for any centralised decision process in general, such a strategy is hardly scalable. The purpose of this work is then to develop and implement a new methodology aiming at turning any high-performance centralised strategy into a distributed strategy. Indeed, distributed strategies are by design resilient, more adaptive to changes in the environment, and scalable. In doing so, the centralised decision process, generally represented in MAP by a coordinator, is distributed into patrolling agents by means of supervised learning methods, so that each agent of the resultant distributed strategy tends to capture a part of the algorithm executed by the centralised decision process. The outcome is a new distributed decision-making algorithm based on machine learning. In this dissertation therefore, such a procedure of distribution of centralised strategy is established, then concretely implemented using some artificial neural networks architectures. By doing so, after having exposed the context and motivations of this work, we pose the problematic that led our study. The main multiagent strategies devised until now as part of MAP are then described, particularly a high-performance coordinated strategy, which is the centralised strategy studied in this work, as well as a simple decentralised strategy used as reference for decentralised strategies. Among others, some existing strategies based on supervised learning are also described. Thereafter, the model as well as certain of key concepts of MAP are defined. We also define the methodology laid down to address and study this problematic. This methodology comes in the form of a procedure that allows decentralising any centralised strategy by means of supervised learning. Then, the software ecosystem we developed for the needs of this work is also described, particularly PyTrol a discrete-time simulator dedicated to MAP developed with the aim of performing MAP simulation, to assess strategies and generate data, and MAPTrainer, a framework hinging on the PyTorch machine learning library, dedicated to research in machine learning in the context of MAP
Franceschi, Jean-Yves. "Apprentissage de représentations et modèles génératifs profonds dans les systèmes dynamiques". Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS014.
Pełny tekst źródłaThe recent rise of deep learning has been motivated by numerous scientific breakthroughs, particularly regarding representation learning and generative modeling. However, most of these achievements have been obtained on image or text data, whose evolution through time remains challenging for existing methods. Given their importance for autonomous systems to adapt in a constantly evolving environment, these challenges have been actively investigated in a growing body of work. In this thesis, we follow this line of work and study several aspects of temporality and dynamical systems in deep unsupervised representation learning and generative modeling. Firstly, we present a general-purpose deep unsupervised representation learning method for time series tackling scalability and adaptivity issues arising in practical applications. We then further study in a second part representation learning for sequences by focusing on structured and stochastic spatiotemporal data: videos and physical phenomena. We show in this context that performant temporal generative prediction models help to uncover meaningful and disentangled representations, and conversely. We highlight to this end the crucial role of differential equations in the modeling and embedding of these natural sequences within sequential generative models. Finally, we more broadly analyze in a third part a popular class of generative models, generative adversarial networks, under the scope of dynamical systems. We study the evolution of the involved neural networks with respect to their training time by describing it with a differential equation, allowing us to gain a novel understanding of this generative model
Narassiguin, Anil. "Apprentissage Ensembliste, Étude comparative et Améliorations via Sélection Dynamique". Thesis, Lyon, 2018. http://www.theses.fr/2018LYSE1075/document.
Pełny tekst źródłaEnsemble methods has been a very popular research topic during the last decade. Their success arises largely from the fact that they offer an appealing solution to several interesting learning problems, such as improving prediction accuracy, feature selection, metric learning, scaling inductive algorithms to large databases, learning from multiple physically distributed data sets, learning from concept-drifting data streams etc. In this thesis, we first present an extensive empirical comparison between nineteen prototypical supervised ensemble learning algorithms, that have been proposed in the literature, on various benchmark data sets. We not only compare their performance in terms of standard performance metrics (Accuracy, AUC, RMS) but we also analyze their kappa-error diagrams, calibration and bias-variance properties. We then address the problem of improving the performances of ensemble learning approaches with dynamic ensemble selection (DES). Dynamic pruning is the problem of finding given an input x, a subset of models among the ensemble that achieves the best possible prediction accuracy. The idea behind DES approaches is that different models have different areas of expertise in the instance space. Most methods proposed for this purpose estimate the individual relevance of the base classifiers within a local region of competence usually given by the nearest neighbours in the euclidean space. We propose and discuss two novel DES approaches. The first, called ST-DES, is designed for decision tree based ensemble models. This method prunes the trees using an internal supervised tree-based metric; it is motivated by the fact that in high dimensional data sets, usual metrics like euclidean distance suffer from the curse of dimensionality. The second approach, called PCC-DES, formulates the DES problem as a multi-label learning task with a specific loss function. Labels correspond to the base classifiers and multi-label training examples are formed based on the ability of each classifier to correctly classify each original training example. This allows us to take advantage of recent advances in the area of multi-label learning. PCC-DES works on homogeneous and heterogeneous ensembles as well. Its advantage is to explicitly capture the dependencies between the classifiers predictions. These algorithms are tested on a variety of benchmark data sets and the results demonstrate their effectiveness against competitive state-of-the-art alternatives
Combes, Richard. "Mécanismes auto-organisants dans les réseaux sans fil". Paris 6, 2013. http://www.theses.fr/2013PA066028.
Pełny tekst źródłaIn this thesis we study the design, modeling and performance evaluation of mechanisms which can manage wireless networks autonomously (self-organizing mechanisms). We recall the technological context, and the required mathematical tools are introduced concisely: queuing theory, point processes, information theory, stochastic approximation, Markov decisions processes and reinforcement learning. In the first part, we study opportunistic scheduling. We are interested in their performance evaluation and their use to perform coverage-capacity optimization. Physical layer phenomena such as channel fading, interference, receiver structure and practical modulation and coding schemes are taken into account. In the second part, an algorithm for automatic load balancing is presented. The dynamical arrivals and departures of users are taken into account. For stationary traffic, the convergence of the mechanism to the optimal configuration is shown using stochastic approximation theorems. For non-stationary traffic, numerical experiments suggest that the mechanism is able to adapt itself to daily traffic patterns. In the third part, we study relay-enhanced networks. Based on a queuing analysis, a simple formula for network dimensioning is given. It is valid for the most general traffic model (stationary ergodic input). The load balancing mechanism is extended to relay-enhanced networks. A dynamical load balancing algorithm based on reinforcement is studied