Дисертації з теми "Apprentissage par renforcement non supervisé"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Apprentissage par renforcement non supervisé".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
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.
Повний текст джерелаRobots 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
Tarbouriech, Jean. "Goal-oriented exploration for reinforcement learning." Electronic Thesis or Diss., Université de Lille (2022-....), 2022. http://www.theses.fr/2022ULILB014.
Повний текст джерелаLearning to reach goals is a competence of high practical relevance to acquire for intelligent agents. For instance, this encompasses many navigation tasks ("go to target X"), robotic manipulation ("attain position Y of the robotic arm"), or game-playing scenarios ("win the game by fulfilling objective Z"). As a living being interacting with the world, I am constantly driven by goals to reach, varying in scope and difficulty.Reinforcement Learning (RL) holds the promise to frame and learn goal-oriented behavior. Goals can be modeled as specific configurations of the environment that must be attained via sequential interaction and exploration of the unknown environment. Although various deep RL algorithms have been proposed for goal-oriented RL, existing methods often lack principled understanding, sample efficiency and general-purpose effectiveness. In fact, very limited theoretical analysis of goal-oriented RL was available, even in the basic scenario of finitely many states and actions.We first focus on a supervised scenario of goal-oriented RL, where a goal state to be reached in minimum total expected cost is provided as part of the problem definition. After formalizing the online learning problem in this setting often known as Stochastic Shortest Path (SSP), we introduce two no-regret algorithms (one is the first available in the literature, the other attains nearly optimal guarantees).Beyond training our RL agent to solve only one task, we then aspire that it learns to autonomously solve a wide variety of tasks, in the absence of any reward supervision. In this challenging unsupervised RL scenario, we advocate to "Set Your Own Goals" (SYOG), which suggests the agent to learn the ability to intrinsically select and reach its own goal states. We derive finite-time guarantees of this popular heuristic in various settings, each with its specific learning objective and technical challenges. As an illustration, we propose a rigorous analysis of the algorithmic principle of targeting "uncertain" goals which we also anchor in deep RL.The main focus and contribution of this thesis are to instigate a principled analysis of goal-oriented exploration in RL, both in the supervised and unsupervised scenarios. We hope that it helps suggest promising research directions to improve the interpretability and sample efficiency of goal-oriented RL algorithms in practical applications
Merckling, Astrid. "Unsupervised pretraining of state representations in a rewardless environment." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS141.
Повний текст джерелаThis 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
Castanet, Nicolas. "Automatic state representation and goal selection in unsupervised reinforcement learning." Electronic Thesis or Diss., Sorbonne université, 2025. http://www.theses.fr/2025SORUS005.
Повний текст джерелаIn the past few years, Reinforcement Learning (RL) achieved tremendous success by training specialized agents owning the ability to drastically exceed human performance in complex games like Chess or Go, or in robotics applications. These agents often lack versatility, requiring human engineering to design their behavior for specific tasks with predefined reward signal, limiting their ability to handle new circumstances. This agent's specialization results in poor generalization capabilities, which make them vulnerable to small variations of external factors and adversarial attacks. A long term objective in artificial intelligence research is to move beyond today's specialized RL agents toward more generalist systems endowed with the capability to adapt in real time to unpredictable external factors and to new downstream tasks. This work aims in this direction, tackling unsupervised reinforcement learning problems, a framework where agents are not provided with external rewards, and thus must autonomously learn new tasks throughout their lifespan, guided by intrinsic motivations. The concept of intrinsic motivation arise from our understanding of humans ability to exhibit certain self-sufficient behaviors during their development, such as playing or having curiosity. This ability allows individuals to design and solve their own tasks, and to build inner physical and social representations of their environments, acquiring an open-ended set of skills throughout their lifespan as a result. This thesis is part of the research effort to incorporate these essential features in artificial agents, leveraging goal-conditioned reinforcement learning to design agents able to discover and master every feasible goals in complex environments. In our first contribution, we investigate autonomous intrinsic goal setting, as a versatile agent should be able to determine its own goals and the order in which to learn these goals to enhance its performances. By leveraging a learned model of the agent's current goal reaching abilities, we show that we can shape an optimal difficulty goal distribution, enabling to sample goals in the Zone of Proximal Development (ZPD) of the agent, which is a psychological concept referring to the frontier between what a learner knows and what it does not, constituting the space of knowledge that is not mastered yet but have the potential to be acquired. We demonstrate that targeting the ZPD of the agent's result in a significant increase in performance for a great variety of goal-reaching tasks. Another core competence is to extract a relevant representation of what matters in the environment from observations coming from any available sensors. We address this question in our second contribution, by highlighting the difficulty to learn a correct representation of the environment in an online setting, where the agent acquires knowledge incrementally as it make progresses. In this context, recent achieved goals are outliers, as there are very few occurrences of this new skill in the agent's experiences, making their representations brittle. We leverage the adversarial setting of Distributionally Robust Optimization in order for the agent's representations of such outliers to be reliable. We show that our method leads to a virtuous circle, as learning accurate representations for new goals fosters the exploration of the environment
Debard, Quentin. "Automatic learning of next generation human-computer interactions." Thesis, Lyon, 2020. http://www.theses.fr/2020LYSEI036.
Повний текст джерелаArtificial Intelligence (AI) and Human-Computer Interactions (HCIs) are two research fields with relatively few common work. HCI specialists usually design the way we interact with devices directly from observations and measures of human feedback, manually optimizing the user interface to better fit users’ expectations. This process is hard to optimize: ergonomy, intuitivity and ease of use are key features in a User Interface (UI) that are too complex to be simply modelled from interaction data. This drastically restrains the possible uses of Machine Learning (ML) in this design process. Currently, ML in HCI is mostly applied to gesture recognition and automatic display, e.g. advertisement or item suggestion. It is also used to fine tune an existing UI to better optimize it, but as of now it does not participate in designing new ways to interact with computers. Our main focus in this thesis is to use ML to develop new design strategies for overall better UIs. We want to use ML to build intelligent – understand precise, intuitive and adaptive – user interfaces using minimal handcrafting. We propose a novel approach to UI design: instead of letting the user adapt to the interface, we want the interface and the user to adapt mutually to each other. The goal is to reduce human bias in protocol definition while building co-adaptive interfaces able to further fit individual preferences. In order to do so, we will put to use the different mechanisms available in ML to automatically learn behaviors, build representations and take decisions. We will be experimenting on touch interfaces, as these interfaces are vastly used and can provide easily interpretable problems. The very first part of our work will focus on processing touch data and use supervised learning to build accurate classifiers of touch gestures. The second part will detail how Reinforcement Learning (RL) can be used to model and learn interaction protocols given user actions. Lastly, we will combine these RL models with unsupervised learning to build a setup allowing for the design of new interaction protocols without the need for real user data
Buhot, Arnaud. "Etude de propriétés d'apprentissage supervisé et non supervisé par des méthodes de Physique Statistique." Phd thesis, Université Joseph Fourier (Grenoble), 1999. http://tel.archives-ouvertes.fr/tel-00001642.
Повний текст джерелаBen-Fares, Maha. "Apprentissage de représentation non supervisé de flux de données textuelles." Electronic Thesis or Diss., CY Cergy Paris Université, 2024. http://www.theses.fr/2024CYUN1316.
Повний текст джерелаThis thesis presents an innovative methods for clustering text data streams and also introduces a system for identifying AI-generated text. This AI detection method can be used independently or as a preprocessing step to filter incoming documents, by removing AI-generated content, preserving the authenticity and validity of the information.Specifically, we develop a classification system that distinguishes between human-written and AI-generated text. This method employs a hierarchical fusion strategy that integrates representations from various layers of the BERT model. By focusing on syntactic features, our model classifies each token as either Human or AI, effectively capturing detailed text structures and ensuring robust performance across multiple languages using the XLM-RoBERTa-Large model.In the field of data stream clustering, particularly for textual data, we first introduce a method called OTTC (Online Topological Text Clustering). This approach leverages topological representation learning in combination with online clustering techniques. It effectively addresses the challenges in clustering textual data streams, such as data dynamism, sparsity, and the curse of dimensionality, which are issues that traditional clustering methods often struggle to manage.To further improve clustering results and address the limitations of OTTC, we propose the MVTStream algorithm, specifically designed for multi-view text data streams. This algorithm operates in three stages: First, it generates diverse text representations of incoming data, treating each representation as a separate view. Then, it employs micro-cluster data structures for real-time processing. Finally, it utilizes ensemble methods to aggregate clusters from the various views and get the final clusters
Chen, Hao. "Vers la ré-identification de personnes non-supervisée." Thesis, Université Côte d'Azur, 2022. http://www.theses.fr/2022COAZ4014.
Повний текст джерелаAs a core component of intelligent video surveillance systems, person re-identification (ReID) targets at retrieving a person of interest across non-overlapping cameras. Despite significant improvements in supervised ReID, cumbersome annotation process makes it less scalable in real-world deployments. Moreover, as appearance representations can be affected by noisy factors, such as illumination level and camera properties, between different domains, person ReID models suffer a large performance drop in the presence of domain gaps. We are particularly interested in designing algorithms that can adapt a person ReID model to a target domain without human supervision. In such context, we mainly focus on designing unsupervised domain adaptation and unsupervised representation learning methods for person ReID.In this thesis, we first explore how to build robust representations by combining both global and local features under the supervised condition. Then, towards an unsupervised domain adaptive ReID system, we propose three unsupervised methods for person ReID, including 1) teacher-student knowledge distillation with asymmetric network structures for feature diversity encouragement, 2) joint generative and contrastive learning framework that generates augmented views with a generative adversarial network for contrastive learning, and 3) exploring inter-instance relations and designing relation-aware loss functions for better contrastive learning based person ReID.Our methods have been extensively evaluated on main-stream ReID datasets, such as Market-1501, DukeMTMC-reID and MSMT17. The proposed methods significantly outperform previous methods on the ReID datasets, significantly pushing person ReID to real-world deployments
Dutech, Alain. "Apprentissage par Renforcement : Au delà des Processus Décisionnels de Markov (Vers la cognition incarnée)." Habilitation à diriger des recherches, Université Nancy II, 2010. http://tel.archives-ouvertes.fr/tel-00549108.
Повний текст джерелаLefort, Mathieu. "Apprentissage spatial de corrélations multimodales par des mécanismes d'inspiration corticale." Phd thesis, Université Nancy II, 2012. http://tel.archives-ouvertes.fr/tel-00756687.
Повний текст джерелаPeyrache, Jean-Philippe. "Nouvelles approches itératives avec garanties théoriques pour l'adaptation de domaine non supervisée." Thesis, Saint-Etienne, 2014. http://www.theses.fr/2014STET4023/document.
Повний текст джерелаDuring the past few years, an increasing interest for Machine Learning has been encountered, in various domains like image recognition or medical data analysis. However, a limitation of the classical PAC framework has recently been highlighted. It led to the emergence of a new research axis: Domain Adaptation (DA), in which learning data are considered as coming from a distribution (the source one) different from the one (the target one) from which are generated test data. The first theoretical works concluded that a good performance on the target domain can be obtained by minimizing in the same time the source error and a divergence term between the two distributions. Three main categories of approaches are derived from this idea : by reweighting, by reprojection and by self-labeling. In this thesis work, we propose two contributions. The first one is a reprojection approach based on boosting theory and designed for numerical data. It offers interesting theoretical guarantees and also seems able to obtain good generalization performances. Our second contribution consists first in a framework filling the gap of the lack of theoretical results for self-labeling methods by introducing necessary conditions ensuring the good behavior of this kind of algorithm. On the other hand, we propose in this framework a new approach, using the theory of (epsilon, gamma, tau)- good similarity functions to go around the limitations due to the use of kernel theory in the specific context of structured data
De, La Bourdonnaye François. "Learning sensori-motor mappings using little knowledge : application to manipulation robotics." Thesis, Université Clermont Auvergne (2017-2020), 2018. http://www.theses.fr/2018CLFAC037/document.
Повний текст джерелаThe thesis is focused on learning a complex manipulation robotics task using little knowledge. More precisely, the concerned task consists in reaching an object with a serial arm and the objective is to learn it without camera calibration parameters, forward kinematics, handcrafted features, or expert demonstrations. Deep reinforcement learning algorithms suit well to this objective. Indeed, reinforcement learning allows to learn sensori-motor mappings while dispensing with dynamics. Besides, deep learning allows to dispense with handcrafted features for the state spacerepresentation. However, it is difficult to specify the objectives of the learned task without requiring human supervision. Some solutions imply expert demonstrations or shaping rewards to guiderobots towards its objective. The latter is generally computed using forward kinematics and handcrafted visual modules. Another class of solutions consists in decomposing the complex task. Learning from easy missions can be used, but this requires the knowledge of a goal state. Decomposing the whole complex into simpler sub tasks can also be utilized (hierarchical learning) but does notnecessarily imply a lack of human supervision. Alternate approaches which use several agents in parallel to increase the probability of success can be used but are costly. In our approach,we decompose the whole reaching task into three simpler sub tasks while taking inspiration from the human behavior. Indeed, humans first look at an object before reaching it. The first learned task is an object fixation task which is aimed at localizing the object in the 3D space. This is learned using deep reinforcement learning and a weakly supervised reward function. The second task consists in learning jointly end-effector binocular fixations and a hand-eye coordination function. This is also learned using a similar set-up and is aimed at localizing the end-effector in the 3D space. The third task uses the two prior learned skills to learn to reach an object and uses the same requirements as the two prior tasks: it hardly requires supervision. In addition, without using additional priors, an object reachability predictor is learned in parallel. The main contribution of this thesis is the learning of a complex robotic task with weak supervision
Aklil, Nassim. "Apprentissage actif sous contrainte de budget en robotique et en neurosciences computationnelles. Localisation robotique et modélisation comportementale en environnement non stationnaire." Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066225/document.
Повний текст джерелаDecision-making is a highly researched field in science, be it in neuroscience to understand the processes underlying animal decision-making, or in robotics to model efficient and rapid decision-making processes in real environments. In neuroscience, this problem is resolved online with sequential decision-making models based on reinforcement learning. In robotics, the primary objective is efficiency, in order to be deployed in real environments. However, in robotics what can be called the budget and which concerns the limitations inherent to the hardware, such as computation times, limited actions available to the robot or the lifetime of the robot battery, are often not taken into account at the present time. We propose in this thesis to introduce the notion of budget as an explicit constraint in the robotic learning processes applied to a localization task by implementing a model based on work developed in statistical learning that processes data under explicit constraints, limiting the input of data or imposing a more explicit time constraint. In order to discuss an online functioning of this type of budgeted learning algorithms, we also discuss some possible inspirations that could be taken on the side of computational neuroscience. In this context, the alternation between information retrieval for location and the decision to move for a robot may be indirectly linked to the notion of exploration-exploitation compromise. We present our contribution to the modeling of this compromise in animals in a non-stationary task involving different levels of uncertainty, and we make the link with the methods of multi-armed bandits
Lefort, Mathieu. "Apprentissage spatial de corrélations multimodales par des mécanismes d'inspiration corticale." Electronic Thesis or Diss., Université de Lorraine, 2012. http://www.theses.fr/2012LORR0106.
Повний текст джерелаThis thesis focuses on unifying multiple modal data flows that may be provided by sensors of an agent. This unification, inspired by psychological experiments like the ventriloquist effect, is based on detecting correlations which are defined as temporally recurrent spatial patterns that appear in the input flows. Learning of the input flow correlations space consists on sampling this space and generalizing theselearned samples. This thesis proposed some functional paradigms for multimodal data processing, leading to the connectionist, generic, modular and cortically inspired architecture SOMMA (Self-Organizing Maps for Multimodal Association). In this model, each modal stimulus is processed in a cortical map. Interconnectionof these maps provides an unifying multimodal data processing. Sampling and generalization of correlations are based on the constrained self-organization of each map. The model is characterised by a gradual emergence of these functional properties : monomodal properties lead to the emergence of multimodal ones and learning of correlations in each map precedes self-organization of these maps.Furthermore, the use of a connectionist architecture and of on-line and unsupervised learning provides plasticity and robustness properties to the data processing in SOMMA. Classical artificial intelligence models usually miss such properties
Maes, Francis. "Learning in Markov decision processes for structured prediction : applications to sequence labeling, tree transformation and learning for search." Paris 6, 2009. http://www.theses.fr/2009PA066500.
Повний текст джерелаMuller, Jean-Denis. "La perception structurante : apprentissage non monotone de fonctions visuelles par croissance et maturation de structures neuromimétiques." Toulouse, ENSAE, 1993. http://www.theses.fr/1993ESAE0030.
Повний текст джерелаAlami, Réda. "Bandits à Mémoire pour la prise de décision en environnement dynamique. Application à l'optimisation des réseaux de télécommunications." Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG063.
Повний текст джерелаIn this PhD thesis, we study the non-stationary multi-armed bandit problem where the non-stationarity behavior of the environment is characterized by several abrupt changes called "change-points". We propose Memory Bandits: a combination between an algorithm for the stochastic multi-armed bandit and the Bayesian Online Change-Point Detector (BOCPD). The analysis of the latter has always been an open problem in the statistical and sequential learning theory community. For this reason, we derive a variant of the Bayesian Online Change-point detector which is easier to mathematically analyze in term of false alarm rateand detection delay (which are the most common criteria for online change-point detection). Then, we introduce the decentralized exploration problem in the multi-armed bandit paradigm where a set of players collaborate to identify the best arm by asynchronously interacting with the same stochastic environment. We propose a first generic solution called decentralized elimination: which uses any best arm identification algorithm as a subroutine with the guar-antee that the algorithm ensures privacy, with a low communication cost. Finally, we perform an evaluation of the multi-armed bandit strategies in two different context of telecommunication networks. First, in LoRaWAN (Long Range Wide Area Network) context, we propose to use multi-armed bandit algorithms instead of the default algorithm ADR (Adaptive Data Rate) in order to minimize the energy consumption and the packet losses of end-devices. Then, in a IEEE 802.15.4-TSCH context, we perform an evaluation of 9 multi-armed bandit algorithms in order to select the ones that choose high-performance channels, using data collected through the FIT IoT-LAB platform. The performance evaluation suggests that our proposal can significantly improve the packet delivery ratio compared to the default TSCH operation, thereby increasing the reliability and the energy efficiency of the transmissions
Wacongne, Catherine. "Traitements conscient et non-conscient des régularités temporelles : Modélisation et neuroimagerie." Thesis, Paris 6, 2014. http://www.theses.fr/2014PA066290/document.
Повний текст джерелаWhat is going to happen next? Natural stimuli tend to follow each other in a reproducible way. Multiple fields of neuroscience and psychology bring evidence that human’s brain and behavior are sensitive to the temporal structure of stimuli and are able to exploit them in multiple ways: to make appropriate decisions, encode efficiently information, react faster to predictable stimuli or orient attention towards surprising ones… Multiple brain areas show sensitivity to the temporal structure of events. However, all areas do not seem to be sensitive to the same kind of temporal regularities. Conscious access to the stimuli seems to play a key role in some of these dissociations and better understanding this role could improve the current diagnostic tools for non-communicative patients. This thesis explores the hierarchical organization of the processing of temporal regularities and the computational properties of conscious and unconscious levels of processing by combining a modeling approach with neuroimaging experiments using magnetoencephalography and electroencephalography (MEEG). First, a plausible neuronal model based on predictive coding principles reproduces the main properties of the preattentive processing of pure tones in the auditory cortex indexed by the evoked potential mismatch negativity (MMN). Second, a MEEG experiment provides evidence for a hierarchical organization of multiple predictive processes in the auditory cortex. Finally, a second model explores the new computational properties and constraints associated to the access of stimuli to a conscious space with a working memory able to maintain information for an arbitrary time but with limited capacity
Delcourt, Alexandre. "Amélioration des détecteurs CdZnTe pour l'imagerie gamma par apprentissage." Electronic Thesis or Diss., Université Grenoble Alpes, 2023. http://www.theses.fr/2023GRALM056.
Повний текст джерелаSince a few years, the wide spread use of CZT-based detectors in gamma imaging drives their performance optimization to stay competitive at the industrial level. However, the presence of structural defect in the CZT crystal deteriorates the output signals quality and holds back the higher volume detectors development.The purpose of this thesis is the use of optimization and artificial intelligence algorithms using realistic simulations to override the impact of the defects and improve the localization performances of gamma interactions in the detector. We will develop a mathematical-based method in three steps as an alternative to common characterization and correction methods.First, we develop 3D CZT detector simulations enabling to implement defects with different natures to observe their impact on output signals. Then we build a simple neural network, which can be introduced in the electronics to localize the gamma interactions in the detector from simulation results. A second network based on a gradient computation method will allow determining the electric field and collection performance of a detector.The addition of these three steps will be used to learn through simulation the intern parameters of a determined detector such as the electric field. This simulation will serve to train the simple neural network and finally be used on experimental data to improve the localization performance of the detector.The development of this mathematical approach will help us having a better understanding of the intern structure of a CZT crystal being able to reproduce its behavior in simulation. In addition, the better performance of the detector might be sufficient to decrease the radiotracer dose for medical imaging or limit the exposition time of operators in a nuclear power plant
Trenquier, 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.
Повний текст джерелаClassification 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
Khacef, Yacine. "Surveillance avancée du trafic routier par détection acoustique distribuée et apprentissage profond." Electronic Thesis or Diss., Université Côte d'Azur, 2024. http://www.theses.fr/2024COAZ5070.
Повний текст джерелаUrban traffic management poses a significant challenge for cities worldwide, intensified by the growing number of vehicles on road infrastructures. Traditional methods, such as cameras and loop detectors, are often suboptimal due to their high deployment and maintenance costs, limited sensing resolution, and privacy concerns. Recently, Distributed Acoustic Sensing (DAS) technology has emerged as a promising solution for traffic monitoring. By transforming standard fiber-optic telecommunication cables into an array of vibration sensors, DAS captures vehicle-induced subsurface deformation with high spatio-temporal resolution, providing a cost-effective and privacy-preserving alternative.In this thesis, we propose several models and frameworks for comprehensive traffic monitoring using DAS technology, focusing on four key aspects: vehicle detection, speed estimation, counting, and classification. First, we introduce a self-supervised DAS data alignment model that temporally aligns the recorded DAS data across multiple measurement points, enabling the extraction of the traffic information. Our model integrates a deep learning module with a non-uniform time warping block, making it capable of handling challenging traffic conditions and accurately aligning DAS data.Next, we present a vehicle detection and speed estimation framework built on the alignment model. Vehicle detection is formulated within the Generalized Likelihood Ratio Test (GLRT) framework, allowing for reliable detection and localization of vehicles. Speed estimation is achieved over the detected vehicles using the warps from the alignment model, and the results are validated against dedicated sensors. Our method achieves a mean error of less than kmph{3}, outperforming traditional time series alignment methods like Dynamic Time Warping (DTW) by nearly 80%. Furthermore, our model's computing time is 16 times faster than DTW, enabling real-time performance.Lastly, we introduce new vehicle counting and classification methods that leverage the DAS technology. We present a first solution, based solely on vehicle detection results, which is effective for truck counting but shows limitations in cars counting under high-traffic conditions. To address these limitations, we develop a second approach for vehicle counting using a supervised deep learning model trained on a specific road section, using the vehicle counting results of the first method and low-time-resolution labels from dedicated sensors. Through an optimal transport-based feature mapping technique, we extend the model to other road segments, demonstrating its scalability and adaptability. Using the first truck counting method along with the deep learning-based vehicle counting model results in a comprehensive vehicle counting and classification solution.Overall, this thesis presents a robust and scalable framework for road traffic monitoring using DAS technology, delivering both high accuracy and real-time performance. The framework paves the way for extracting a wide range of other crucial traffic information, such as accident detection. Moreover, this approach can be generalized to various road configurations and extended to other transportation modes, such as tramways and trains, demonstrating its broader applicability
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.
Повний текст джерелаNajar, Anis. "Shaping robot behaviour with unlabeled human instructions." Electronic Thesis or Diss., Paris 6, 2017. http://www.theses.fr/2017PA066152.
Повний текст джерелаMost of current interactive learning systems rely on predefined protocols that constrain the interaction with the user. Relaxing the constraints of interaction protocols can therefore improve the usability of these systems.This thesis tackles the question of interpreting human instructions, in order to relax the constraints about predetermining their meanings. We propose a framework that enables a human teacher to shape a robot behaviour, by interactively providing it with unlabeled instructions. Our approach consists in grounding the meaning of instruction signals in the task learning process, and using them simultaneously for guiding the latter. This approach has a two-fold advantage. First, it provides more freedom to the teacher in choosing his preferred signals. Second, it reduces the required engineering efforts, by removing the necessity to encode the meaning of each instruction signal. We implement our framework as a modular architecture, named TICS, that offers the possibility to combine different information sources: a predefined reward function, evaluative feedback and unlabeled instructions. This allows for more flexibility in the teaching process, by enabling the teacher to switch between different learning modes. Particularly, we propose several methods for interpreting instructions, and a new method for combining evaluative feedback with a predefined reward function. We evaluate our framework through a series of experiments, performed both in simulation and with real robots. The experimental results demonstrate the effectiveness of our framework in accelerating the task learning process, and in reducing the number of required interactions with the teacher
Monnet, Jean-matthieu. "Caractérisation des forêts de montagne par scanner laser aéroporté : estimation de paramètres de peuplement par régression SVM et apprentissage non supervisé pour la détection de sommets." Phd thesis, Université de Grenoble, 2011. http://tel.archives-ouvertes.fr/tel-00652698.
Повний текст джерелаMonnet, Jean-Matthieu. "Caractérisation des forêts de montagne par scanner laser aéroporté : estimation de paramètres de peuplement par régression SVM et apprentissage non supervisé pour la détection de sommets." Thesis, Grenoble, 2011. http://www.theses.fr/2011GRENT056/document.
Повний текст джерелаNumerous studies have shown the potential of airborne laser scanningfor the mapping of forest resources. However, the application of thisremote sensing technique to complex forests encountered in mountainousareas requires further investigation. In this thesis, the two mainmethods used to derive forest information are tested with airbornelaser scanning data acquired in the French Alps, and adapted to theconstraints of mountainous environments. In particular,a framework for unsupervised training of treetop detection isproposed, and the performance of support vector regression combinedwith dimension reduction for forest stand parameters estimation isevaluated
Najar, Anis. "Shaping robot behaviour with unlabeled human instructions." Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066152.
Повний текст джерелаMost of current interactive learning systems rely on predefined protocols that constrain the interaction with the user. Relaxing the constraints of interaction protocols can therefore improve the usability of these systems.This thesis tackles the question of interpreting human instructions, in order to relax the constraints about predetermining their meanings. We propose a framework that enables a human teacher to shape a robot behaviour, by interactively providing it with unlabeled instructions. Our approach consists in grounding the meaning of instruction signals in the task learning process, and using them simultaneously for guiding the latter. This approach has a two-fold advantage. First, it provides more freedom to the teacher in choosing his preferred signals. Second, it reduces the required engineering efforts, by removing the necessity to encode the meaning of each instruction signal. We implement our framework as a modular architecture, named TICS, that offers the possibility to combine different information sources: a predefined reward function, evaluative feedback and unlabeled instructions. This allows for more flexibility in the teaching process, by enabling the teacher to switch between different learning modes. Particularly, we propose several methods for interpreting instructions, and a new method for combining evaluative feedback with a predefined reward function. We evaluate our framework through a series of experiments, performed both in simulation and with real robots. The experimental results demonstrate the effectiveness of our framework in accelerating the task learning process, and in reducing the number of required interactions with the teacher
Sahasrabudhe, Mihir. "Unsupervised and weakly supervised deep learning methods for computer vision and medical imaging." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASC010.
Повний текст джерелаThe first two contributions of this thesis (Chapter 2 and 3) are models for unsupervised 2D alignment and learning 3D object surfaces, called Deforming Autoencoders (DAE) and Lifting Autoencoders (LAE). These models are capable of identifying canonical space in order to represent different object properties, for example, appearance in a canonical space, deformation associated with this appearance that maps it to the image space, and for human faces, a 3D model for a face, its facial expression, and the angle of the camera. We further illustrate applications of models to other domains_ alignment of lung MRI images in medical image analysis, and alignment of satellite images for remote sensing imagery. In Chapter 4, we concentrate on a problem in medical image analysis_ diagnosis of lymphocytosis. We propose a convolutional network to encode images of blood smears obtained from a patient, followed by an aggregation operation to gather information from all images in order to represent them in one feature vector which is used to determine the diagnosis. Our results show that the performance of the proposed models is at-par with biologists and can therefore augment their diagnosis
Saporta, Antoine. "Domain Adaptation for Urban Scene Segmentation." Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS115.
Повний текст джерелаThis thesis tackles some of the scientific locks of perception systems based on neural networks for autonomous vehicles. This dissertation discusses domain adaptation, a class of tools aiming at minimizing the need for labeled data. Domain adaptation allows generalization to so-called target data that share structures with the labeled so-called source data allowing supervision but nevertheless following a different statistical distribution. First, we study the introduction of privileged information in the source data, for instance, depth labels. The proposed strategy, BerMuDA, bases its domain adaptation on a multimodal representation obtained by bilinear fusion, modeling complex interactions between segmentation and depth. Next, we examine self-supervised learning strategies in domain adaptation, relying on selecting predictions on the unlabeled target data, serving as pseudo-labels. We propose two new selection criteria: first, an entropic criterion with ESL; then, with ConDA, using an estimate of the true class probability. Finally, the extension of adaptation scenarios to several target domains as well as in a continual learning framework is proposed. Two approaches are presented to extend traditional adversarial methods to multi-target domain adaptation: Multi-Dis. and MTKT. In a continual learning setting for which the target domains are discovered sequentially and without rehearsal, the proposed CTKT approach adapts MTKT to this new problem to tackle catastrophic forgetting
Doan, Tien Tai. "Réalisation d’une aide au diagnostic en orthodontie par apprentissage profond." Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG033.
Повний текст джерелаAccurate processing and diagnosis of dental images is an essential factor determining the success of orthodontic treatment. Many image processing methods have been proposed to address this problem. Those studies mainly work on small datasets of radiographs under laboratory conditions and are not highly applicable as complete products or services. In this thesis, we train deep learning models to diagnose dental problems such as gingivitis and crowded teeth using mobile phones' images. We study feature layers of these models to find the strengths and limitations of each method. Besides training deep learning models, we also embed each of them in a pipeline, including preprocessing and post-processing steps, to create a complete product. For the lack of training data problem, we studied a variety of methods for data augmentation, especially domain adaptation methods using image-to-image translation models, both supervised and unsupervised, and obtain promising results. Image translation networks are also used to simplifying patients' choice of orthodontic appliances by showing them how their teeth could look like during treatment. Generated images have are realistic and in high resolution. Researching further into unsupervised image translation neural networks, we propose an unsupervised imageto- image translation model which can manipulate features of objects in the image without requiring additional annotation. Our model outperforms state-of-the-art techniques on multiple image translation applications and is also extended for few-shot learning problems
Dubois, Amaury. "Optimisation et apprentissage de modèles biologiques : application à lirrigation [sic l'irrigation] de pomme de terre." Thesis, Littoral, 2020. http://www.theses.fr/2020DUNK0560.
Повний текст джерелаThe subject of this PhD concerns one of the LISIC themes : modelling and simulation of complex systems, as well as optimization and automatic learning for agronomy. The objectives of the thesis are to answer the questions of irrigation management of the potato crop and the development of decision support tools for farmers. The choice of this crop is motivated by its important share in the Haut-de-France region. The manuscript is divided into 3 parts. The first part deals with continuous multimodal optimization in a black box context. This is followed by a presentation of a methodology for the automatic calibration of biological model parameters through reformulation into a black box multimodal optimization problem. The relevance of the use of inverse analysis as a methodology for automatic parameterisation of large models in then demonstrated. The second part presents 2 new algorithms, UCB Random with Decreasing Step-size and UCT Random with Decreasing Step-size. Thes algorithms are designed for continuous multimodal black-box optimization whose choice of the position of the initial local search is assisted by a reinforcement learning algorithms. The results show that these algorithms have better performance than (Quasi) Random with Decreasing Step-size algorithms. Finally, the last part focuses on machine learning principles and methods. A reformulation of the problem of predicting soil water content at one-week intervals into a supervised learning problem has enabled the development of a new decision support tool to respond to the problem of crop management
Bounhar, Abdelaziz. "Information theory and reinforcement learning of mixed covert and non-covert wireless networks." Electronic Thesis or Diss., Institut polytechnique de Paris, 2024. http://www.theses.fr/2024IPPAT005.
Повний текст джерелаWhile cryptographic methods offer security, they are often impractical for Internet of Things (IoT) devices due to their limited computational resources and battery life. In light of these challenges, physical layer security techniques, particularly covert communication, seems to be an adequate solution for securing IoT communications. Existing research on covert communication has predominantly focused on systems with solely covert users. This thesis addresses this gap and pioneers the characterization of the information-theoretic fundamental limits of communication systems involving both covert and non-covert users, demonstrating how and when non-covert users can enhance covert communication. It also advances previous findings on the single and multi-users setup by characterizing the exact secret-key rate needed to communicate at a given covert data rate.In another line of work, we address the central approach to modern semantic and goal-oriented communication systems. Specifically, we address the joint source-channel coding problem under a covertness constraints, identifying optimal coding schemes that meet the covertness requirement. These theoretical insights are validated through deep learning techniques, showing that covert semantic communication is only guaranteed when the established theoretical constraints are met. Lastly, to further enrich our research, we extend our work to setups that encompass both covert and non-covert users operating using Non-Orthogonal Multiple Access in an Additive White Gaussian Noise channel. By leveraging reinforcement learning techniques, we develop efficient resource allocation policies that effectively optimize performance in these intricate environments, accounting for real-world constraints such as imperfect channel state information and energy limitations
Hedjazi, Lyamine. "Outil d'aide au diagnostic du cancer à partir d'extraction d'informations issues de bases de données et d'analyses par biopuces." Phd thesis, Toulouse 3, 2011. http://thesesups.ups-tlse.fr/1391/.
Повний текст джерелаCancer is one of the most common causes of death in the world. Currently, breast cancer is the most frequent in female cancers. Although the significant improvement made last decades in cancer management, an accurate cancer management is still needed to help physicians take the necessary treatment decisions and thereby reducing its related adverse effects as well as its expensive medical costs. This work addresses the use of machine learning techniques to develop such tools of breast cancer management. Clinical factors, such as patient age and histo-pathological variables, are still the basis of day-to-day decision for cancer management. However, with the emergence of high throughput technology, gene expression profiling is gaining increasing attention to build more accurate predictive tools for breast cancer. Nevertheless, several challenges have to be faced for the development of such tools mainly (1) high dimensionality of data issued from microarray technology; (2) low signal-to-noise ratio in microarray measurement; (3) membership uncertainty of patients to cancer groups; and (4) heterogeneous (or mixed-type) data present usually in clinical datasets. In this work we propose some approaches to deal appropriately with such challenges. A first approach addresses the problem of high data dimensionality by taking use of l1 learning capabilities to design an embedded feature selection algorithm for SVM (l1 SVM) based on a gradient descent technique. The main idea is to transform the initial constrained convex optimization problem into an unconstrained one through the use of an approximated loss function. A second approach handles simultaneously all challenges and therefore allows the integration of several data sources (clinical, microarray. . . ) to build more accurate predictive tools. In this order a unified principle to deal with the data heterogeneity problem is proposed. This principle is based on the mapping of different types of data from initially heterogeneous spaces into a common space through an adequacy measure. To take into account membership uncertainty and increase model interpretability, this principle is proposed within a fuzzy logic framework. Besides, in order to alleviate the problem of high level noise, a symbolic approach is proposed suggesting the use of interval representation to model the noisy measurements. Since all data are mapped into a common space, they can be processed in a unified way whatever its initial type for different data analysis purposes. We particularly designed, based on this principle, a supervised fuzzy feature weighting approach. The weighting process is mainly based on the definition of a membership margin for each sample. It optimizes then a membership-margin based objective function using classical optimization approach to avoid combinatorial search. An extension of this approach to the unsupervised case is performed to develop a weighted fuzzy rule-based clustering algorithm. The effectiveness of all approaches has been assessed through extensive experimental studies and compared with well-know state-of-the-art methods. Finally, some breast cancer applications have been performed based on the proposed approaches. In particular, predictive and prognostic models were derived based on microarray and/or clinical data and compared with genetic and clinical based approaches
Hedjazi, Lyamine. "Outil d'aide au diagnostic du cancer à partir d'extraction d'informations issues de bases de données et d'analyses par biopuces." Phd thesis, Université Paul Sabatier - Toulouse III, 2011. http://tel.archives-ouvertes.fr/tel-00657959.
Повний текст джерелаPavão, Adrien. "Methodology for Design and Analysis of Machine Learning Competitions." Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPASG088.
Повний текст джерелаWe develop and study a systematic and unified methodology to organize and use scientific challenges in research, particularly in the domain of machine learning (data-driven artificial intelligence). As of today, challenges are becoming more and more popular as a pedagogic tool and as a means of pushing the state-of-the-art by engaging scientists of all ages, within or outside academia. This can be thought of as a form of citizen science. There is the promise that this form of community involvement in science might contribute to reproducible research and democratize artificial intelligence. However, while the distinction between organizers and participants may mitigate certain biases, there exists a risk that biases in data selection, scoring metrics, and other experimental design elements could compromise the integrity of the outcomes and amplify the influence of randomness. In extreme cases, the results could range from being useless to detrimental for the scientific community and, ultimately, society at large. Our objective is to structure challenge organization within a rigorous framework and offer the community insightful guidelines. In conjunction with the tools of challenge organization that we are developing as part of the CodaLab project, we aim to provide a valuable contribution to the community. This thesis includes theoretical fundamental contributions drawing on experimental design, statistics and game theory, and practical empirical findings resulting from the analysis of data from previous challenges
Kara, Sandra. "Unsupervised object discovery in images and video data." Electronic Thesis or Diss., université Paris-Saclay, 2025. http://www.theses.fr/2025UPASG019.
Повний текст джерелаThis thesis explores self-supervised learning methods for object localization, commonly known as Object Discovery. Object localization in images and videos is an essential component of computer vision tasks such as detection, re-identification, tracking etc. Current supervised algorithms can localize (and classify) objects accurately but are costly due to the need for annotated data. The process of labeling is typically repeated for each new data or category of interest, limiting their scalability. Additionally, the semantically specialized approaches require prior knowledge of the target classes, restricting their use to known objects. Object Discovery aims to address these limitations by being more generic. The first contribution of this thesis focused on the image modality, investigating how features from self-supervised vision transformers can serve as cues for multi-object discovery. To localize objects in their broadest definition, we extended our focus to video data, leveraging motion cues and targeting the localization of objects that can move. We introduced background modeling and knowledge distillation in object discovery to tackle the background over-segmentation issue in existing object discovery methods and to reintegrate static objects, significantly improving the signal-to-noise ratio in predictions. Recognizing the limitations of single-modality data, we incorporated 3D data through a cross-modal distillation framework. The knowledge exchange between 2D and 3D domains improved alignment on object regions between the two modalities, enabling the use of multi-modal consistency as a confidence criterion
Akakzia, Ahmed. "Teaching Predicate-based Autotelic Agents." Electronic Thesis or Diss., Sorbonne université, 2022. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2022SORUS415.pdf.
Повний текст джерелаAs part of the quest for designing embodied machines that autonomously explore their environments, discover new behaviors and acquire open-ended repertoire of skills, artificial intelligence has been taking long looks at the inspiring fields of developmental psychology and cognitive sciences which investigate the remarkable continuous and unbounded learning of humans. This gave birth to the field of developmental robotics which aims at designing autonomous artificial agents capable of self-organizing their own learning trajectories based on their intrinsic motivations. It bakes the developmental framework of intrinsically motivated goal exploration processes (IMGEPs) into reinforcement learning (RL). This combination has been recently introduced as autotelic reinforcement learning, where autotelic agents are intrinsically motivated to self-represent, self-organize and autonomously learn about their own goals. Naturally, such agents need to be endowed with good exploration capabilities as they need to first physically encounter a certain goal in order to take ownership of and learn about it. Unfortunately, discovering interesting behavior is usually tricky, especially in hard exploration setups where the rewarding signals are parsimonious, deceptive or adversarial. In such scenarios, the agents’ physical situatedness-in the Piagetian sense of the term-seems insufficient. Luckily, research in developmental psychology and education sciences have been praising the remarkable role of socio-cultural signals in the development of human children. This social situatedness-in the Vygotskyan sense of the term-enhances the toddlers’ exploration capabilities, creativity and development. However, deep \rl considers social interactions as dictating instructions to the agents, depriving them from their autonomy. This research introduces \textit{teachable autotelic agents}, a novel family of autonomous machines that can learn both alone and from external social signals. We formalize such a family as a hybrid goal exploration process (HGEPs), where autotelic agents are endowed with an internalization mechanism to rehearse social signals and with a goal source selector to actively query for social guidance. The present manuscript is organized in two parts. In the first part, we focus on the design of teachable autotelic agents and attempt to leverage the most important properties that would later serve the social interaction. Namely, we introduce predicate-based autotelic agents, a novel family of autotelic agents that represent their goals using spatial binary predicates. These insights were based on the Mandlerian view on the prelinguistic concept acquisition suggesting that toddlers are endowed with some innate mechanisms enabling them to translate spatio-temporal information into an iconic static form. We show that the underlying semantic representation plays a pivotal role between raw sensory inputs and language inputs, enabling the decoupling of sensorimotor learning and language grounding. We also investigate the design of such agents' policies and state-action value functions, and argue that combining Graph Neural Networks (GNNs) with relational predicates provides a light computational scheme to transfer efficiently between skills. In the second part, we formalize social interactions as a goal exploration process. We introduce Help Me Explore (HME), a novel social interaction protocol where an expert social partner progressively guides the learning agent beyond its zone of proximal development (ZPD). The agent actively selects to query its social partner whenever it estimates that it is not progressing enough alone. It eventually internalizes the social signals, becomes less dependent on its social partner and maximizes its control over its goal space
Lucas, Thomas. "Modèles génératifs profonds : sur-généralisation et abandon de mode." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM049.
Повний текст джерелаThis dissertation explores the topic of generative modelling of natural images,which is the task of fitting a data generating distribution.Such models can be used to generate artificial data resembling the true data, or to compress images.Latent variable models, which are at the core of our contributions, seek to capture the main factors of variations of an image into a variable that can be manipulated.In particular we build on two successful latent variable generative models, the generative adversarial network (GAN) and Variational autoencoder (VAE) models.Recently GANs significantly improved the quality of images generated by deep models, obtaining very compelling samples.Unfortunately these models struggle to capture all the modes of the original distribution, ie they do not cover the full variability of the dataset.Conversely, likelihood based models such as VAEs typically cover the full variety of the data well and provide an objective measure of coverage.However these models produce samples of inferior visual quality that are more easily distinguished from real ones.The work presented in this thesis strives for the best of both worlds: to obtain compelling samples while modelling the full support of the distribution.To achieve that, we focus on i) the optimisation problems used and ii) practical model limitations that hinder performance.The first contribution of this manuscript is a deep generative model that encodes global image structure into latent variables, built on the VAE, and autoregressively models low level detail.We propose a training procedure relying on an auxiliary loss function to control what information is captured by the latent variables and what information is left to an autoregressive decoder.Unlike previous approaches to such hybrid models, ours does not need to restrict the capacity of the autoregressive decoder to prevent degenerate models that ignore the latent variables.The second contribution builds on the standard GAN model, which trains a discriminator network to provide feedback to a generative network.The discriminator usually assesses the quality of individual samples, which makes it hard to evaluate the variability of the data.Instead we propose to feed the discriminator with emph{batches} that mix both true and fake samples, and train it to predict the ratio of true samples in the batch.These batches work as approximations of the distribution of generated images and allows the discriminator to approximate distributional statistics.We introduce an architecture that is well suited to solve this problem efficiently,and show experimentally that our approach reduces mode collapse in GANs on two synthetic datasets, and obtains good results on the CIFAR10 and CelebA datasets.The mutual shortcomings of VAEs and GANs can in principle be addressed by training hybrid models that use both types of objective.In our third contribution, we show that usual parametric assumptions made in VAEs induce a conflict between them, leading to lackluster performance of hybrid models.We propose a solution based on deep invertible transformations, that trains a feature space in which usual assumptions can be made without harm.Our approach provides likelihood computations in image space while being able to take advantage of adversarial training.It obtains GAN-like samples that are competitive with fully adversarial models while improving likelihood scores over existing hybrid models at the time of publication, which is a significant advancement
Chahla, Charbel. "Non-linear feature extraction for object re-identification in cameras networks." Thesis, Troyes, 2017. http://www.theses.fr/2017TROY0023.
Повний текст джерелаReplicating the visual system that the brain uses to process the information is an area of substantial interest. This thesis is situated in the context of a fully automated system capable of analyzing facial features when the target is near the cameras, and tracking his identity when his facial features are no more traceable. The first part of this thesis is devoted to face pose estimation procedures to be used in face recognition scenarios. We proposed a new label-sensitive embedding based on a sparse representation called Sparse Label sensitive Locality Preserving Projections. In an uncontrolled environment observed by cameras from an unknown distance, person re-identification relying upon conventional biometrics such as face recognition is not feasible. Instead, visual features based on the appearance of people can be exploited more reliably. In this context, we propose a new embedding scheme for single-shot person re-identification under non overlapping target cameras. Each person is described as a vector of kernel similarities to a collection of prototype person images. The robustness of the algorithm is improved by proposing the Color Categorization procedure. In the last part of this thesis, we propose a Siamese architecture of two Convolutional Neural Networks (CNN), with each CNN reduced to only eleven layers. This architecture allows a machine to be fed directly with raw data and to automatically discover the representations needed for classification
Ho, Vinh Thanh. "Techniques avancées d'apprentissage automatique basées sur la programmation DC et DCA." Thesis, Université de Lorraine, 2017. http://www.theses.fr/2017LORR0289/document.
Повний текст джерелаIn this dissertation, we develop some advanced machine learning techniques in the framework of online learning and reinforcement learning (RL). The backbones of our approaches are DC (Difference of Convex functions) programming and DCA (DC Algorithm), and their online version that are best known as powerful nonsmooth, nonconvex optimization tools. This dissertation is composed of two parts: the first part studies some online machine learning techniques and the second part concerns RL in both batch and online modes. The first part includes two chapters corresponding to online classification (Chapter 2) and prediction with expert advice (Chapter 3). These two chapters mention a unified DC approximation approach to different online learning algorithms where the observed objective functions are 0-1 loss functions. We thoroughly study how to develop efficient online DCA algorithms in terms of theoretical and computational aspects. The second part consists of four chapters (Chapters 4, 5, 6, 7). After a brief introduction of RL and its related works in Chapter 4, Chapter 5 aims to provide effective RL techniques in batch mode based on DC programming and DCA. In particular, we first consider four different DC optimization formulations for which corresponding attractive DCA-based algorithms are developed, then carefully address the key issues of DCA, and finally, show the computational efficiency of these algorithms through various experiments. Continuing this study, in Chapter 6 we develop DCA-based RL techniques in online mode and propose their alternating versions. As an application, we tackle the stochastic shortest path (SSP) problem in Chapter 7. Especially, a particular class of SSP problems can be reformulated in two directions as a cardinality minimization formulation and an RL formulation. Firstly, the cardinality formulation involves the zero-norm in objective and the binary variables. We propose a DCA-based algorithm by exploiting a DC approximation approach for the zero-norm and an exact penalty technique for the binary variables. Secondly, we make use of the aforementioned DCA-based batch RL algorithm. All proposed algorithms are tested on some artificial road networks
Kannan, Hariprasad. "Quelques applications de l’optimisation numérique aux problèmes d’inférence et d’apprentissage." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLC067/document.
Повний текст джерелаNumerical optimization and machine learning have had a fruitful relationship, from the perspective of both theory and application. In this thesis, we present an application oriented take on some inference and learning problems. Linear programming relaxations are central to maximum a posteriori (MAP) inference in discrete Markov Random Fields (MRFs). Especially, inference in higher-order MRFs presents challenges in terms of efficiency, scalability and solution quality. In this thesis, we study the benefit of using Newton methods to efficiently optimize the Lagrangian dual of a smooth version of the problem. We investigate their ability to achieve superior convergence behavior and to better handle the ill-conditioned nature of the formulation, as compared to first order methods. We show that it is indeed possible to obtain an efficient trust region Newton method, which uses the true Hessian, for a broad range of MAP inference problems. Given the specific opportunities and challenges in the MAP inference formulation, we present details concerning (i) efficient computation of the Hessian and Hessian-vector products, (ii) a strategy to damp the Newton step that aids efficient and correct optimization, (iii) steps to improve the efficiency of the conjugate gradient method through a truncation rule and a pre-conditioner. We also demonstrate through numerical experiments how a quasi-Newton method could be a good choice for MAP inference in large graphs. MAP inference based on a smooth formulation, could greatly benefit from efficient sum-product computation, which is required for computing the gradient and the Hessian. We show a way to perform sum-product computation for trees with sparse clique potentials. This result could be readily used by other algorithms, also. We show results demonstrating the usefulness of our approach using higher-order MRFs. Then, we discuss potential research topics regarding tightening the LP relaxation and parallel algorithms for MAP inference.Unsupervised learning is an important topic in machine learning and it could potentially help high dimensional problems like inference in graphical models. We show a general framework for unsupervised learning based on optimal transport and sparse regularization. Optimal transport presents interesting challenges from an optimization point of view with its simplex constraints on the rows and columns of the transport plan. We show one way to formulate efficient optimization problems inspired by optimal transport. This could be done by imposing only one set of the simplex constraints and by imposing structure on the transport plan through sparse regularization. We show how unsupervised learning algorithms like exemplar clustering, center based clustering and kernel PCA could fit into this framework based on different forms of regularization. We especially demonstrate a promising approach to address the pre-image problem in kernel PCA. Several methods have been proposed over the years, which generally assume certain types of kernels or have too many hyper-parameters or make restrictive approximations of the underlying geometry. We present a more general method, with only one hyper-parameter to tune and with some interesting geometric properties. From an optimization point of view, we show how to compute the gradient of a smooth version of the Schatten p-norm and how it can be used within a majorization-minimization scheme. Finally, we present results from our various experiments
Monnier, Tom. "Unsupervised image analysis by synthesis." Electronic Thesis or Diss., Marne-la-vallée, ENPC, 2023. http://www.theses.fr/2023ENPC0037.
Повний текст джерелаThe goal of this thesis is to develop machine learning approaches to analyze collections of images without annotations. Advances in this area hold particular promises for high-impact 3D-related applications (e.g., reconstructing a real-world scene with 3D actionable components for animation movies or video games) where annotating examples to teach the machines is difficult, as well as more micro applications related to specific needs (e.g., analyzing the character evolution from 12th century documents) where spending significant effort on annotating large-scale database is debatable. The central idea of this dissertation is to build machines that learn to analyze an image collection by synthesizing the images in the collection. Learning analysis models by synthesis is difficult because it requires the design of a learnable image generation system that explicitly exhibits the desired analysis output. To achieve our goal, we present three key contributions.The first contribution of this thesis is a new conceptual approach to category modeling. We propose to represent the category of an image, a 2D object or a 3D shape, with a prototype that is transformed using deep learning to model the different instances within the category. Specifically, we design meaningful parametric transformations (e.g., geometric deformations or colorimetric variations) and use neural networks to predict the transformation parameters necessary to instantiate the prototype for a given image. We demonstrate the effectiveness of this idea to cluster images and reconstruct 3D objects from single-view images. We obtain performances on par with the best state-of-the-art methods which leverage handcrafted features or annotations.The second contribution is a new way to discover elements in a collection of images. We propose to represent an image collection by a set of learnable elements composed together to synthesize the images and optimized by gradient descent. We first demonstrate the effectiveness of this idea by discovering 2D elements related to semantic objects represented by a large image collection. Our approach have performances similar to the best concurrent methods which synthesize images with neural networks, and ours comes with better interpretability. We also showcase the capability of this idea by discovering 3D elements related to simple primitive shapes given as input a collection of images depicting a scene from multiple viewpoints. Compared to prior works finding primitives in 3D point clouds, we showcase much better qualitative and quantitative performances.The third contribution is more technical and consist in a new formulation to compute differentiable mesh rendering. Specifically, we formulate the differentiable rendering of a 3D mesh as the alpha compositing of the mesh faces in an increasing depth order. Compared to prior works, this formulation is key to enable us to learn 3D meshes without requiring object region annotations. In addition, it allows us to seamlessly introduce the possibility to learn transparent meshes, which we design to model a scene as a composition of a variable number of meshes
Zhukov, Dimitri. "Learning to localize goal-oriented actions with weak supervision." Electronic Thesis or Diss., Université Paris sciences et lettres, 2021. http://www.theses.fr/2021UPSLE105.
Повний текст джерелаThe goal of this thesis is to develop methods for automatic understanding of video content. We focus on instructional videos that demonstrate how to perform complex tasks, such as making an omelette or hanging a picture. First, we investigate learning visual models for the steps of tasks, using only a list of steps for each task, instead of costly and time consuming human annotations. Our model allows us to share the information between the tasks on the substep level, effectively multiplying the amount of available training data. We demonstrate the benefits of our method on a newly collected dataset of instructional videos, CrossTask. Next, we present a method for isolating taskrelated actions from the surrounding background, that doesn’t rely on human supervision. Finally, we learn to associate natural language instructions with the corresponding objects within the 3D scene, reconstructed from the videos
Ho, Vinh Thanh. "Techniques avancées d'apprentissage automatique basées sur la programmation DC et DCA." Electronic Thesis or Diss., Université de Lorraine, 2017. http://www.theses.fr/2017LORR0289.
Повний текст джерелаIn this dissertation, we develop some advanced machine learning techniques in the framework of online learning and reinforcement learning (RL). The backbones of our approaches are DC (Difference of Convex functions) programming and DCA (DC Algorithm), and their online version that are best known as powerful nonsmooth, nonconvex optimization tools. This dissertation is composed of two parts: the first part studies some online machine learning techniques and the second part concerns RL in both batch and online modes. The first part includes two chapters corresponding to online classification (Chapter 2) and prediction with expert advice (Chapter 3). These two chapters mention a unified DC approximation approach to different online learning algorithms where the observed objective functions are 0-1 loss functions. We thoroughly study how to develop efficient online DCA algorithms in terms of theoretical and computational aspects. The second part consists of four chapters (Chapters 4, 5, 6, 7). After a brief introduction of RL and its related works in Chapter 4, Chapter 5 aims to provide effective RL techniques in batch mode based on DC programming and DCA. In particular, we first consider four different DC optimization formulations for which corresponding attractive DCA-based algorithms are developed, then carefully address the key issues of DCA, and finally, show the computational efficiency of these algorithms through various experiments. Continuing this study, in Chapter 6 we develop DCA-based RL techniques in online mode and propose their alternating versions. As an application, we tackle the stochastic shortest path (SSP) problem in Chapter 7. Especially, a particular class of SSP problems can be reformulated in two directions as a cardinality minimization formulation and an RL formulation. Firstly, the cardinality formulation involves the zero-norm in objective and the binary variables. We propose a DCA-based algorithm by exploiting a DC approximation approach for the zero-norm and an exact penalty technique for the binary variables. Secondly, we make use of the aforementioned DCA-based batch RL algorithm. All proposed algorithms are tested on some artificial road networks
Chen, Yuxin. "Apprentissage interactif de mots et d'objets pour un robot humanoïde." Electronic Thesis or Diss., Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLY003.
Повний текст джерелаFuture applications of robotics, especially personal service robots, will require continuous adaptability to the environment, and particularly the ability to recognize new objects and learn new words through interaction with humans. Though having made tremendous progress by using machine learning, current computational models for object detection and representation still rely heavily on good training data and ideal learning supervision. In contrast, two year old children have an impressive ability to learn to recognize new objects and at the same time to learn the object names during interaction with adults and without precise supervision. Therefore, following the developmental robotics approach, we develop in the thesis learning approaches for objects, associating their names and corresponding features, inspired by the infants' capabilities, in particular, the ambiguous interaction with humans, inspired by the interaction that occurs between children and parents.The general idea is to use cross-situational learning (finding the common points between different presentations of an object or a feature) and to implement multi-modal concept discovery based on two latent topic discovery approaches : Non Negative Matrix Factorization (NMF) and Latent Dirichlet Association (LDA). Based on vision descriptors and sound/voice inputs, the proposed approaches will find the underlying regularities in the raw dataflow to produce sets of words and their associated visual meanings (eg. the name of an object and its shape, or a color adjective and its correspondence in images). We developed a complete approach based on these algorithms and compared their behavior in front of two sources of uncertainties: referential ambiguities, in situations where multiple words are given that describe multiple objects features; and linguistic ambiguities, in situations where keywords we intend to learn are merged in complete sentences. This thesis highlights the algorithmic solutions required to be able to perform efficient learning of these word-referent associations from data acquired in a simplified but realistic acquisition setup that made it possible to perform extensive simulations and preliminary experiments in real human-robot interactions. We also gave solutions for the automatic estimation of the number of topics for both NMF and LDA.We finally proposed two active learning strategies, Maximum Reconstruction Error Based Selection (MRES) and Confidence Based Exploration (CBE), to improve the quality and speed of incremental learning by letting the algorithms choose the next learning samples. We compared the behaviors produced by these algorithms and show their common points and differences with those of humans in similar learning situations
Pascal, Barbara. "Estimation régularisée d'attributs fractals par minimisation convexe pour la segmentation de textures : formulations variationnelles conjointes, algorithmes proximaux rapides et sélection non supervisée des paramètres de régularisation; Applications à l'étude du frottement solide et de la microfluidique des écoulements multiphasiques." Thesis, Lyon, 2020. http://www.theses.fr/2020LYSEN042.
Повний текст джерелаIn this doctoral thesis several scale-free texture segmentation procedures based on two fractal attributes, the Hölder exponent, measuring the local regularity of a texture, and local variance, are proposed.A piecewise homogeneous fractal texture model is built, along with a synthesis procedure, providing images composed of the aggregation of fractal texture patches with known attributes and segmentation. This synthesis procedure is used to evaluate the proposed methods performance.A first method, based on the Total Variation regularization of a noisy estimate of local regularity, is illustrated and refined thanks to a post-processing step consisting in an iterative thresholding and resulting in a segmentation.After evidencing the limitations of this first approach, deux segmentation methods, with either "free" or "co-located" contours, are built, taking in account jointly the local regularity and the local variance.These two procedures are formulated as convex nonsmooth functional minimization problems.We show that the two functionals, with "free" and "co-located" penalizations, are both strongly-convex. and compute their respective strong convexity moduli.Several minimization schemes are derived, and their convergence speed are compared.The segmentation performance of the different methods are evaluated over a large amount of synthetic data in configurations of increasing difficulty, as well as on real world images, and compared to state-of-the-art procedures, including convolutional neural networks.An application for the segmentation of multiphasic flow through a porous medium experiment images is presented.Finally, a strategy for automated selection of the hyperparameters of the "free" and "co-located" functionals is built, inspired from the SURE estimator of the quadratic risk
Faucheux, Lilith. "Learning from incomplete biomedical data : guiding the partition toward prognostic information." Electronic Thesis or Diss., Université Paris Cité, 2021. http://www.theses.fr/2021UNIP5242.
Повний текст джерелаThe topic of this thesis is partition learning analyses in the context of incomplete data. Two methodological development are presented, with two medical and biomedical applications. The first methodological development concerns the implementation of unsupervised partition learning in the presence of incomplete data. Two types of incomplete data were considered: missing data and left-censored data (that is, values “lower than some detection threshold"), and handled through multiple imputation (MI) framework. Multivariate imputation by chained equation (MICE) was used to perform tailored imputations for each type of incomplete data. Then, for each imputed dataset, unsupervised learning was performed, with a data-based selected number of clusters. Last, a consensus clustering algorithm was used to pool the partitions, as an alternative to Rubin's rules. The second methodological development concerns the implementation of semisupervised partition learning in an incomplete dataset, to combine data structure and patient survival. This aimed at identifying patient profiles that relate both to differences in the group structure extracted from the data, and in the patients' prognosis. The supervised (prognostic value) and unsupervised (group structure) objectives were combined through Pareto multi-objective optimization. Missing data were handled, as above, through MI, with Rubin's rules used to combine the supervised and unsupervised objectives across the imputations, and the optimal partitions pooled using consensus clustering. Two applications are provided, one on the immunological landscape of the breast tumor microenvironment and another on the COVID-19 infection in the context of a hematological disease
Bakri, Sihem. "Towards enforcing network slicing in 5G networks." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS067.
Повний текст джерелаThe current architecture “one size fits all” of 4G network cannot support the next-generation 5G heterogeneous services criteria. Therefore, research around 5G aims to provide more adequate architectures and mechanisms to deal with this purpose. The 5G architecture is envisioned to accommodate the diverse and conflicting demands of services in terms of latency, bandwidth, and reliability, which cannot be sustained by the same network infrastructure. In this context, network slicing provided by network virtualization allows the infrastructure to be divided into different slices. Each slice is tailored to meet specific service requirements allowing different services (such as automotive, Internet of Things, etc.) to be provided by different network slice instances. Each of these instances consists of a set of virtual network functions that run on the same infrastructure with specially adapted orchestration. Three main service classes of network slicing have been defined by the researchers as follows: Enhanced Mobile Broadband (eMBB), massive Machine Type Communication (mMTC), and ultra-Reliable and Low-Latency Communication (uRLLC). One of the main challenges when it comes to deploying Network Slices is slicing the Radio Access Network (RAN). Indeed, managing RAN resources and sharing them among Network Slices is an increasingly difficult task, which needs to be properly designed. This thesis proposes solutions that aim to improve network performance, and introduce flexibility and greater utilization of network resources by accurately and dynamically provisioning the activated network slices with the appropriate amounts of resources to meet their diverse requirements
Velcin, Julien. "Extraction automatique de stéréotypes à partir de données symboliques et lacunaires." Paris 6, 2005. http://www.theses.fr/2005PA066465.
Повний текст джерелаOudjail, Veïs. "Réseaux de neurones impulsionnels appliqués à la vision par ordinateur." Electronic Thesis or Diss., Université de Lille (2022-....), 2022. http://www.theses.fr/2022ULILB048.
Повний текст джерелаArtificial neural networks (ANN) have become a must-have technique in computer vision, a trend that started during the 2012 ImageNet challenge. However, this success comes with a non-negligible human cost for manual data labeling, very important in model learning, and a high energy cost caused by the need for large computational resources. Spiking Neural Networks (SNN) provide solutions to these problems. It is a particular class of ANNs, close to the biological model, in which neurons communicate asynchronously by representing information through spikes. The learning of SNNs can rely on an unsupervised rule: the STDP. It modulates the synaptic weights according to the local temporal correlations observed between the incoming and outgoing spikes. Different hardware architectures have been designed to exploit the properties of SNNs (asynchrony, sparse and local operation, etc.) in order to design low-power solutions, some of them dividing the cost by several orders of magnitude. SNNs are gaining popularity and there is growing interest in applying them to vision. Recent work shows that SNNs are maturing by being competitive with the state of the art on "simple" image datasets such as MNIST (handwritten numbers) but not on more complex datasets. However, SNNs can potentially stand out from ANNs in video processing. The first reason is that these models incorporate an additional temporal dimension. The second reason is that they lend themselves well to the use of event-driven cameras. They are bio-inspired sensors that perceive temporal contrasts in a scene, in other words, they are sensitive to motion. Each pixel can detect a light variation (positive or negative), which triggers an event. Coupling these cameras to neuromorphic chips allows the creation of totally asynchronous and massively parallelized vision systems. The objective of this thesis is to exploit the capabilities offered by SNNs in video processing. In order to explore the potential offered by SNNs, we are interested in motion analysis and more particularly in motion direction estimation. The goal is to develop a model capable of learning incrementally, without supervision and with few examples, to extract spatiotemporal features. We have therefore performed several studies examining the different points mentioned using synthetic event datasets. We show that the tuning of the SNN parameters is essential for the model to be able to extract useful features. We also show that the model is able to learn incrementally by presenting it with new classes without deteriorating the performance on the mastered classes. Finally, we discuss some limitations, especially on the weight learning, suggesting the possibility of more delay learning, which are still not very well exploited and which could mark a break with ANNs
Cler, Gauthier. "Horizontal Side Channel Attacks on Noisy Traces." Electronic Thesis or Diss., Université de Montpellier (2022-....), 2024. http://www.theses.fr/2024UMONS010.
Повний текст джерелаRecently introduced to the field of side channel analysis, neural networks have showed to be a powerful and relevant alternative to template attacks. However, their applicability is limited to profiled attack context, as supervised training is needed in order to build a relevant generalized model. When profiling on an open device is not possible, and vertical attacks cannot be applied, the only left possible approach is horizontal attacks. While several contributions have been made for tackling horizontal attacks on asymmetric cryptography algorithms implementations such as RSA or elliptic curve cryptography, their performance remains low and their applicability hard in real life scenario with the presence of high noise. Still, another neural network family known as unsupervised learning neural networks exists, which would not require an open device access and. It must be known if these networks unsupervised learning paradigm and their associated topology can be applied to the context of side-channel attacks and if such is the case, whether or not they can provide better results than traditional methods. Thus, In this work, several approaches are considered to improve clustering based horizontal side channel attacks efficiency. A novel methodology based on statistical analysis is also introduced for univariate points of interest selection. Additionally, an alternative metric for quantifying points of interest exploitability in a clustering attack is proposed and compared to commonly used metrics. The proposed methods allow providing significant improvement over state of the art attacks performance and giving a better explainability of obtained results