Literatura científica selecionada sobre o tema "Réseaux neuronaux basés sur la physique"
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Consulte a lista de atuais artigos, livros, teses, anais de congressos e outras fontes científicas relevantes para o tema "Réseaux neuronaux basés sur la physique".
Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.
Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.
Artigos de revistas sobre o assunto "Réseaux neuronaux basés sur la physique"
Lek, S., I. Dimopoulos, M. Derraz e Y. El Ghachtoul. "Modélisation de la relation pluie-débit à l'aide des réseaux de neurones artificiels". Revue des sciences de l'eau 9, n.º 3 (12 de abril de 2005): 319–31. http://dx.doi.org/10.7202/705255ar.
Texto completo da fonteFaretta, Elisa, e Cristina Civilotti. "Thérapie EMDR et psycho-oncologie : un pont entre le corps et l'esprit". Journal of EMDR Practice and Research 11, n.º 4 (2017): 102E—117E. http://dx.doi.org/10.1891/1933-3196.11.4.102.
Texto completo da fonteGenre-Grandpierre, Cyrille. "Changing the metric of the roads networks in order to regulate automobile dependence: “the slow networks”". Les Cahiers Scientifiques du Transport - Scientific Papers in Transportation 52 | 2007 (30 de novembro de 2007). http://dx.doi.org/10.46298/cst.12060.
Texto completo da fonteTeses / dissertações sobre o assunto "Réseaux neuronaux basés sur la physique"
Bois, Léo. "Méthodes numériques basées sur l'apprentissage pour les EDP hyperboliques et cinétiques". Electronic Thesis or Diss., Strasbourg, 2023. http://www.theses.fr/2023STRAD060.
Texto completo da fonteDifferent applications of neural networks for numerical methods are explored, in the context of fluid or plasma simulation.A first application is the learning of a closure for a macroscopic model, based on data from a kinetic model. Numerical results are given for the Vlasov-Poisson equation in 1D and the Boltzmann equation in 2D.A second application is the learning of problem-dependent parameters in numerical schemes. In this way, an artificial viscosity coefficient is learned for a discontinuous Galerkin scheme, and a relaxation matrix for the Lattice-Boltzmann method
Doriat, Aurélien. "Caractérisation des couplages aéro-thermo-mécaniques lors d’un vieillissement par thermo-oxydation de composites à matrice polymère soumis à un écoulement rapide et chauffé". Electronic Thesis or Diss., Chasseneuil-du-Poitou, Ecole nationale supérieure de mécanique et d'aérotechnique, 2024. http://www.theses.fr/2024ESMA0018.
Texto completo da fonteCarbon fiber-reinforced polymer matrix composites (CFRP) are widely used in cold aeronautical structures. In aeronautical engine applications, such as fan blades, these materials can be subjected to particularly severe environmental conditions, with temperatures reaching up to 120 ◦C and airflow speeds close to Mach 1. It is well established that epoxy polymers are prone to thermo-oxidation phenomena when exposed to high temperatures.This phenomenon involves the diffusion and reaction of oxygen within the polymer, leading to color changes, antiplasticization of the material, and embrittlement. Until now, aging tests have been mainly conducted in static air ovens, providing a detailed understanding of the phenomenon under these conditions. However, the impact of airflow on thermo-oxidation remains to be explored.This study thus aims to deepen the understanding of the coupling between airflow and material degradation due to thermo-oxidation.Samples were aged in an oven under air at atmospheric pressure and in the BATH wind tunnel, adapted for these tests and capable of generating an airflow at over 150 ◦C and Mach 1, thereby reproducing the most severe usage conditions encountered in aircraft engines. This comparison between oven and wind tunnel tests showed an acceleration of aging in the wind tunnel. To achieve this result, an experimental technique based on the color change induced by oxidation was developed and used. This technique was validated with indentation tests. With this improved understanding of the accelerated aging, a coupled model between the airflow, oxidation chemistry, and changes in mechanical properties was established to better understand the interfacial mechanisms. This modeling comprises three steps. The pressure and temperature fields at the sample surface were calculated using Reynolds-Averaged Navier-Stokes (RANS) fluid simulations. Then, a mechanistic model was used to describe the chemical reactions during oxidation. Finally, based on thecolor measurements, a physics-informed neural network (PINN) was implemented to couple the chemical quantities to the mechanical properties
Eclercy, Daniel. "Contribution à l'étude de synthèse d'antennes et de réseaux. Elaboration d'outils de calcul originaux basés sur des approches déterministes et stochastiques". Limoges, 1998. http://www.theses.fr/1998LIMO0018.
Texto completo da fonteBlagouchine, Iaroslav. "Modélisation et analyse de la parole : Contrôle d’un robot parlant via un modèle interne optimal basé sur les réseaux de neurones artificiels. Outils statistiques en analyse de la parole". Thesis, Aix-Marseille 2, 2010. http://www.theses.fr/2010AIX26666.
Texto completo da fonteThis Ph.D. dissertation deals with speech modeling and processing, which both share the speech quality aspect. An optimum internal model with constraints is proposed and discussed for the control of a biomechanical speech robot based on the equilibrium point hypothesis (EPH, lambda-model). It is supposed that the robot internal space is composed of the motor commands lambda of the equilibrium point hypothesis. The main idea of the work is that the robot movements, and in particular the robot speech production, are carried out in such a way that, the length of the path, traveled in the internal space, is minimized under acoustical and mechanical constraints. Mathematical aspect of the problem leads to one of the problems of variational calculus, the so-called geodesic problem, whose exact analytical solution is quite complicated. By using some empirical findings, an approximate solution for the proposed optimum internal model is then developed and implemented. It gives interesting and challenging results, and shows that the proposed internal model is quite realistic; namely, some similarities are found between the robot speech and the real one. Next, by aiming to analyze speech signals, several methods of statistical speech signal processing are developed. They are based on higher-order statistics (namely, on normalized central moments and on the fourth-order cumulant), as well as on the discrete normalized entropy. In this framework, we also designed an unbiased and efficient estimator of the fourth-order cumulant in both batch and adaptive versions
Delorme-Costil, Alexandra. "Modèles prédictifs et adaptatifs pour la gestion énergétique du bâtiment résidentiel individuel : réseaux de neurones artificiels basés sur les données usuellement disponibles". Thesis, Ecole nationale des Mines d'Albi-Carmaux, 2018. http://www.theses.fr/2018EMAC0020.
Texto completo da fonteThe use of predictive control permits to reduce the energy consumption of residential buildings without reducing the comfort of the inhabitant. The company BoostHeat develops a thermodynamic furnace with high energy efficiency for this purpose. Simultaneous production of domestic hot water (DHW) and heating allows many control strategies to optimize performance. The use of predictive controls makes it possible to anticipate energy needs, to take into account the impact of building inertia on indoor temperature and thus to make production management choices that minimize energy consumption. The models used today in predictive controls are binding. Indeed, these models require large amounts of data, either on a representative sample of buildings or on each modeled building. They may also need detailed studies of the building, the occupants and their consumption practices. In order to allow BoostHeat to use predictive control without going through a complex modeling step at every furnace installation, we propose adaptive models using information commonly available on a typical installation. We choose to develop artificial neural networks for the prediction on the one hand of the consumptions of DHW and on the other hand of the ambiant temperature of the building. Artificial neural networks are already used to model the energy consumption of a specific building, however our models are generic and automatically adapt to the building in which the furnace is installed. Many models are developed to study the impact of the choice of inputs, amounts of learning data and artificial neural network architecture on the accuracy of prediction. The DHW consumption prediction models are tested on three experimental cases while the indoor temperature prediction models are tested on two experimental cases and one hundred and twenty simulated cases. This makes it possible to test their adaptation to the entire French housing stock. We show, for the prediction of DHW consumption as for the indoor temperature prediction, that two weeks of collected data are sufficient for a good adaptation of the models to a specific case. The most efficient model for the prediction of domestic hot water consumption only needs the consumptions of the previous instants. The indoor temperature prediction model performs better on less isolated buildings. The results obtained are promising for the application of predictive controls on a large scale
Yu, Lei. "Fingerprinting based techniques for indoor localization exploiting UWB signal properties". Rennes 1, 2011. http://www.theses.fr/2011REN1S096.
Texto completo da fonteNowadays, wireless localization systems are considered as a potential technology for future services. Various techniques have been proposed for both indoor and outdoor localization systems. These techniques and systems allowed to conceive different LBSs. The two main processes a localization system must be able to do are the measurement of location-dependent parameters (RSSI, TOA,. . . ) and the estimation of position using different localization techniques. In this manuscript, the estimation and measurement of LDPs such as RSSI and TOA are investigated using a provided UWB measurements campaign. Four different TOA estimation techniques are proposed. RSSI based ranging techniques are also introduced. The main goal of this thesis is the study of fingerprinting based techniques for indoor localization. The neural networks technique is used to learn the fingerprinting database and to locate the targeted points. The construction of the neural networks and the adopted approaches are described. Both the pre-measured and the pre-simulated fingerprinting databases are established to be used in the fingerprinting techniques. Different fingerprints and different sizes of the database are utilized to evaluate the positioning performances. The MultiWall model is proposed to predict the RSSI fingerprint depending on the real propagation environment. An adaptation of the classic MultiWall model to take into account the effect of diffraction for the metallic furniture shows that it can improve the quality of positioning
Reganaz, Lucas. "Etude des fluctuations de résistance dans les ReRAM : origine physique, dépendance temporelle et impact sur la fiabilité de la mémoire". Electronic Thesis or Diss., Université Grenoble Alpes, 2024. http://www.theses.fr/2024GRALT012.
Texto completo da fonteThis thesis investigates the pivotal role of emerging non-volatile memory (NVM) technologies, with a primary focus on Resistive Random-Access Memory (ReRAM), in addressing the challenges of memory latency associated with the shrinking of logic components. The exploration begins by elucidating the fundamental physics of ReRAM and its potential applications in in-memory and neuromorphic computing.The second chapter delves into material engineering strategies to optimize ReRAM performance, covering aspects such as top electrode materials, doping effects, and the benefits of a bi-layer resistive switching (RS) oxide stack. These insights provide a foundation for subsequent investigations into device reliability.A Kinetic Monte Carlo (KMC) simulation framework is introduced in the third chapter, offering a powerful tool for probing the microscopic dynamic behavior of ReRAM. This framework becomes instrumental in the fourth chapter, where the physics of ReRAM reliability, specifically resistance fluctuations, is explored in depth. The analysis reveals intricate mechanisms governing fluctuations and their impact on metrics like the standard Failing Bit Count (FBC).In the final chapter, the application of ReRAM devices as synapses in artificial neural networks (ANNs) is revisited. Programming techniques and strategies to mitigate the impact of fluctuations, particularly in multi-level cell (MLC) ReRAM, are discussed. The thesis concludes by emphasizing the crucial role of ReRAM material stack engineering in designing reliable synapses for future computing paradigms.This comprehensive exploration contributes to advancing our understanding of ReRAM's potential, offering insights into device optimization, reliability, and its application in neuromorphic computing. Looking forward, the research underscores the significance of continued innovation in ReRAM material engineering to unlock its full capabilities and facilitate its integration into the evolving landscape of computing technologies
Grelier, Erwan. "Learning with tree-based tensor formats : Application to uncertainty quantification in vibroacoustics". Thesis, Ecole centrale de Nantes, 2019. http://www.theses.fr/2019ECDN0070.
Texto completo da fonteMany problems require the evaluation of complex parametrized models for many instances of the parameters, particularly for uncertainty quantification. When the model is costly to evaluate, it is usually approximated by another model cheaper to evaluate. The aim of this thesis is to develop statistical learning methods using model classes of functions in treebased tensor formats for the approximation of highdimensional functions, both for supervised and unsupervised learning tasks. These model classes, which are rank-structured functions parametrized by a tree-structured network of low-order tensors, can be interpreted as deep neural networks with particular architecture and activation functions. The approximation is obtained by empirical risk minimization over the set of functions in tree-based tensor format. For a high-dimensional function, or when little information on the function is available, the model class has to be carefully selected. We propose stable learning algorithms that adapt the tree and ranks and select the model based on crossvalidation estimates. Furthermore, some functions might only exhibit a low-rank structure after a suitable change of variables. For such cases, we propose adaptive learning algorithms with model classes combining tree-based tensor formats and changes of variables. The proposed algorithms are applied to uncertainty quantification in vibroacoustics. This thesis is included in the Joint Laboratory of Marine Technology between Naval Group, Centrale Nantes and Université de Nantes, and in the Eval-PI project
Dakkak, Mustapha. "Géo-localisation en environnement fermé des terminaux mobiles". Phd thesis, Université Paris-Est, 2012. http://tel.archives-ouvertes.fr/tel-00794586.
Texto completo da fonteHaberstich, Cécile. "Adaptive approximation of high-dimensional functions with tree tensor networks for Uncertainty Quantification". Thesis, Ecole centrale de Nantes, 2020. http://www.theses.fr/2020ECDN0045.
Texto completo da fonteUncertainty quantification problems for numerical models require a lot of simulations, often very computationally costly (in time and/or memory). This is why it is essential to build surrogate models that are cheaper to evaluate. In practice, the output of a numerical model is represented by a function, then the objective is to construct an approximation.The aim of this thesis is to construct a controlled approximation of a function while using as few evaluations as possible.In a first time, we propose a new method based on weighted least-squares to construct the approximation of a function onto a linear approximation space. We prove that the projection verifies a numerical stability property almost surely and a quasi-optimality property in expectation. In practice we observe that the sample size is closer to the dimension of the approximation space than with existing weighted least-squares methods.For high-dimensional approximation, and in order to exploit potential low-rank structures of functions, we consider the model class of functions in tree-based tensor formats. These formats admit a multilinear parametrization with parameters forming a tree network of low-order tensors and are therefore also called tree tensor networks. In this thesis we propose an algorithm for approximating functions in tree-based tensor formats. It consists in constructing a hierarchy of nested subspaces associated to the different levels of the tree. The construction of these subspaces relies on principal component analysis extended to multivariate functions and the new weighted least-squares method. To reduce the number of evaluations necessary to build the approximation with a certain precision, we propose adaptive strategies for the control of the discretization error, the tree selection, the control of the ranks and the estimation of the principal components
Capítulos de livros sobre o assunto "Réseaux neuronaux basés sur la physique"
BELMONTE, Romain, Pierre TIRILLY, Ioan Marius BILASCO, Nacim IHADDADENE e Chaabane DJERABA. "Détection de points de repères faciaux par modélisation spatio-temporelle". In Analyse faciale en conditions non contrôlées, 105–49. ISTE Group, 2024. http://dx.doi.org/10.51926/iste.9111.ch3.
Texto completo da fonte