Índice
Literatura académica sobre el tema "Apprentissage profond Bayésien"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte las listas temáticas de artículos, libros, tesis, actas de conferencias y otras fuentes académicas sobre el tema "Apprentissage profond Bayésien".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Tesis sobre el tema "Apprentissage profond Bayésien"
Rossi, Simone. "Improving Scalability and Inference in Probabilistic Deep Models". Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS042.
Texto completoThroughout the last decade, deep learning has reached a sufficient level of maturity to become the preferred choice to solve machine learning-related problems or to aid decision making processes.At the same time, deep learning is generally not equipped with the ability to accurately quantify the uncertainty of its predictions, thus making these models less suitable for risk-critical applications.A possible solution to address this problem is to employ a Bayesian formulation; however, while this offers an elegant treatment, it is analytically intractable and it requires approximations.Despite the huge advancements in the last few years, there is still a long way to make these approaches widely applicable.In this thesis, we address some of the challenges for modern Bayesian deep learning, by proposing and studying solutions to improve scalability and inference of these models.The first part of the thesis is dedicated to deep models where inference is carried out using variational inference (VI).Specifically, we study the role of initialization of the variational parameters and we show how careful initialization strategies can make VI deliver good performance even in large scale models.In this part of the thesis we also study the over-regularization effect of the variational objective on over-parametrized models.To tackle this problem, we propose an novel parameterization based on the Walsh-Hadamard transform; not only this solves the over-regularization effect of VI but it also allows us to model non-factorized posteriors while keeping time and space complexity under control.The second part of the thesis is dedicated to a study on the role of priors.While being an essential building block of Bayes' rule, picking good priors for deep learning models is generally hard.For this reason, we propose two different strategies based (i) on the functional interpretation of neural networks and (ii) on a scalable procedure to perform model selection on the prior hyper-parameters, akin to maximization of the marginal likelihood.To conclude this part, we analyze a different kind of Bayesian model (Gaussian process) and we study the effect of placing a prior on all the hyper-parameters of these models, including the additional variables required by the inducing-point approximations.We also show how it is possible to infer free-form posteriors on these variables, which conventionally would have been otherwise point-estimated
Theobald, Claire. "Bayesian Deep Learning for Mining and Analyzing Astronomical Data". Electronic Thesis or Diss., Université de Lorraine, 2023. http://www.theses.fr/2023LORR0081.
Texto completoIn this thesis, we address the issue of trust in deep learning predictive systems in two complementary research directions. The first line of research focuses on the ability of AI to estimate its level of uncertainty in its decision-making as accurately as possible. The second line, on the other hand, focuses on the explainability of these systems, that is, their ability to convince human users of the soundness of their predictions.The problem of estimating the uncertainties is addressed from the perspective of Bayesian Deep Learning. Bayesian Neural Networks assume a probability distribution over their parameters, which allows them to estimate different types of uncertainties. First, aleatoric uncertainty which is related to the data, but also epistemic uncertainty which quantifies the lack of knowledge the model has on the data distribution. More specifically, this thesis proposes a Bayesian neural network can estimate these uncertainties in the context of a multivariate regression task. This model is applied to the regression of complex ellipticities on galaxy images as part of the ANR project "AstroDeep''. These images can be corrupted by different sources of perturbation and noise which can be reliably estimated by the different uncertainties. The exploitation of these uncertainties is then extended to galaxy mapping and then to "coaching'' the Bayesian neural network. This last technique consists of generating increasingly complex data during the model's training process to improve its performance.On the other hand, the problem of explainability is approached from the perspective of counterfactual explanations. These explanations consist of identifying what changes to the input parameters would have led to a different prediction. Our contribution in this field is based on the generation of counterfactual explanations relying on a variational autoencoder (VAE) and an ensemble of predictors trained on the latent space generated by the VAE. This method is particularly adapted to high-dimensional data, such as images. In this case, they are referred as counterfactual visual explanations. By exploiting both the latent space and the ensemble of classifiers, we can efficiently produce visual counterfactual explanations that reach a higher degree of realism than several state-of-the-art methods
Wolinski, Pierre. "Structural Learning of Neural Networks". Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASS026.
Texto completoThe structure of a neural network determines to a large extent its cost of training and use, as well as its ability to learn. These two aspects are usually in competition: the larger a neural network is, the better it will perform the task assigned to it, but the more it will require memory and computing time resources for training. Automating the search of efficient network structures -of reasonable size and performing well- is then a very studied question in this area. Within this context, neural networks with various structures are trained, which requires a new set of training hyperparameters for each new structure tested. The aim of the thesis is to address different aspects of this problem. The first contribution is a training method that operates within a large perimeter of network structures and tasks, without needing to adjust the learning rate. The second contribution is a network training and pruning technique, designed to be insensitive to the initial width of the network. The last contribution is mainly a theorem that makes possible to translate an empirical training penalty into a Bayesian prior, theoretically well founded. This work results from a search for properties that theoretically must be verified by training and pruning algorithms to be valid over a wide range of neural networks and objectives
Cutajar, Kurt. "Broadening the scope of gaussian processes for large-scale learning". Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS063.
Texto completoThe renewed importance of decision making under uncertainty calls for a re-evaluation of Bayesian inference techniques targeting this goal in the big data regime. Gaussian processes (GPs) are a fundamental building block of many probabilistic kernel machines; however, the computational and storage complexity of GPs hinders their scaling to large modern datasets. The contributions presented in this thesis are two-fold. We first investigate the effectiveness of exact GP inference on a computational budget by proposing a novel scheme for accelerating regression and classification by way of preconditioning. In the spirit of probabilistic numerics, we also show how the numerical uncertainty introduced by approximate linear algebra should be adequately evaluated and incorporated. Bridging the gap between GPs and deep learning techniques remains a pertinent research goal, and the second broad contribution of this thesis is to establish and reinforce the role of GPs, and their deep counterparts (DGPs), in this setting. Whereas GPs and DGPs were once deemed unfit to compete with alternative state-of-the-art methods, we demonstrate how such models can also be adapted to the large-scale and complex tasks to which machine learning is now being applied
Kozyrskiy, Bogdan. "Exploring the Intersection of Bayesian Deep Learning and Gaussian Processes". Electronic Thesis or Diss., Sorbonne université, 2023. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2023SORUS064archi.pdf.
Texto completoDeep learning played a significant role in establishing machine learning as a must-have instrument in multiple areas. The use of deep learning poses several challenges. Deep learning requires a lot of computational power for training and applying models. Another problem with deep learning is its inability to estimate the uncertainty of the predictions, which creates obstacles in risk-sensitive applications. This thesis presents four projects to address these problems: We propose an approach making use of Optical Processing Units to reduce energy consumption and speed up the inference of deep models. We address the problem of uncertainty estimates for classification with Bayesian inference. We introduce techniques for deep models that decreases the cost of Bayesian inference. We developed a novel framework to accelerate Gaussian Process regression. We propose a technique to impose meaningful functional priors for deep models through Gaussian Processes
Boonkongkird, Chotipan. "Deep learning for Lyman-alpha based cosmology". Electronic Thesis or Diss., Sorbonne université, 2023. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2023SORUS733.pdf.
Texto completoAs cosmological surveys advance and become more sophisticated, they provide data with increasing resolution and volume. The Lyman-α forest has emerged as a powerful probe to study the intergalactic medium (IGM) properties up to a very high redshift. Analysing this extensive data requires advanced hydrodynamical simulations capable of resolving the observational data, which demands robust hardware and a considerable amount of computational time. Recent developments in machine learning, particularly neural networks, offer potential solutions. With their ability to function as universal fitting mechanisms, neural networks are gaining traction in various disciplines, including astrophysics and cosmology. In this doctoral thesis, we explore a machine learning framework, specifically, an artificial neural network to emulate hydrodynamical simulations from N-body simulations of dark matter. The core principle of this work is based on the fluctuating Gunn-Peterson approximation (FGPA), a framework commonly used to emulate the Lyman-α forest from dark matter. While useful for physical understanding, the FGPA misses to properly predict the absorption by neglecting non-locality in the construction of the IGM. Instead, our method includes the diversity of the IGM while being interpretable, which does not exclusively benefit the Lyman-α forest and extends to other applications. It also provides a more efficient solution to generate simulations, significantly reducing time compared to standard hydrodynamical simulations. We also test its resilience and explore the potential of using this framework to generalise to various astrophysical hypotheses of the IGM physics using a transfer learning method. We discuss how the results relate to other existing methods. Finally, the Lyman-α simulator typically constructs the observational volume using a single timestep of the cosmological simulations. This implies an identical astrophysical environment everywhere, which does not reflect the real universe. We explore and experiment to go beyond this limitation with our emulator, accounting for variable baryonic effects along the line of sight. While this is still preliminary, it could become a framework for constructing consistent light-cones. We apply neural networks to interpolate astrophysical feedback across different cells in simulations to provide mock observables more realistic to the real universe, which would allow us to understand the nature of IGM better and to constrain the ΛCDM model
Tran, Gia-Lac. "Advances in Deep Gaussian Processes : calibration and sparsification". Electronic Thesis or Diss., Sorbonne université, 2020. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2020SORUS410.pdf.
Texto completoGaussian Processes (GPs) are an attractive specific way of doing non-parametric Bayesian modeling in a supervised learning problem. It is well-known that GPs are able to make inferences as well as predictive uncertainties with a firm mathematical background. However, GPs are often unfavorable by the practitioners due to their kernel's expressiveness and the computational requirements. Integration of (convolutional) neural networks and GPs are a promising solution to enhance the representational power. As our first contribution, we empirically show that these combinations are miscalibrated, which leads to over-confident predictions. We also propose a novel well-calibrated solution to merge neural structures and GPs by using random features and variational inference techniques. In addition, these frameworks can be intuitively extended to reduce the computational cost by using structural random features. In terms of computational cost, the exact Gaussian Processes require the cubic complexity to training size. Inducing point-based Gaussian Processes are a common choice to mitigate the bottleneck by selecting a small set of active points through a global distillation from available observations. However, the general case remains elusive and it is still possible that the required number of active points may exceed a certain computational budget. In our second study, we propose Sparse-within-Sparse Gaussian Processes which enable the approximation with a large number of inducing points without suffering a prohibitive computational cost
Tran, Trung-Minh. "Contributions to Agent-Based Modeling and Its Application in Financial Market". Electronic Thesis or Diss., Université Paris sciences et lettres, 2023. http://www.theses.fr/2023UPSLP022.
Texto completoThe analysis of complex models such as financial markets helps managers to make reasonable policies and traders to choose effective trading strategies. Agent-based modeling is a computational methodology to model complex systems and analyze the influence of different assumptions on the behaviors of agents. In the scope of this thesis, we consider a financial market model that includes 3 types of agent: technical agents, fundamental agents and noise agents. We start with the technical agent with the challenge of optimizing a trading strategy based on technical analysis through an automated trading system. Then, the proposed optimization methods are applied with suitable objective functions to optimize the parameters for the ABM model. The study was conducted with a simple ABM model including only noise agents, then the model was extended to include different types of agents. The first part of the thesis investigates the trading behavior of technical agents. Different approaches are introduced such as: Genetic Algorithm, Bayesian Optimization and Deep Reinforcement Learning. The trading strategies are built based on a leading indicator, Relative Strength Index, and two lagging indicators, Bollinger Band and Moving Average Convergence-Divergence. Multiple experiments are performed in different markets including: cryptocurrency market, stock market and crypto futures market. The results show that optimized strategies from proposed approaches can generate higher returns than their typical form and Buy and Hold strategy. Using the results from the optimization of trading strategies, we propose a new approach to optimize the parameters of the agent-based model. The second part of the thesis presents an application of agent-based modeling to the stock market. As a result, we have shown that ABM models can be optimized using the Bayesian Optimization method with multiple objective functions. The stylized facts of the actual market can be reproduced by carefully constructing the objective functions of the agent. Our work includes the development of an environment, the behaviors of different agents and their interactions. Bayesian optimization method with Kolmogorov-Smirnov test as objective function has shown advantages and potential in estimating an optimal set of parameters for an artificial financial market model. The model we propose is capable of reproducing the stylized facts of the real market. Furthermore, a new stylized fact about the proportion of traders in the market is presented. With empirical data of the Dow Jones Industrial Average index, we found that fundamental traders account for 9%-11% of all traders in the stock market. In the future, more research will be done to improve the model and optimization methods, such as applying machine learning models, multi-agent reinforcement learning or considering the application in different markets and traded instruments
Kodi, Ramanah Doogesh. "Bayesian statistical inference and deep learning for primordial cosmology and cosmic acceleration". Thesis, Sorbonne université, 2019. http://www.theses.fr/2019SORUS169.
Texto completoThe essence of this doctoral research constitutes the development and application of novel Bayesian statistical inference and deep learning techniques to meet statistical challenges of massive and complex data sets from next-generation cosmic microwave background (CMB) missions or galaxy surveys and optimize their scientific returns to ultimately improve our understanding of the Universe. The first theme deals with the extraction of the E and B modes of the CMB polarization signal from the data. We have developed a high-performance hierarchical method, known as the dual messenger algorithm, for spin field reconstruction on the sphere and demonstrated its capabilities in reconstructing pure E and B maps, while accounting for complex and realistic noise models. The second theme lies in the development of various aspects of Bayesian forward modelling machinery for optimal exploitation of state-of-the-art galaxy redshift surveys. We have developed a large-scale Bayesian inference framework to constrain cosmological parameters via a novel implementation of the Alcock-Paczyński test and showcased our cosmological constraints on the matter density and dark energy equation of state. With the control of systematic effects being a crucial limiting factor for modern galaxy redshift surveys, we also presented an augmented likelihood which is robust to unknown foreground and target contaminations. Finally, with a view to building fast complex dynamics emulators in our above Bayesian hierarchical model, we have designed a novel halo painting network that learns to map approximate 3D dark matter fields to realistic halo distributions