Dissertations / Theses on the topic 'Réseaux neuronaux pour les graphs'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Réseaux neuronaux pour les graphs.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Hafidi, Hakim. "Robust machine learning for Graphs/Networks." Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAT004.
Full textThis thesis addresses advancements in graph representation learning, focusing on the challengesand opportunities presented by Graph Neural Networks (GNNs). It highlights the significanceof graphs in representing complex systems and the necessity of learning node embeddings that capture both node features and graph structure. The study identifies key issues in GNNs, such as their dependence on high-quality labeled data, inconsistent performanceacross various datasets, and susceptibility to adversarial attacks.To tackle these challenges, the thesis introduces several innovative approaches. Firstly, it employs contrastive learning for node representation, enabling self-supervised learning that reduces reliance on labeled data. Secondly, a Bayesian-based classifier isproposed for node classification, which considers the graph’s structure to enhance accuracy. Lastly, the thesis addresses the vulnerability of GNNs to adversarialattacks by assessing the robustness of the proposed classifier and introducing effective defense mechanisms.These contributions aim to improve both the performance and resilience of GNNs in graph representation learning
Carboni, Lucrezia. "Graphes pour l’exploration des réseaux de neurones artificiels et de la connectivité cérébrale humaine." Electronic Thesis or Diss., Université Grenoble Alpes, 2023. http://www.theses.fr/2023GRALM060.
Full textThe main objective of this thesis is to explore brain and artificial neural network connectivity from agraph-based perspective. While structural and functional connectivity analysis has been extensivelystudied in the context of the human brain, there is a lack of a similar analysis framework in artificialsystems.To address this gap, this research focuses on two main axes.In the first axis, the main objective is to determine a healthy signature characterization of the humanbrain resting state functional connectivity. To achieve this objective, a novel framework is proposed,integrating traditional graph statistics and network reduction tools, to determine healthy connectivitypatterns. Hence, we build a graph pair-wise comparison and a classifier to identify pathological statesand rank associated perturbed brain regions. Additionally, the generalization and robustness of theproposed framework were investigated across multiple datasets and variations in data quality.The second research axis explores the benefits of brain-inspired connectivity exploration of artificialneural networks (ANNs) in the future perspective of more robust artificial systems development. Amajor robustness issue in ANN models is represented by catastrophic forgetting when the networkdramatically forgets previously learned tasks when adapting to new ones. Our work demonstrates thatgraph modeling offers a simple and elegant framework for investigating ANNs, comparing differentlearning strategies, and detecting deleterious behaviors such as catastrophic forgetting.Moreover, we explore the potential of leveraging graph-based insights to effectively mitigatecatastrophic forgetting, laying a foundation for future research and explorations in this area
Khalife, Sammy. "Graphes, géométrie et représentations pour le langage et les réseaux d'entités." Thesis, Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAX055.
Full textThe automated treatment of familiar objects, either natural or artifacts, always relies on a translation into entities manageable by computer programs. The choice of these abstract representations is always crucial for the efficiency of the treatments and receives the utmost attention from computer scientists and developers. However, another problem rises: the correspondence between the object to be treated and "its" representation is not necessarily one-to-one! Therefore, the ambiguous nature of certain discrete structures is problematic for their modeling as well as their processing and analysis with a program. Natural language, and in particular its textual representation, is an example. The subject of this thesis is to explore this question, which we approach using combinatorial and geometric methods. These methods allow us to address the problem of extracting information from large networks of entities and to construct representations useful for natural language processing.Firstly, we start by showing combinatorial properties of a family of graphs implicitly involved in sequential models. These properties essentially concern the inverse problem of finding a sequence representing a given graph. The resulting algorithms allow us to carry out an experimental comparison of different sequential models used in language modeling.Secondly, we consider an application for the problem of identifying named entities. Following a review of recent solutions, we propose a competitive method based on the comparison of knowledge graph structures which is less costly in annotating examples dedicated to the problem. We also establish an experimental analysis of the influence of entities from capital relations. This analysis suggests to broaden the framework for applying the identification of entities to knowledge bases of different natures. These solutions are used today in a software library in the banking sector.Then, we perform a geometric study of recently proposed representations of words, during which we discuss a geometric conjecture theoretically and experimentally. This study suggests that language analogies are difficult to transpose into geometric properties, and leads us to consider the paradigm of distance geometry in order to construct new representations.Finally, we propose a methodology based on the paradigm of distance geometry in order to build new representations of words or entities. We propose algorithms for solving this problem on some large scale instances, which allow us to build interpretable and competitive representations in performance for extrinsic tasks. More generally, we propose through this paradigm a new framework and research leadsfor the construction of representations in machine learning
Hubert, Nicolas. "Mesure et enrichissement sémantiques des modèles à base d'embeddings pour la prédiction de liens dans les graphes de connaissances." Electronic Thesis or Diss., Université de Lorraine, 2024. http://www.theses.fr/2024LORR0059.
Full textKnowledge graph embedding models (KGEMs) have gained considerable traction in recent years. These models learn a vector representation of knowledge graph entities and relations, a.k.a. knowledge graph embeddings (KGEs). This thesis specifically explores the advancement of KGEMs for the link prediction (LP) task, which is of utmost importance as it underpins several downstream applications such as recommender systems. In this thesis, various challenges around the use of KGEMs for LP are identified: the scarcity of semantically rich resources, the unidimensional nature of evaluation frameworks, and the lack of semantic considerations in prevailing machine learning-based approaches. Central to this thesis is the proposition of novel solutions to these challenges. Firstly, the thesis contributes to the development of semantically rich resources: mainstream datasets for link prediction are enriched using schema-based information, EducOnto and EduKG are proposed to overcome the paucity of resources in the educational domain, and PyGraft is introduced as an innovative open-source tool for generating synthetic ontologies and knowledge graphs. Secondly, the thesis proposes a new semantic-oriented evaluation metric, Sem@K, offering a multi-dimensional perspective on model performance. Importantly, popular models are reassessed using Sem@K, which reveals essential insights into their respective capabilities and highlights the need for multi-faceted evaluation frameworks. Thirdly, the thesis delves into the development of neuro-symbolic approaches, transcending traditional machine learning paradigms. These approaches do not only demonstrate improved semantic awareness but also extend their utility to diverse applications such as recommender systems. In summary, the present work not only redefines the evaluation and functionality of knowledge graph embedding models but also sets the stage for more versatile, interpretable AI systems, underpinning future explorations at the intersection of machine learning and symbolic reasoning
Bekkouch, Imad Eddine Ibrahim. "Auxiliary learning & Adversarial training pour les études des manuscrits médiévaux." Electronic Thesis or Diss., Sorbonne université, 2024. http://www.theses.fr/2024SORUL014.
Full textThis thesis is at the intersection of musicology and artificial intelligence, aiming to leverage AI to help musicologists with repetitive work, such as object searching in the museum's manuscripts. We annotated four new datasets for medieval manuscript studies: AMIMO, AnnMusiconis, AnnVihuelas, and MMSD. In the second part, we improve object detectors' performances using Transfer learning techniques and Few Shot Object Detection.In the third part, we discuss a powerful approach to Domain Adaptation, which is auxiliary learning, where we train the model on the target task and an extra task that allows for better stabilization of the model and reduces over-fitting.Finally, we discuss self-supervised learning, which does not use extra meta-data by leveraging the adversarial learning approach, forcing the model to extract domain-independent features
Mazari, Ahmed. "Apprentissage profond pour la reconnaissance d’actions en vidéos." Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS171.
Full textNowadays, video contents are ubiquitous through the popular use of internet and smartphones, as well as social media. Many daily life applications such as video surveillance and video captioning, as well as scene understanding require sophisticated technologies to process video data. It becomes of crucial importance to develop automatic means to analyze and to interpret the large amount of available video data. In this thesis, we are interested in video action recognition, i.e. the problem of assigning action categories to sequences of videos. This can be seen as a key ingredient to build the next generation of vision systems. It is tackled with AI frameworks, mainly with ML and Deep ConvNets. Current ConvNets are increasingly deeper, data-hungrier and this makes their success tributary of the abundance of labeled training data. ConvNets also rely on (max or average) pooling which reduces dimensionality of output layers (and hence attenuates their sensitivity to the availability of labeled data); however, this process may dilute the information of upstream convolutional layers and thereby affect the discrimination power of the trained video representations, especially when the learned action categories are fine-grained
Aissa, Wafa. "Réseaux de modules neuronaux pour un raisonnement visuel compositionnel." Electronic Thesis or Diss., Paris, HESAM, 2023. http://www.theses.fr/2023HESAC033.
Full textThe context of this PhD thesis is compositional visual reasoning. When presented with an image and a question pair, our objective is to have neural networks models answer the question by following a reasoning chain defined by a program. We assess the model's reasoning ability through a Visual Question Answering (VQA) setup.Compositional VQA breaks down complex questions into modular easier sub-problems.These sub-problems include reasoning skills such as object and attribute detection, relation detection, logical operations, counting, and comparisons. Each sub-problem is assigned to a different module. This approach discourages shortcuts, demanding an explicit understanding of the problem. It also promotes transparency and explainability.Neural module networks (NMN) are used to enable compositional reasoning. The framework is based on a generator-executor framework, the generator learns the translation of the question to its function program. The executor instantiates a neural module network where each function is assigned to a specific module. We also design a neural modules catalog and define the function and the structure of each module. The training and evaluations are conducted using the pre-processed GQA dataset cite{gqa}, which includes natural language questions, functional programs representing the reasoning chain, images, and corresponding answers.The research contributions revolve around the establishment of an NMN framework for the VQA task.One primary contribution involves the integration of vision and language pre-trained (VLP) representations into modular VQA. This integration serves as a ``warm-start" mechanism for initializing the reasoning process.The experiments demonstrate that cross-modal vision and language representations outperform uni-modal ones. This utilization enables the capture of intricate relationships within each individual modality while also facilitating alignment between different modalities, consequently enhancing overall accuracy of our NMN.Moreover, we explore various training techniques to enhance the learning process and improve cost-efficiency. In addition to optimizing the modules within the reasoning chain to collaboratively produce accurate answers, we introduce a teacher-guidance approach to optimize the intermediate modules in the reasoning chain. This ensures that these modules perform their specific reasoning sub-tasks without taking shortcuts or compromising the reasoning process's integrity. We propose and implement several teacher-guidance techniques, one of which draws inspiration from the teacher-forcing method commonly used in sequential models. Comparative analyses demonstrate the advantages of our teacher-guidance approach for NMNs, as detailed in our paper [1].We also introduce a novel Curriculum Learning (CL) strategy tailored for NMNs to reorganize the training examples and define a start-small training strategy. We begin by learning simpler programs and progressively increase the complexity of the training programs. We use several difficulty criteria to define the CL approach. Our findings demonstrate that by selecting the appropriate CL method, we can significantly reduce the training cost and required training data, with only a limited impact on the final VQA accuracy. This significant contribution forms the core of our paper [2].[1] W. Aissa, M. Ferecatu, and M. Crucianu. Curriculum learning for compositional visual reasoning. In Proceedings of VISIGRAPP 2023, Volume 5: VISAPP, 2023.[2] W. Aissa, M. Ferecatu, and M. Crucianu. Multimodal representations for teacher-guidedcompositional visual reasoning. In Advanced Concepts for Intelligent Vision Systems, 21st International Conference (ACIVS 2023). Springer International Publishing, 2023.[3] D. A. Hudson and C. D. Manning. GQA: A new dataset for real-world visual reasoning and compositional question answering. 2019
Foucher, Christophe. "Analyse et amélioration d'algorithmes neuronaux et non neuronaux de quantification vectorielle pour la compression d'images." Rennes 1, 2002. http://www.theses.fr/2002REN10120.
Full textHenniges, Philippe. "PSO pour l'apprentissage supervisé des réseaux neuronaux de type fuzzy ARTMAP." Mémoire, École de technologie supérieure, 2006. http://espace.etsmtl.ca/508/1/HENNIGES_Pihilippe.pdf.
Full textQuélavoine, Régis. "Etude de l'apprentissage et des structures des réseaux de neurones multicouches pour l'analyse de données." Avignon, 1997. http://www.theses.fr/1997AVIG0002.
Full textVo, Thi Quynh Trang. "Algorithms and Machine Learning for fair and classical combinatorial optimization." Electronic Thesis or Diss., Université Clermont Auvergne (2021-...), 2024. http://www.theses.fr/2024UCFA0035.
Full textCombinatorial optimization is a field of mathematics that searches for an optimal solution in a finite set of objects. It has crucial applications in many fields, including applied mathematics, software engineering, theoretical computer science, and machine learning. extit{Branch-and-cut} is one of the most widely-used algorithms for solving combinatorial optimization problems exactly. In this thesis, we focus on the computational aspects of branch-and-cut when studying two critical dimensions of combinatorial optimization: extit{the fairness of solutions} and extit{the integration of machine learning}.In Partef{part:1} (Chaptersef{chap:bnc-btsp} andef{chap:owa}), we study two common approaches to deal with the issue of fairness in combinatorial optimization, which has gained significant attention in the past decades. The first approach is extit{balanced combinatorial optimization}, which finds a fair solution by minimizing the difference between the largest and smallest components used. Due to the difficulties in bounding these components, to the best of our knowledge, no general exact framework based on mixed-integer linear programming (MILP) has been proposed for balanced combinatorial optimization. To address this gap, in Chapteref{chap:bnc-btsp}, we present a branch-and-cut algorithm and a novel class of local cutting planes tailored for balanced combinatorial optimization problems. We demonstrate the effectiveness of the proposed framework in the Balanced Traveling Salesman Problem. Additionally, we introduce bounding algorithms and mechanisms to fix variables to accelerate performance further.The second approach to handling the issue of fairness is extit{Ordered Weighted Average (OWA) combinatorial optimization}, which integrates the OWA operator into the objective function. Due to the ordering operator, OWA combinatorial optimization is nonlinear, even if its original constraints are linear. Two MILP formulations of different sizes have been introduced in the literature to linearize the OWA operator. However, which formulation performs best for OWA combinatorial optimization remains uncertain, as integrating the linearization methods may introduce additional difficulties. In Chapteref{chap:owa}, we provide theoretical and empirical comparisons of the two MILP formulations for OWA combinatorial optimization. In particular, we prove that the formulations are equivalent in terms of the linear programming relaxation. We empirically show that for OWA combinatorial optimization problems, the formulation with more variables can be solved faster with branch-and-cut.In Partef{part:2} (Chapteref{chap:mlbnc}), we develop methods for applying machine learning to enhance fundamental decision problems in branch-and-cut, with a focus on cut generation. Cut generation refers to the decision of whether to generate cuts or to branch at each node of the search tree. We empirically demonstrate that this decision significantly impacts branch-and-cut performance, especially for combinatorial cuts that exploit the facial structure of the convex hull of feasible solutions. We then propose a general framework combining supervised and reinforcement learning to learn effective strategies for generating combinatorial cuts in branch-and-cut. Our framework has two components: a cut detector to predict cut existence and a cut evaluator to choose between generating cuts and branching. Finally, we provide experimental results showing that the proposed method outperforms commonly used strategies for cut generation, even on instances larger than those used for training
Maktoobi, Sheler. "Couplage diffractif pour réseaux de neurones optiques." Thesis, Bourgogne Franche-Comté, 2020. http://www.theses.fr/2020UBFCD019.
Full textPhotonic networks with high performance can be considered as substrates for future computing systems. In comparison with electronics, photonic systems have substantial privileges, for instance the possibility of a fully parallel implementation of networks. Recently, neural networks have moved into the center of attention of the photonic community. One of the most important requirements for parallel large-scale photonic networks is to realize the connectivities. Diffraction is considered as a method to process the connections between the nodes (coupling) in optical neural networks. In the current thesis, we evaluate the scalability of a diffractive coupling in more details as follow:First, we begin with a general introductions for artificial intelligence, machine learning, artificial neural network and photonic neural networks. To establish a working neural network, learning rules are an essential part to optimize a configuration for obtaining a low error from the system, hence learning rules are introduced (Chapter 1). We investigate the fundamental concepts of diffractive coupling in our spatio-temporal reservoir. In that case, theory of diffraction is explained. We use an analytical scheme to provide the limits for the size of diffractive networks which is a part of our photonic neural network (Chapter 2). The concepts of diffractive coupling are investigated experimentally by two different experiments to confirm the analytical limits and to obtain maximum number of nodes which can be coupled in the photonic network (Chapter 3). Numerical simulations for such an experimental setup is modeled in two different schemes to obtain the maximum size of network numerically, which approaches a surface of 100 mm2 (Chapter 4). Finally, the complete photonic neural network is demonstrated. We design a spatially extended reservoir for 900 nodes. Consequently, our system generalizes the prediction for the chaotic Mackey–Glass sequence (Chapter 5)
Kara, Reda. "Une Approche modulaire du réseau de neurones CMAC pour la commande d'un système robot-vision." Mulhouse, 2002. http://www.theses.fr/2002MULH0704.
Full textThe work of this thesis investigates artificial neural networks capabilities to estimate robotic functions, and their performances as controllers. We propose an adaptive visual servoing scheme based on the CMAC ("Cerebellar Model Articulation Controller") network. The CMAC network is thus well suited for robot control but in practice there are two drawbacks: its output is "discrete" and its precision depends on its size. Thus, we have developed two modular neural : the HCMAC ("Hierarchical CMAC") and the AL_CMAC ("Adaptive Linear CMAC"). These two networks are a combination of networks of small size. The efficiency of the HCMAC and AL_CMAC neuro-controller is validated through visual servoing experiments with a three degrees of freedom robot arm and with a two camera vision system. Visual servoing experiments consist in positioning tasks and in tracking mobile objects. The performances are compared to other neuro-controllers like CMAC and SSOM ("Supervised Self-Organizing Maps") networks
Alché-Buc, Florence d'. "Modèles neuronaux et algorithmes constructifs pour l'apprentissage de règles de décision." Paris 11, 1993. http://www.theses.fr/1993PA112468.
Full textMaghrebi, Fatine. "Modèles de réseaux de neurones pour la commande des carrefours à feux." Paris 1, 1994. http://www.theses.fr/1994PA010082.
Full textBétrouni, Mohamed. "Réseaux de neurones pour la projection plane de données multidimensionnelles et pour le suivi de procédés industriels." Lille 1, 1999. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/1999/50376-1999-21.pdf.
Full textColnet, Brigitte. "Approches neuromimétiques pour la localisation de sources acoustiques." Nancy 1, 1995. http://www.theses.fr/1995NAN10415.
Full textNovytskyy, Dmytro. "Méthodes géométriques pour la mémoire et l'apprentissage." Toulouse 3, 2007. http://www.theses.fr/2007TOU30152.
Full textThis thesis is devoted to geometric methods in optimization, learning and neural networks. In many problems of (supervised and unsupervised) learning, pattern recognition, and clustering there is a need to take into account the internal (intrinsic) structure of the underlying space, which is not necessary Euclidean. For Riemannian manifolds we construct computational algorithms for Newton method, conjugate-gradient methods, and some non-smooth optimization methods like the r-algorithm. For this purpose we develop methods for geodesic calculation in submanifolds based on Hamilton equations and symplectic integration. Then we construct a new type of neural associative memory capable of unsupervised learning and clustering. Its learning is based on generalized averaging over Grassmann manifolds. Further extension of this memory involves implicit space transformation and kernel machines. Also we consider geometric algorithms for signal processing and adaptive filtering. Proposed methods are tested for academic examples as well as real-life problems of image recognition and signal processing. Application of proposed neural networks is demonstrated for a complete real-life project of chemical image recognition (electronic nose)
Monrocq, Christophe. "Approche probabiliste pour l'élaboration et la validation de systèmes de décision : application aux réseaux neuronaux." Paris 9, 1994. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1994PA090012.
Full textRochel, Olivier. "Une approche événementielle pour la modélisation et la simulation de réseaux de neurones impulsionnels." Nancy 1, 2004. http://www.theses.fr/2004NAN10004.
Full textAt present, there exists no generic modeling and simulation framework that addresses the study of large spiking neural networks. In the existing models, the impulses are generally associated with discontinuities in the otherwise continuous dynamics of the neurons. This raises modeling and practical implementation issues. We propose an novel approach based on the discrete-event system abstraction, grounded on the DEVS formalism, that can be used to represent a large class of spiking neurons and permits the modeling of large networks. A simulation engine has been developed on top of this formalism. It is based on an efficient event-driven algorithm and has been evaluated on sequential as well as parallel machines. We have tested our approach within a multi-disciplinary project on olfactory perception
Malek, Maria. "Un modèle hybride de mémoire pour le raisonnement à partir de cas." Université Joseph Fourier (Grenoble), 1996. http://www.theses.fr/1996GRE10186.
Full textBigot, Pascal. "Utilisation des réseaux de neurones pour la télégestion des réseaux techniques urbains." Lyon 1, 1995. http://www.theses.fr/1995LYO10036.
Full textRobitaille, Louis-Emile. "Réseaux de neurones pour l'apprentissage de la préférence en microscopie super-résolution." Master's thesis, Université Laval, 2021. http://hdl.handle.net/20.500.11794/68744.
Full textFor many years, fluorescent microscopy has been limited by diffraction. However, to study dynamic phenomena inside cells, a nanometric resolution is often necessary. To cope with this problem, an important development for fluorescent microscopy was the invention ofSTimulated-Emission-Depletion microscopy (STED) (Hell and Wichmann, 1994). If STEDachieves nanometric microscopy, it is also an extremely sophisticated technique that requires advanced knowledge across a wide range of domains, e.g. physics, chemistry and biology. With the goal of democratising the microscope, Durand et al. (2018) use the last development in artificial intelligence to automate STED parameterization with an optimisation loop. The objective aimed is to produce high-quality images while minimising photo bleaching and exposition time. The inability of measuring image quality and of choosing between compromise among objectives still forces an expert to stay behind the microscope. By automating the assessment of image quality and the selection of compromise, this master thesis intends to demonstrate the potential of neural networks for preference learning in life science.
Zaïdi, Abdelaziz. "Intégration des réseaux bayésiens et bond graphs pour la supervision des systèmes dynamiques." Thesis, Lille 1, 2012. http://www.theses.fr/2012LIL10035/document.
Full textThe supervision of complex and critical industrial processes is a very heavy task which requires effective algorithms. The literature shows a growing interest of graphical approaches because of the simplicity of establishment of the derived algorithms. The model based diagnosis is a method which becomes widespread because of the richness of graphical and structural methods allowing modeling of most complex processes. The bond graph (BG) tool, with its multidisciplinary representation, is one of the most recognized approaches in this framework. In this context, we try in present work to couple this graphical approach with another graphical one allowing incorporating statistics of components failures. All this aims to mitigate the problems: unknown failure signatures or identical signatures for several components and monitoring the system degradation. Indeed, on the basis of consulted literature, it does not appear work which evokes a supervision strategy associating a Bayesian reliability model with a BG model based fault detection and isolation (FDI) approach. Consequently, the suggested work illustrates a method to outline this objective. We propose a new methodology for the supervision of the dynamic and hybrid dynamic systems. Our contribution appears in the proposal for a strategy of risk based supervision by combining two graphical approaches: BG and Bayesian networks (BN). The resulting model for diagnosis is a hybrid BN. It is able to make a decision under uncertainties of BG model and takes account of the probabilities of false alarm and non-detection. Furthermore, integration of two graphical approaches (BG and Bayesian networks (BN) to design robust supervision system is another innovative interest. Generated residuals from BG model are coupled with the component reliability model of components leading to a hybrid BN diagnostic model. This model is then used to make a decision under uncertainties of BG model and takes into account the probabilities of false alarm and non-detection. The developed theory is applied to a thermal power station
Pujol, Hubert. "Réseau d'interconnexion haut débit pour les architectures parallèles connexionnistes." Paris 11, 1994. http://www.theses.fr/1994PA112192.
Full textEl, Aidi Chafei. "Relations structure-odeur pour des composés aromatiques : comparaison entre analyses multivariées et réseaux neuronaux." Lyon 1, 1997. http://www.theses.fr/1997LYO10213.
Full textNocera, Pascal. "Utilisation conjointe de réseaux neuronaux et de connaissances explicites pour le décodage acoustico-phonétique." Avignon, 1992. http://www.theses.fr/1992AVIG0102.
Full textRosar, Kós Lassance Carlos Eduardo. "Graphs for deep learning representations." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2020. http://www.theses.fr/2020IMTA0204.
Full textIn recent years, Deep Learning methods have achieved state of the art performance in a vast range of machine learning tasks, including image classification and multilingual automatic text translation. These architectures are trained to solve machine learning tasks in an end-to-end fashion. In order to reach top-tier performance, these architectures often require a very large number of trainable parameters. There are multiple undesirable consequences, and in order to tackle these issues, it is desired to be able to open the black boxes of deep learning architectures. Problematically, doing so is difficult due to the high dimensionality of representations and the stochasticity of the training process. In this thesis, we investigate these architectures by introducing a graph formalism based on the recent advances in Graph Signal Processing (GSP). Namely, we use graphs to represent the latent spaces of deep neural networks. We showcase that this graph formalism allows us to answer various questions including: ensuring generalization abilities, reducing the amount of arbitrary choices in the design of the learning process, improving robustness to small perturbations added to the inputs, and reducing computational complexity
Mousset, Paul. "Modèles neuronaux pour la représentation et l'appariement d'objets géotextuels." Thesis, Toulouse 3, 2020. http://www.theses.fr/2020TOU30042.
Full textStimulated by the heavy use of smartphones, the joint use of textual and spatial data in space-textual objects (e.g., tweets, Flickr photos, POI reviews) became the mainstay of many applications, such as crisis management, tourist assistance or the finding of places of interest. These tasks are fundamentally based on the representation of spatial objects and the definition of matching functions. In previous work, the problem has been addressed using linguistic models that rely on costly probability estimation of the relevance of words in spatial regions. However, these traditional methods are not very effective when dealing with social network data. These data are usually short, use unconventional or ambiguous words, and are difficult to match with other documents because of vocabulary mismatches. As a result, the proposed approaches generally lead to low recall and precision rates. In this thesis, we focus on tackling the semantic gap in the representation and matching of geotagged tweets and POIs. We propose to leverage geographic contexts and distributional semantics to resolve the semantic location prediction task. Our work consists of two main contributions: (1) improving word embeddings which can be combined to construct object representations using spatial word distributions; (2) exploiting deep neural networks to perform semantic matching between tweets and POIs. Regarding the improvement of text representations, we propose to regularize word embeddings that can be combined to construct object representations. The purpose is to reveal possible local semantic relationships between words and the multiplicity of meanings of the same word. To detect the local specificities of the different meanings, we consider two alternatives. One based on a spatial partitioning method using the k-means algorithm, and the other one based on a probabilistic partitioning using a kernel density estimation (KDE). Word embeddings are then retrofitted using a regularization function that integrates the spatial distributions to compute the local semantic relationships between words. Regarding the use of deep neural networks for the semantic location prediction task, we propose an interaction-based neural model designed for tweet-POI pair matching. Unlike existing architectures, our approach is based on joint learning of local and global interactions between tweet-POI pairs. According to the proposed model, the exact matching signals of the local word-to-word interactions are corrected by a spatial damping factor. Then, these smoothed signals are processed using matching histograms. The local interactions reveal word-pairs patterns similarity driven by spatial information. Global interactions consider the strength of the interaction between the tweet and the POI, both spatially, through a geographical distance between geotextual objects, and semantically, through a semantic proximity of their latent representation
Lorquet, Vincent. "Etude d'un codage semi-distribué adaptatif pour les réseaux multi-couches. Application au diagnostic, à la modélisation et à la commande." Paris, ENST, 1992. http://www.theses.fr/1992ENST0025.
Full textForgez, Christophe. "Méthodologie de modélisation et de commande par réseaux de neurones pour des dispositifs électrotechniques non linéaires." Lille 1, 1998. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/1998/50376-1998-309.pdf.
Full textKuhn, Daniel. "Une approche neuronale pour l'asservissement visuel d'un robot manipulateur." Mulhouse, 1997. http://www.theses.fr/1997MULH0477.
Full textBourgeois, Yoann. "Les réseaux de neurones artificiels pour mesurer les risques économiques et financiers." Paris, EHESS, 2003. http://www.theses.fr/2003EHES0118.
Full textThe objective of this thesis is to provide complete methodologies to solve prediction and classification problems in economy and finance by using Artificial Neural networks. The plan of work shows that the thesisplays a great part in establishing in several ways a statistic methodology for neural networks. We proceed in four chapters. The first chapter describes supervised and unsupervised neural network methodology to modelize quantitative or qualitative variables. In the second chapter, we are interested by the bayesian approach for supervised neural networks and the developpement of a set of misspecification statistic tests for binary choice models. In chapter three, we show that multivariate supervised neural networks enable to take into account structural changes and the neural networks methodology is able to estimate some probabilities of exchange crisis. In chapter four, we develope a complete based neural network-GARCH model to manage a stocks portfolio. We introduce some terms as conditional returns or conditional risk for a stock or a portfolio. Next, we apply bayesian Self-Organizing Map in order to estimate the univariate probability density function of the DM/USD exchange rate
Sainthillier, Jean Marie. "Application des réseaux neuronaux pour le traitement et l'analyse des images en bio-ingénierie cutanée." Besançon, 2004. http://www.theses.fr/2004BESA3001.
Full textThe objective of this work is to use videocapillaroscopy to characterise cutaneous microcirculation automatically. With this technique, it is possible to study microvascular vessels for the diagnosis and monitoring of skin pathologies. The neuronal tool is used to detect and count automatically the capillary loops which constitute the vascular network. This method was validated by comparison With manual detection. In order to modelise the spatial distribution of these loops, several methods of geometrical analysis (Delaunay triangulation and Voronoï diagram) were developed. The reliability of these modelisations was tested by simulating at random the omission or the addition of capillaries. Finally, we built a neuronal filter to quantify and score rosacea according to its redness and intensity. By processing the colour, this filter allows the fast and automated detection of images
Vasiliu, Adrian Alexandru. "Une approche CAO pour la préconception des mécanismes plans générateurs de trajectoire : REALISME." Châtenay-Malabry, Ecole centrale de Paris, 1997. https://tel.archives-ouvertes.fr/tel-00393842.
Full textGherari, Zineddine. "Stratégie de commandes neurofloues pour un système continu non linéaire." Paris 12, 1998. http://www.theses.fr/1998PA120062.
Full textMaillard, Eric. "Mise en oeuvre des réseaux neuromimétiques pour le traitement d'image sonar, étude et amélioration des capacités de généralisation." Mulhouse, 1993. http://www.theses.fr/1993MULH0272.
Full textNguyen, Gia Hung. "Modèles neuronaux pour la recherche d'information : approches dirigées par les ressources sémantiques." Thesis, Toulouse 3, 2018. http://www.theses.fr/2018TOU30233.
Full textIn this thesis, we focus on bridging the semantic gap between the documents and queries representations, hence improve the matching performance. We propose to combine relational semantics from knowledge resources and distributed semantics of the corpus inferred by neural models. Our contributions consist of two main aspects: (1) Improving distributed representations of text for IR tasks. We propose two models that integrate relational semantics into the distributed representations: a) an offline model that combines two types of pre-trained representations to obtain a hybrid representation of the document; b) an online model that jointly learns distributed representations of documents, concepts and words. To better integrate relational semantics from knowledge resources, we propose two approaches to inject these relational constraints, one based on the regularization of the objective function, the other based on instances in the training text. (2) Exploiting neural networks for semantic matching of documents}. We propose a neural model for document-query matching. Our neural model relies on: a) a representation of raw-data that models the relational semantics of text by jointly considering objects and relations expressed in a knowledge resource, and b) an end-to-end neural architecture that learns the query-document relevance by leveraging the distributional and relational semantics of documents and queries
Gatet, Laurent. "Intégration de Réseaux de Neurones pour la Télémétrie Laser." Phd thesis, Toulouse, INPT, 2007. http://oatao.univ-toulouse.fr/7595/1/gatet.pdf.
Full textDeleglise, Bérangère. "Reconstruction de voies neuro-anatomiques en culture microfluidique pour l’étude des mécanismes de dégénérescence transynaptique." Paris 6, 2013. http://www.theses.fr/2013PA066242.
Full textBehloul, Faïza. "Fusion de donnees TEP-IRM par methodes neurofloues pour l'etude de la viabilite du myocarde." Lyon, INSA, 1999. http://www.theses.fr/1999ISAL0025.
Full textPredicting which patient with alteration in contractile function will benefit from revascularization procedure after myocardial infarction is a challenging issue for clinicians. This prediction is based on the assessment of myocardial viability. Experimental studies showed that accurate viability assessment requires information about myocardial blood flow (perfusion) glucose metabolism and contractile function of the myocardium. Unfortunately, no imaging modality permits the examination of the three myocardial functions. Furthermore, integrating a growing number of parameters is tedious for clinicians and it is difficult to distinguish the different ischemic processes involved in ischemic heart disease based on visual image analysis. Thus, a multimodality data fusion system for automatic decision making is necessary. Therefore, our work was aimed to integrate perfusion, metabolism assessed by Positron Emission Tomography (PET) and Magnetic Resonance Imaging (MRI) and contractile function assessed by tagging MRI, to derive automatically accurate assessment of myocardial viability. Our fusion system is designed to process human-like expertise adapt itself and improve it performances in growing data bases via learning procedures. The quintessence of designing such an intelligent system lies in neuro-fuzzy computing, which is considered the backbone of a recent discipline called Soft Computing. The fusion system is a hierarchical modular network consisting of four Adaptive Network-based Fuzzy Inference Systems. The design of the networks and the tuning of its parameters was based on expend knowledge and unsupervised fuzzy clustering algorithms. Segmentation, visualization and registration techniques necessary for the fusion process have been developed and integrated to interactive software. This software permits accurate viability assessment and quantification that will help to confirm and enhance already existing clinical knowledge about myocardial viability. The first validation results, based on the kappa statistic measure are very encouraging
Elbayad, Maha. "Une alternative aux modèles neuronaux séquence-à-séquence pour la traduction automatique." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM012.
Full textIn recent years, deep learning has enabled impressive achievements in Machine Translation.Neural Machine Translation (NMT) relies on training deep neural networks with large number of parameters on vast amounts of parallel data to learn how to translate from one language to another.One crucial factor to the success of NMT is the design of new powerful and efficient architectures. State-of-the-art systems are encoder-decoder models that first encode a source sequence into a set of feature vectors and then decode the target sequence conditioning on the source features.In this thesis we question the encoder-decoder paradigm and advocate for an intertwined encoding of the source and target so that the two sequences interact at increasing levels of abstraction. For this purpose, we introduce Pervasive Attention, a model based on two-dimensional convolutions that jointly encode the source and target sequences with interactions that are pervasive throughout the network.To improve the efficiency of NMT systems, we explore online machine translation where the source is read incrementally and the decoder is fed partial contexts so that the model can alternate between reading and writing. We investigate deterministic agents that guide the read/write alternation through a rigid decoding path, and introduce new dynamic agents to estimate a decoding path for each sample.We also address the resource-efficiency of encoder-decoder models and posit that going deeper in a neural network is not required for all instances.We design depth-adaptive Transformer decoders that allow for anytime prediction and sample-adaptive halting mechanisms to favor low cost predictions for low complexity instances and save deeper predictions for complex scenarios
Igusti, Bagus Made Swastika Putra. "Étude et réalisation des régulateurs de réseaux neuronaux pour des convertisseurs triphasés de type GTO/IGBT." Thèse, Université du Québec à Trois-Rivières, 1999. http://depot-e.uqtr.ca/3171/1/000664922.pdf.
Full textDo, Huu Nicolas. "Apprentissage de représentations sensori-motrices pour la reconnaissance d'objet en robotique." Phd thesis, Université Paul Sabatier - Toulouse III, 2007. http://tel.archives-ouvertes.fr/tel-00283073.
Full textCougnaud, Anthony. "Optimisation de filtres de charbon actif pour la potabilisation d'eau : étude expérimentale et modélisation par réseaux de neurones." Nantes, 2005. http://www.theses.fr/2005NANT2080.
Full textThis study is devoted to modelling of the behaviour of activated carbon filters by neural networks (NN), in comparison with a knowledge model based on mathematical equations. Two kinds of NN are used : a " static " NN which considers time as an input neuron, and a " recurrent " NN which takes into account the dynamic character of the process. First, the adsorption of pesticides onto activated carbon is studied in batch reactor and the concomitant influence of solute properties (solubility, molecular weight) and porous characteristics of adsorbents (microporous volume, specific surface area) is shown. In the case of surface water, the competitive effects between natural organic matter and pesticides increase the effect of pore size distribution, especially pore size distribution between primary (d < 0. 8 nm) and secondary micropores (0. 8 < d < 2 nm). These qualitative analyses are quantified with a multiple linear regression and a static neural network which allows to explain more than 97 % of data scattering, while the linear regression performance is lower (R2 = 82 % and 53 % for a distillated water and a surface water respectively). .
Ruckebusch, Cyril. "Spectroscopie infrarouge et chimiométrie pour l'instrumentation en chimie analytique des procédés : application au suivi de l'hydrolyse d'hémoglobine bovine." Lille 1, 2000. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/2000/50376-2000-480.pdf.
Full textBellanger-Dujardin, Anne-Sophie. "Contribution à l'étude de structures neuronales pour la classification de signatures : application au diagnostic de pannes des systèmes industriels et à l'aide au diagnostic médical." Paris 12, 2003. https://athena.u-pec.fr/primo-explore/search?query=any,exact,990002111250204611&vid=upec.
Full textThe problem of diagnosis occurs in many fields, especially medical and industrial, where operator has a key role. The major difficulty bound to this problem lies on the resemblance between the signatures which allow to make a diagnosis. Furthermore, we often have an empirical knowledge of the system, and thus, an incomplete model, requiring the appeal to an expert. Our efforts were focused on techniques based on neural techniques for computer aided diagnosis. For the tasks of pattern recognition, classification and decision, the proposed techniques indeed presents a number of advantages over conventional models because of their abilities of learning and generalization. Moreover, noticing that simple neural techniques do not allow obtaining good results, we propose a neural hybrid structure. Two areas of applications have been considered: one linked to the biomedical field and the other concerning the industrial domain
Gueriot, Didier. "Utilisation des algorithmes génétiques pour des problèmes d'optimisation spécifiques : application aux réseaux de neurones et au traitement d'images sonar." Mulhouse, 1998. http://www.theses.fr/1998MULH0531.
Full textTrabelsi, Mohamed El Hadi. "Combinaison d'informations visuelles et ultrasonores pour la localisation d'un robot mobile et la saisie d'objets." Evry-Val d'Essonne, 2006. http://www.biblio.univ-evry.fr/theses/2006/Interne/2006EVRY0036.pdf.
Full textMy research bellows at the ARPH project. The aim of this project is to bring an assistance to disabled people in the various tasks of life, using a mobile robot and an arm manipulator. The first part of my thesis is devoted to the development of a localization system for the mobile robot. We use a 2D/3D matching between the 3D environment model enriched with ultrasonic information and 2D image segments. Function which transforms the 3D coordinates of the model segments to the camera coordinates is based on the Lowe linear principle. The choice of the best position is obtained by measuring distances between the two groups of segments in space. The second part of my thesis was devoted to the development of a seizure strategy for simple objects (cylinder or sphere). A camera and a sonar followed by a neural networks are installed at the robot gripper. The combination of information received from these two sensors allows the grabbing of the object. This object is centered in the visual field of the camera by image processing. The gripper approaches the object until the seizure. This method is based on several elements which take part in the development of a visual servoing strategy
Prévotet, Jean-Christophe. "Etude des systèmes électroniques pour les réseaux connexionnistes appliqués à l'instrumentation en temps-réel." Paris 6, 2002. http://www.theses.fr/2002PA066463.
Full text