Дисертації з теми "Réseau neuronal en graphes"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Réseau neuronal en graphes".
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.
Albano, Alice. "Dynamique des graphes de terrain : analyse en temps intrinsèque." Electronic Thesis or Diss., Paris 6, 2014. http://www.theses.fr/2014PA066260.
Повний текст джерелаWe are surrounded by a multitude of interaction networks from different contexts. These networks can be modeled as graphs, called complex networks. They have a community structure, i.e. groups of nodes closely related to each other and less connected with the rest of the graph. An other phenomenon studied in complex networks in many contexts is diffusion. The spread of a disease is an example of diffusion. These phenomena are dynamic and depend on an important parameter, which is often little studied: the time scale in which they are observed. According to the chosen scale, the graph dynamics can vary significantly. In this thesis, we propose to study dynamic processes using a suitable time scale. We consider a notion of relative time which we call intrinsic time, opposed to "traditional" time, which we call extrinsic time. We first study diffusion phenomena using intrinsic time, and we compare our results with an extrinsic time scale. This allows us to highlight the fact that the same phenomenon observed at two different time scales can have a very different behavior. We then analyze the relevance of the use of intrinsic time scale for detecting dynamic communities. Comparing communities obtained according extrinsic and intrinsic scales shows that the intrinsic time scale allows a more significant detection than extrinsic time scale
Albano, Alice. "Dynamique des graphes de terrain : analyse en temps intrinsèque." Thesis, Paris 6, 2014. http://www.theses.fr/2014PA066260/document.
Повний текст джерелаWe are surrounded by a multitude of interaction networks from different contexts. These networks can be modeled as graphs, called complex networks. They have a community structure, i.e. groups of nodes closely related to each other and less connected with the rest of the graph. An other phenomenon studied in complex networks in many contexts is diffusion. The spread of a disease is an example of diffusion. These phenomena are dynamic and depend on an important parameter, which is often little studied: the time scale in which they are observed. According to the chosen scale, the graph dynamics can vary significantly. In this thesis, we propose to study dynamic processes using a suitable time scale. We consider a notion of relative time which we call intrinsic time, opposed to "traditional" time, which we call extrinsic time. We first study diffusion phenomena using intrinsic time, and we compare our results with an extrinsic time scale. This allows us to highlight the fact that the same phenomenon observed at two different time scales can have a very different behavior. We then analyze the relevance of the use of intrinsic time scale for detecting dynamic communities. Comparing communities obtained according extrinsic and intrinsic scales shows that the intrinsic time scale allows a more significant detection than extrinsic time scale
Wang, Lianfa. "Improving the confidence of CFD results by deep learning." Electronic Thesis or Diss., Université Paris sciences et lettres, 2024. http://www.theses.fr/2024UPSLM008.
Повний текст джерелаComputational Fluid Dynamics (CFD) has become an indispensable tool for studying complex flow phenomena in both research and industry over the years. The accuracy of CFD simulations depends on various parameters – geometry, mesh, schemes, solvers, etc. – as well as phenomenological knowledge that only an expert CFD engineer can configure and optimize. The objective of this thesis is to propose an AI assistant to help users, whether they are experts or not, to better choose simulation options and ensure the reliability of results for a target flow phenomenon. In this context, deep learning algorithms are explored to identify the characteristics of flows computed on structured and unstructured meshes of complex geometries. Initially, convolutional neural networks (CNNs), known for their ability to extract patterns from im-ages, are used to identify flow phenomena such as vortices and thermal stratification on structured 2D meshes. Although the results obtained on structured meshes are satisfactory, CNNs can only be applied to structured meshes. To overcome this limitation, a graph-based neural network (GNN) framework is proposed. This framework uses the U-Net architecture and a hierarchy of successively refined graphs through the implementation of a multigrid method (AMG) inspired by the one used in the Code_Saturne CFD code. Subsequently, an in-depth study of kernel functions was conducted according to identification accuracy and training efficiency criteria to better filter the different phenomena on unstructured meshes. After comparing available kernel functions in the literature, a new kernel function based on the Gaussian mixture model was proposed. This function is better suited to identifying flow phenomena on unstructured meshes. The superiority of the proposed architecture and kernel function is demonstrated by several numerical experiments identifying 2D vortices and its adaptability to identifying the characteristics of a 3D flow
Aracena, Julio. "Modèles mathématiques discrets associées à des systèmes biologiques : applications aux réseaux de régulation génétique." Université Joseph Fourier (Grenoble ; 1971-2015), 2001. http://www.theses.fr/2001GRE10215.
Повний текст джерелаAracena, Julio. "Modèles mathématiques discrets associées à des systèmes biologiques : applications aux réseaux de régulation génétique." Université Joseph Fourier (Grenoble), 2001. http://www.theses.fr/2001GRE1A004.
Повний текст джерелаTiano, Donato. "Learning models on healthcare data with quality indicators." Electronic Thesis or Diss., Lyon 1, 2022. http://www.theses.fr/2022LYO10182.
Повний текст джерелаTime series are collections of data obtained through measurements over time. The purpose of this data is to provide food for thought for event extraction and to represent them in an understandable pattern for later use. The whole process of discovering and extracting patterns from the dataset is carried out with several extraction techniques, including machine learning, statistics, and clustering. This domain is then divided by the number of sources adopted to monitor a phenomenon. Univariate time series when the data source is single and multivariate time series when the data source is multiple. The time series is not a simple structure. Each observation in the series has a strong relationship with the other observations. This interrelationship is the main characteristic of time series, and any time series extraction operation has to deal with it. The solution adopted to manage the interrelationship is related to the extraction operations. The main problem with these techniques is that they do not adopt any pre-processing operation on the time series. Raw time series have many undesirable effects, such as noisy points or the huge memory space required for long series. We propose new data mining techniques based on the adoption of the most representative features of time series to obtain new models from the data. The adoption of features has a profound impact on the scalability of systems. Indeed, the extraction of a feature from the time series allows for the reduction of an entire series to a single value. Therefore, it allows for improving the management of time series, reducing the complexity of solutions in terms of time and space. FeatTS proposes a clustering method for univariate time series that extracts the most representative features of the series. FeatTS aims to adopt the features by converting them into graph networks to extract interrelationships between signals. A co-occurrence matrix merges all detected communities. The intuition is that if two time series are similar, they often belong to the same community, and the co-occurrence matrix reveals this. In Time2Feat, we create a new multivariate time series clustering. Time2Feat offers two different extractions to improve the quality of the features. The first type of extraction is called Intra-Signal Features Extraction and allows to obtain of features from each signal of the multivariate time series. Inter-Signal Features Extraction is used to obtain features by considering pairs of signals belonging to the same multivariate time series. Both methods provide interpretable features, which makes further analysis possible. The whole time series clustering process is lighter, which reduces the time needed to obtain the final cluster. Both solutions represent the state of the art in their field. In AnomalyFeat, we propose an algorithm to reveal anomalies from univariate time series. The characteristic of this algorithm is the ability to work among online time series, i.e. each value of the series is obtained in streaming. In the continuity of previous solutions, we adopt the functionality of revealing anomalies in the series. With AnomalyFeat, we unify the two most popular algorithms for anomaly detection: clustering and recurrent neural network. We seek to discover the density area of the new point obtained with clustering
Faucheux, Cyrille. "Segmentation supervisée d'images texturées par régularisation de graphes." Thesis, Tours, 2013. http://www.theses.fr/2013TOUR4050/document.
Повний текст джерелаIn this thesis, we improve a recent image segmentation algorithm based on a graph regularization process. The goal of this method is to compute an indicator function that satisfies a regularity and a fidelity criteria. Its particularity is to represent images with similarity graphs. This data structure allows relations to be established between similar pixels, leading to non-local processing of the data. In order to improve this approach, combine it with another non-local one: the texture features. Two solutions are developped, both based on Haralick features. In the first one, we propose a new fidelity term which is based on the work of Chan and Vese and is able to evaluate the homogeneity of texture features. In the second method, we propose to replace the fidelity criteria by the output of a supervised classifier. Trained to recognize several textures, the classifier is able to produce a better modelization of the problem by identifying the most relevant texture features. This method is also extended to multiclass segmentation problems. Both are applied to 2D and 3D textured images
Limnios, Stratis. "Graph Degeneracy Studies for Advanced Learning Methods on Graphs and Theoretical Results Edge degeneracy: Algorithmic and structural results Degeneracy Hierarchy Generator and Efficient Connectivity Degeneracy Algorithm A Degeneracy Framework for Graph Similarity Hcore-Init: Neural Network Initialization based on Graph Degeneracy." Thesis, Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAX038.
Повний текст джерелаExtracting Meaningful substructures from graphs has always been a key part in graph studies. In machine learning frameworks, supervised or unsupervised, as well as in theoretical graph analysis, finding dense subgraphs and specific decompositions is primordial in many social and biological applications among many others.In this thesis we aim at studying graph degeneracy, starting from a theoretical point of view, and building upon our results to find the most suited decompositions for the tasks at hand.Hence the first part of the thesis we work on structural results in graphs with bounded edge admissibility, proving that such graphs can be reconstructed by aggregating graphs with almost-bounded-edge-degree. We also provide computational complexity guarantees for the different degeneracy decompositions, i.e. if they are NP-complete or polynomial, depending on the length of the paths on which the given degeneracy is defined.In the second part we unify the degeneracy and admissibility frameworks based on degree and connectivity. Within those frameworks we pick the most expressive, on the one hand, and computationally efficient on the other hand, namely the 1-edge-connectivity degeneracy, to experiment on standard degeneracy tasks, such as finding influential spreaders.Following the previous results that proved to perform poorly we go back to using the k-core but plugging it in a supervised framework, i.e. graph kernels. Thus providing a general framework named core-kernel, we use the k-core decomposition as a preprocessing step for the kernel and apply the latter on every subgraph obtained by the decomposition for comparison. We are able to achieve state-of-the-art performance on graph classification for a small computational cost trade-off.Finally we design a novel degree degeneracy framework for hypergraphs and simultaneously on bipartite graphs as they are hypergraphs incidence graph. This decomposition is then applied directly to pretrained neural network architectures as they induce bipartite graphs and use the coreness of the neurons to re-initialize the neural network weights. This framework not only outperforms state-of-the-art initialization techniques but is also applicable to any pair of layers convolutional and linear thus being applicable however needed to any type of architecture
Lachaud, Guillaume. "Extensions and Applications of Graph Neural Networks." Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS434.
Повний текст джерелаGraphs are used everywhere to represent interactions between entities, whether physical such as atoms, molecules or people, or more abstract such as cities, friendships, ideas, etc. Amongst all the methods of machine learning that can be used, the recent advances in deep learning have made graph neural networks the de facto standard for graph representation learning. This thesis can be divided in two parts. First, we review the theoretical underpinnings of the most powerful graph neural networks. Second, we explore the challenges faced by the existing models when training on real world graph data. The powerfulness of a graph neural network is defined in terms of its expressiveness, i.e., its ability to distinguish non isomorphic graphs; or, in an equivalent manner, its ability to approximate permutation invariant and equivariant functions. We distinguish two broad families of the most powerful models. We summarise the mathematical properties as well as the advantages and disadvantages of these models in practical situations. Apart from the choice of the architecture, the quality of the graph data plays a crucial role in the ability to learn useful representations. Several challenges are faced by graph neural networks given the intrinsic nature of graph data. In contrast to typical machine learning methods that deal with tabular data, graph neural networks need to consider not only the features of the nodes but also the interconnectedness between them. Due to the connections between nodes, training neural networks on graphs can be done in two settings: in transductive learning, the model can have access to the test features in the training phase; in the inductive setting, the test data remains unseen. We study the differences in terms of performance between inductive and transductive learning for the node classification task. Additionally, the features that are fed to a model can be noisy or even missing. In this thesis we evaluate these challenges on real world datasets, and we propose a novel architecture to perform missing data imputation on graphs. Finally, while graphs can be the natural way to describe interactions, other types of data can benefit from being converted into graphs. In this thesis, we perform preliminary work on how to extract the most important parts of skin lesion images that could be used to create graphs and learn hidden relations in the data
Hafidi, Hakim. "Robust machine learning for Graphs/Networks." Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAT004.
Повний текст джерелаThis 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
Elagouni, Khaoula. "Combining neural-based approaches and linguistic knowledge for text recognition in multimedia documents." Thesis, Rennes, INSA, 2013. http://www.theses.fr/2013ISAR0013/document.
Повний текст джерелаThis thesis focuses on the recognition of textual clues in images and videos. In this context, OCR (optical character recognition) systems, able to recognize caption texts as well as natural scene texts captured anywhere in the environment have been designed. Novel approaches, robust to text variability (differentfonts, colors, sizes, etc.) and acquisition conditions (complex background, non uniform lighting, low resolution, etc.) have been proposed. In particular, two kinds of methods dedicated to text recognition are provided:- A segmentation-based approach that computes nonlinear separations between characters well adapted to the localmorphology of images;- Two segmentation-free approaches that integrate a multi-scale scanning scheme. The first one relies on a graph model, while the second one uses a particular connectionist recurrent model able to handle spatial constraints between characters.In addition to the originalities of each approach, two extra contributions of this work lie in the design of a character recognition method based on a neural classification model and the incorporation of some linguistic knowledge that enables to take into account the lexical context.The proposed OCR systems were tested and evaluated on two datasets: a caption texts video dataset and a natural scene texts dataset (namely the public database ICDAR 2003). Experiments have demonstrated the efficiency of our approaches and have permitted to compare their performances to those of state-of-the-art methods, highlighting their advantages and limits
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.
Повний текст джерелаThe 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
Boschin, Armand. "Machine learning techniques for automatic knowledge graph completion." Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAT016.
Повний текст джерелаA knowledge graph is a directed graph in which nodes are entities and edges, typed by a relation, represent known facts linking two entities. These graphs can encode a wide variety of information, but their construction and exploitation can be complex. Historically, symbolic methods have been used to extract rules about entities and relations, to correct anomalies or to predict missing facts. More recently, techniques of representation learning, or embeddings, have attempted to solve these same tasks. Initially purely algebraic or geometric, these methods have become more complex with deep neural networks and have sometimes been combined with pre-existing symbolic techniques.In this thesis, we first focus on the problem of implementation. Indeed, the diversity of libraries used makes the comparison of results obtained by different models a complex task. In this context, the Python library TorchKGE was developed to provide a unique setup for the implementation of embedding models and a highly efficient inference evaluation module. This library relies on graphic acceleration of tensor computation provided by PyTorch, is compatible with widespread optimization libraries and is available as open source.We then consider the automatic enrichment of Wikidata by typing the hyperlinks linking Wikipedia pages. A preliminary study showed that the graph of Wikipedia articles is much denser than the corresponding knowledge graph in Wikidata. A new training method involving relations and an inference method using entity types were proposed and experiments showed the relevance of the combined approach, including on a new dataset.Finally, we explore automatic entity typing as a hierarchical classification task. That led to the design of a new hierarchical loss used to train tensor-based models along with a new type of encoder. Experiments on two datasets have allowed a good understanding of the impact a prior knowledge of class taxonomy can have on a classifier but also reinforced the intuition that the hierarchy can be learned from the features if the dataset is large enough
Pasdeloup, Bastien. "Extending convolutional neural networks to irregular domains through graph inference." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2017. http://www.theses.fr/2017IMTA0048/document.
Повний текст джерелаThis manuscript sums up our work on extending convolutional neuralnetworks to irregular domains through graph inference. It consists of three main chapters, each giving the details of a part of a methodology allowing the definition of such networks to process signals evolving on graphs with unknown structures.First, graph inference from data is explored, in order to provide a graph modeling the support of the signals to classify. Second, translation operators that preserve neighborhood properties of the vertices are identified on the inferred graph. Third, these translations are used to shift a convolutional kernel on the graph in order to define a convolutional neural network that is adapted to the input data.We have illustrated our methodology on a dataset of images. While not using any particular knowledge on the signals, we have been able to infer a graph that is close to a grid. Translations on this graph resemble Euclidean translations. Therefore, this has allowed us to define an adapted convolutional neural network that is very close what one would obtain when using the information that signals are images. This network, trained on the initial data, has out performed state of the art methods by more than 13 points, while using a very simple and easily improvable architecture.The method we have introduced is a generalization of convolutional neural networks. As a matter of fact, they can be seen as aparticularization of our approach in the case where the graph is a grid. Our work thus opens the way to numerous perspectives, as it provides an efficient way to build networks that are adapted to the data
Rosar, 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.
Повний текст джерелаIn 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
Godard, Emmanuel. "Réécritures de graphes et algorithmique distribuée." Bordeaux 1, 2002. http://www.theses.fr/2002BOR12518.
Повний текст джерелаMessé, Arnaud. "Caractérisation de la relation structure-fonction dans le cerveau humain à partir de données d'IRM fonctionnelle et de diffusion : méthodes et applications cognitive et clinique." Phd thesis, Université de Nice Sophia-Antipolis, 2010. http://tel.archives-ouvertes.fr/tel-00845014.
Повний текст джерелаKhalife, Sammy. "Graphes, géométrie et représentations pour le langage et les réseaux d'entités." Thesis, Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAX055.
Повний текст джерелаThe 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
Topart, Hélène. "Etude d’une nouvelle classe de graphes : les graphes hypotriangulés." Electronic Thesis or Diss., Paris, CNAM, 2011. http://www.theses.fr/2011CNAM0776.
Повний текст джерелаIn this thesis, we define a new class of graphs : the hypochordal graphs. These graphs satisfy that for any path of length two, there exists a chord or another path of length two between its two endpoints. This class can represent robust networks. Indeed, we show that in such graphs, in the case of an edge or a vertex deletion, the distance beween any pair of nonadjacent vertices remains unchanged. Then, we study several properties for this class of graphs. Especially, after introducing a family of specific partitions, we show the relations between some of these partitions and hypochordality. Moreover, thanks to these partitions, we characterise minimum hypochordal graph, that are, among connected hypochordal graphs, those that minimise the number of edges for a given number of vertices. In a second part, we study the complexity, for hypochordal graphs, of problems that are NP-hard in the general case. We first show that the classical problems of hamiltonian cycle, colouring, maximum clique and maximum stable set remain NP-hard for this class of graphs. Then, we analyse graph modification problems : deciding the minimal number of edges to add or delete from a graph, in order to obtain an hypochordal graph. We study the complexity of these problems for sevaral classes of graphs
Xydas, Ioannis. "Aide à la surveillance de l’application d’une politique de sécurité dans un réseau par prise de connaissance d’un graphe de fonctionnement du réseau." Limoges, 2007. https://aurore.unilim.fr/theses/nxfile/default/ba3a6a50-5708-4f1a-9d00-dca7fa1469cd/blobholder:0/2007LIMO4006.pdf.
Повний текст джерелаIn this thesis we study the possibility of applying visualization and visual analytics in the context of data analysis for network security. In particular, we studied Internet web security and by using an “intelligent” visual representation of web attacks we extracted knowledge from a network operation graph. To achieve this goal we designed and developed an intelligent prototype system. This system is a surveillance aid for the security and web analyst, offering him/her a user friendly visual tool to detect anomalies in web requests by monitoring and exploring 3D graphs, to understand quickly the kind of undergoing attack by means of colours and the ability to navigate into the web request payload, of either normal or malicious traffic, for further analysis and appropriate response. The fundamental parts of such a system are Artificial Intelligence and Visualization. A hybrid expert system such as an Evolutionary Artificial Neural Network proved to be ideal for the classification of the web attacks
Pineau, Edouard. "Contributions to representation learning of multivariate time series and graphs." Electronic Thesis or Diss., Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAT037.
Повний текст джерелаMachine learning (ML) algorithms are designed to learn models that have the ability to take decisions or make predictions from data, in a large panel of tasks. In general, the learned models are statistical approximations of the true/optimal unknown decision models. The efficiency of a learning algorithm depends on an equilibrium between model richness, complexity of the data distribution and complexity of the task to solve from data. Nevertheless, for computational convenience, the statistical decision models often adopt simplifying assumptions about the data (e.g. linear separability, independence of the observed variables, etc.). However, when data distribution is complex (e.g. high-dimensional with nonlinear interactions between observed variables), the simplifying assumptions can be counterproductive. In this situation, a solution is to feed the model with an alternative representation of the data. The objective of data representation is to separate the relevant information with respect to the task to solve from the noise, in particular if the relevant information is hidden (latent), in order to help the statistical model. Until recently and the rise of modern ML, many standard representations consisted in an expert-based handcrafted preprocessing of data. Recently, a branch of ML called deep learning (DL) completely shifted the paradigm. DL uses neural networks (NNs), a family of powerful parametric functions, as learning data representation pipelines. These recent advances outperformed most of the handcrafted data in many domains.In this thesis, we are interested in learning representations of multivariate time series (MTS) and graphs. MTS and graphs are particular objects that do not directly match standard requirements of ML algorithms. They can have variable size and non-trivial alignment, such that comparing two MTS or two graphs with standard metrics is generally not relevant. Hence, particular representations are required for their analysis using ML approaches. The contributions of this thesis consist of practical and theoretical results presenting new MTS and graphs representation learning frameworks.Two MTS representation learning frameworks are dedicated to the ageing detection of mechanical systems. First, we propose a model-based MTS representation learning framework called Sequence-to-graph (Seq2Graph). Seq2Graph assumes that the data we observe has been generated by a model whose graphical representation is a causality graph. It then represents, using an appropriate neural network, the sample on this graph. From this representation, when it is appropriate, we can find interesting information about the state of the studied mechanical system. Second, we propose a generic trend detection method called Contrastive Trend Estimation (CTE). CTE learns to classify pairs of samples with respect to the monotony of the trend between them. We show that using this method, under few assumptions, we identify the true state underlying the studied mechanical system, up-to monotone scalar transform.Two graph representation learning frameworks are dedicated to the classification of graphs. First, we propose to see graphs as sequences of nodes and create a framework based on recurrent neural networks to represent and classify them. Second, we analyze a simple baseline feature for graph classification: the Laplacian spectrum. We show that this feature matches minimal requirements to classify graphs when all the meaningful information is contained in the structure of the graphs
Hérault, Laurent. "Réseaux de neurones récursifs pour l'optimisation combinatoire : application à la théorie des graphes et à la vision par ordinateur." Grenoble INPG, 1991. http://www.theses.fr/1991INPG0019.
Повний текст джерелаBekkouch, 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.
Повний текст джерелаThis 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
Mokhtari, Myriam. "Réseau neuronal aléatoire : applications à l'apprentissage et à la reconnaissance d'images." Paris 5, 1994. http://www.theses.fr/1994PA05S019.
Повний текст джерелаWauquier, Pauline. "Task driven representation learning." Thesis, Lille 3, 2017. http://www.theses.fr/2017LIL30005/document.
Повний текст джерелаMachine learning proposes numerous algorithms to solve the different tasks that can be extracted from real world prediction problems. To solve the different concerned tasks, most Machine learning algorithms somehow rely on relationships between instances. Pairwise instances relationships can be obtained by computing a distance between the vectorial representations of the instances. Considering the available vectorial representation of the data, none of the commonly used distances is ensured to be representative of the task that aims at being solved. In this work, we investigate the gain of tuning the vectorial representation of the data to the distance to more optimally solve the task. We more particularly focus on an existing graph-based algorithm for classification task. An algorithm to learn a mapping of the data in a representation space which allows an optimal graph-based classification is first introduced. By projecting the data in a representation space in which the predefined distance is representative of the task, we aim at outperforming the initial vectorial representation of the data when solving the task. A theoretical analysis of the introduced algorithm is performed to define the conditions ensuring an optimal classification. A set of empirical experiments allows us to evaluate the gain of the introduced approach and to temper the theoretical analysis
Kalainathan, Diviyan. "Generative Neural Networks to infer Causal Mechanisms : algorithms and applications." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLS516.
Повний текст джерелаCausal discovery is of utmost importance for agents who must plan, reason and decide based on observations; where mistaking correlation with causation might lead to unwanted consequences. The gold standard to discover causal relations is to perform experiments.However, experiments are in many cases expensive, unethical, or impossible to realize. In these situations, there is a need for observational causal discovery, that is, the estimation of causal relations from observations alone.Causal discovery in the observational data setting traditionally involves making significant assumptions on the data and on the underlying causal model.This thesis aims to alleviate some of the assumptions made on the causal models by exploiting the modularity and expressiveness of neural networks for causal discovery, leveraging both conditional independences and simplicity of the causal mechanisms through two algorithms.Extensive experiments on both simulated and real-world data and a throughout theoretical anaylsis prove the good performance and the soundness of the proposed approaches
Topart, Hélène. "Etude d’une nouvelle classe de graphes : les graphes hypotriangulés." Thesis, Paris, CNAM, 2011. http://www.theses.fr/2011CNAM0776/document.
Повний текст джерелаIn this thesis, we define a new class of graphs : the hypochordal graphs. These graphs satisfy that for any path of length two, there exists a chord or another path of length two between its two endpoints. This class can represent robust networks. Indeed, we show that in such graphs, in the case of an edge or a vertex deletion, the distance beween any pair of nonadjacent vertices remains unchanged. Then, we study several properties for this class of graphs. Especially, after introducing a family of specific partitions, we show the relations between some of these partitions and hypochordality. Moreover, thanks to these partitions, we characterise minimum hypochordal graph, that are, among connected hypochordal graphs, those that minimise the number of edges for a given number of vertices. In a second part, we study the complexity, for hypochordal graphs, of problems that are NP-hard in the general case. We first show that the classical problems of hamiltonian cycle, colouring, maximum clique and maximum stable set remain NP-hard for this class of graphs. Then, we analyse graph modification problems : deciding the minimal number of edges to add or delete from a graph, in order to obtain an hypochordal graph. We study the complexity of these problems for sevaral classes of graphs
Vermet, Franck. "Étude asymptotique d'un réseau neuronal: le modèle de mémoire associative de Hopfield." Phd thesis, Université Rennes 1, 1994. http://tel.archives-ouvertes.fr/tel-00598243.
Повний текст джерелаGoncalves, Pedro. "Un Modèle du réseau neuronal de l'intégrateur oculomoteur : théorie pour la dissection." Paris 6, 2012. http://www.theses.fr/2012PA066200.
Повний текст джерелаZhou, Rongyan. "Exploration of opportunities and challenges brought by Industry 4.0 to the global supply chains and the macroeconomy by integrating Artificial Intelligence and more traditional methods." Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPAST037.
Повний текст джерелаIndustry 4.0 is a significant shift and a tremendous challenge for every industrial segment, especially for the manufacturing industry that gave birth to the new industrial revolution. The research first uses literature analysis to sort out the literature, and focuses on the use of “core literature extension method” to enumerate the development direction and application status of different fields, which devotes to showing a leading role for theory and practice of industry 4.0. The research then explores the main trend of multi-tier supply in Industry 4.0 by combining machine learning and traditional methods. Next, the research investigates the relationship of industry 4.0 investment and employment to look into the inter-regional dependence of industry 4.0 so as to present a reasonable clustering based on different criteria and make suggestions and analysis of the global supply chain for enterprises and organizations. Furthermore, our analysis system takes a glance at the macroeconomy. The combination of natural language processing in machine learning to classify research topics and traditional literature review to investigate the multi-tier supply chain significantly improves the study's objectivity and lays a solid foundation for further research. Using complex networks and econometrics to analyze the global supply chain and macroeconomic issues enriches the research methodology at the macro and policy level. This research provides analysis and references to researchers, decision-makers, and companies for their strategic decision-making
De, Joydeep. "Les signaux quotidiens et saisonniers modulent la configuration du réseau neuronal d'horloge circadienne." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLS256.
Повний текст джерелаThe ubiquity of circadian clocks across a vast range of taxa signifies the adaptive value of knowing the time of the day. These clocks enable organisms to synchronize their daily biological processes to changing external and internal environments. In my PhD project, I used Drosophila as a model system to test hypotheses regarding the neural basis of the seasonal adaptation of the clock-driven daily activity pattern. In Drosophila, the brain clock regulating bimodal locomotor activity functions as a multi-oscillator network. Two distinct sets of neurons control morning and evening bouts of daily locomotor activity. Neurons contributing to the evening activity (E oscillators; 6 LNds, 1 sLNv and around 12 to 15 DN1ps in each hemisphere) are numerous and quite diverse within themselves in terms of their anatomical loci, projection patterns, neurochemistry, and photoreceptive modalities. My work indicates that the different E oscillators also possess distinct functional loci in the clock neuronal network. I show that only 2 pairs of E oscillators (ITP+ CRY+) out of around 150 clock neurons are sufficient for the evening anticipatory activity. Genetic dissection of various evening oscillator subsets further indicates that not only these two pairs of neurons are sufficient for the evening activity, but also, they are functionally superior to other evening oscillators in their contribution to the evening activity. Hence, an operational hierarchy exists among the evening oscillators in which the ITP+ CRY+ (henceforth, ITP E) oscillator neurons inhabit the highest rung. I further show that this hierarchy is rather flexible, and the partners of this hierarchical relationship switch roles depending on neuropeptidergic inputs (namely, PDF). Studying behavior and calcium responses in diverse evening neurons suggest that PDF and seasonal cues act on a functional framework of E neurons in which some build evening activity by promotion of activity in the later parts of the day and while others, by inhibiting activity in the earlier afternoon. Alongside PDF, seasonal cues such as day-length, light intensity and temperature, determine the functional weightage among evening oscillators. Specific seasonal cues recruit different oscillators to carry out the same function under different seasons. ITP E oscillators are recruited mostly by winter-like conditions whereas non- ITP E oscillators contribute more under summer-like conditions. This biased recruitment of oscillators partly occurs via modulation of the PDF levels by seasonal cues. Even though there are numerous E oscillators in the brain circadian circuit, their functional relevance is defined by external (seasonal cues) and internal (neuropeptides) environments through conditional oscillator recruitment. In summary, my PhD study attempts to provide a plausible explanation of how seasonal adaptation of the circadian clock and the behaviours that it times, is achieved at the neural level. My results support the idea that environmentally gated recruitment of oscillators facilitates seasonal adjustment of the daily activity pattern sculpted by the multi-oscillator circadian clock.LNd: dorsal-lateral neuronssLNv: small ventral-lateral neuronsDN1p: dorsal neurons 1 (posterior)ITP: Ion Transport PeptideCRY: CryptochromePDF: Pigment Dispersing Factor
Boulet, Romain. "Comparaison de graphes, applications à l'étude d'un réseau de sociabilité paysan au Moyen Age." Toulouse 2, 2008. http://www.theses.fr/2008TOU20078.
Повний текст джерелаThe aim of this thesis is to compare graphs with algebraic tools (especially eigenelements of some graph matrices). A first aspect of this graph comparison is the study of a medieval social network. The eigenelements of the Laplacian matrix enable us to highlight some communities; by coupling this result with statistical methods it is possible to obtain a simplified representation of the network. The comparison of two medieval networks (for instance before and after the Hundred Years' war) can then be done by comparing the two simplified representations. Comparing two graphs by knowing only their spectra (for a given matrix, adjacency or Laplacian for example) raises the question of whether two graphs with the same spectrum are isomorphic. In other words: "Which are the graphs determined by their spectrum ?". At the moment, only few graphs have been proved to answer this question and finding new families of graphs determined by their spectrum will provide new elements of reply. In this thesis we expose a new way to count the closed walks on a graph which is relevant to show the non-cospectrality (for the adjacency matrix) of two given graphs. Then new classes of graphs determined by their spectrum are shown
Wang, Xiaomin. "Décider du type de distribution de degré d'un graphe (réseau) à partir des mesures traceroute-like." Paris 6, 2011. http://www.theses.fr/2011PA066608.
Повний текст джерелаChavy, Cyril. "Codeur neuronal prédictif : application au codage de phonèmes." Paris 6, 2004. http://www.theses.fr/2004PA066526.
Повний текст джерелаAndriamanga, Vahiniaina Herinjiva. "Exploration de l'évolution du réseau métabolique chez les champignons." Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPASL150.
Повний текст джерелаMetabolism is the set of biochemical reactions that occur within an organism. The sequence of these reactions forms metabolic pathways, and their interconnections constitute the organism's complete metabolic network. Reactions within the metabolic network are mostly catalyzed by enzymes, which are classified based on the specific reaction they catalyze. This metabolic network determines the organism's metabolic capacities, including its ability to use chemical compounds found in the environment and to synthesize new products. These networks evolve, giving rise to new pathways capable of producing new products or utilizing new substrates. To unravel the evolution dynamics of the metabolic network, we investigated the evolution of 910 enzyme activities (identified by EC-number) in 174 fungal species. Fungi serve as ideal models for this study due to their diverse metabolic profiles. They catabolize a wide variety of substrates, including lignin and cellulose, which are the most abundant biopolymers on earth. Moreover, fungi synthesize a variety of molecules, such as antibiotics and toxins. They also have successfully colonized every corner of the earth. The analysis of the conservation of the 910 enzyme activities across the studied species exhibited 454 enzyme activities being universally present in all the species, while the remaining 456 were associated with particular clades or specific species. By grouping enzyme activities according to their phylogenetic profiles' similarity, we can identify sets of enzyme activities specific to particular clades or species. Through a phylostratigraphy approach, we reconstructed the evolutionary history, encompassing both the losses and acquisitions of enzyme activities related to specific clades or species. Our study revealed that 860 of these enzyme activities were already present in fungal ancestors but half of them were subsequently lost during evolution, while 8 newly emerged as fungal-specific enzyme activities. The evolutionary origin of the remaining 42 enzyme activities could not be determined. We subsequently mapped the evolutionary information onto the metabolic network. The core of this metabolic network is mainly composed of primary metabolic pathways, while secondary metabolic pathways predominantly occupy the periphery. Using graph theory tools , we assess the localization of enzyme activities within the metabolic network. Lineage-specific enzyme activities tend to occupy the network's periphery, demonstrating lower connectivity compared to common enzyme activities. Often, these lineage-specific activities serve as alternatives to the common ones. Furthermore, when we group enzyme activities based on the similarity of their phylogenetic profiles, we observe that those with similar profiles tend to cluster together within the network. Our observations suggest that the loss of network-disrupting enzyme activity is tolerated for two reasons: either the affected portion of the subnetwork becomes dispensable, considering it as an accessory, or there exists an alternative enzyme activity to bridge the two sections. This study underscore the significant role of enzyme loss in driving fungal metabolic network evolution, revealing a noteworthy constraint on the emergence of specific enzyme activities. Enzyme activity losses played a pivotal role in delineating specific taxonomic groups during the course of evolution. Importantly, the metabolic network constrains the evolution of enzyme activities, with certain network positions being prone to losses
Aïder, Méziane. "Réseaux d'interconnexion bipartis : colorations généralisées dans les graphes." Phd thesis, Grenoble 1, 1987. http://tel.archives-ouvertes.fr/tel-00325779.
Повний текст джерелаPekergin, Mehmet Ferhan. "Optimisation combinatoire par le calcul neuronal et parallelisme optimal." Paris 5, 1992. http://www.theses.fr/1992PA05S017.
Повний текст джерелаSaive, Anne-Lise. "Les odeurs, une passerelle vers les souvenirs : caractérisation des processus cognitifs et des fondements neuronaux de la mémoire épisodique olfactive." Thesis, Lyon 1, 2015. http://www.theses.fr/2015LYO10078/document.
Повний текст джерелаEpisodic memory is the memory that permits the conscious re-experience of specific personal events and associated with a specific context. This doctoral research aims at investigating the cognitive processes and the neural bases of episodic retrieval in humans. Odor-evoked memories are known to be more detailed and more emotional than memories triggered by other sensorial cues. These specificities explain why we studied odor-evoked memories. First, a novel behavioral task has been designed to study in a controlled way the memory of complex episodes comprising unfamiliar odors (What), localized spatially (Where), within a visual context (Which context). From this approach, we suggest that when the binding between the episodes’ dimensions is strong, the odor perception evokes the whole episodic memory. The episodic retrieval is mainly based on recollection processes, the feeling of knowing being insufficient to induce complete memory recovery. Moreover, emotion carried by odors, whatever its valence, promote accurate episodic retrieval. Functionally, episodic memory is underpinned by a distributed network, constituted of regions typically found in laboratory and autobiographical memory approaches. Accurate memories are associated with a specific neural network, from odor perception to memory re-experience. Modularity analyses show that neural interactions within this network also depend on memory accuracy. Altogether, results of this research suggest that episodic retrieval is a dynamic and complex process, triggered by odors perception, closely linked to other memory systems such as perceptual and semantic memories
Cabirol-Pol, Marie-Jeanne. "Caractérisation morphofonctionnelle d'un réseau neuronal simple : implications de la géométrie des neurones et de la ségrégation des synapses intra-réseau et modulatrices." Bordeaux 1, 1998. http://www.theses.fr/1998BOR10561.
Повний текст джерелаBoulnois, Philippe. "Contribution à l'étude de différentes architectures de réseaux de neurones artificiels réalisant une transcription graphèmes-phonèmes pour le français." Compiègne, 1994. http://www.theses.fr/1994COMPD675.
Повний текст джерелаRuiz, Pinales José. "Reconnaissance hors-ligne de l'écriture cursive par l'utilisation de modèles perceptifs et neuronaux." Paris, ENST, 2001. http://www.theses.fr/2001ENST0028.
Повний текст джерелаChen, Dexiong. "Modélisation de données structurées avec des machines profondes à noyaux et des applications en biologie computationnelle." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM070.
Повний текст джерелаDeveloping efficient algorithms to learn appropriate representations of structured data, including sequences or graphs, is a major and central challenge in machine learning. To this end, deep learning has become popular in structured data modeling. Deep neural networks have drawn particular attention in various scientific fields such as computer vision, natural language understanding or biology. For instance, they provide computational tools for biologists to possibly understand and uncover biological properties or relationships among macromolecules within living organisms. However, most of the success of deep learning methods in these fields essentially relies on the guidance of empirical insights as well as huge amounts of annotated data. Exploiting more data-efficient models is necessary as labeled data is often scarce.Another line of research is kernel methods, which provide a systematic and principled approach for learning non-linear models from data of arbitrary structure. In addition to their simplicity, they exhibit a natural way to control regularization and thus to avoid overfitting.However, the data representations provided by traditional kernel methods are only defined by simply designed hand-crafted features, which makes them perform worse than neural networks when enough labeled data are available. More complex kernels inspired by prior knowledge used in neural networks have thus been developed to build richer representations and thus bridge this gap. Yet, they are less scalable. By contrast, neural networks are able to learn a compact representation for a specific learning task, which allows them to retain the expressivity of the representation while scaling to large sample size.Incorporating complementary views of kernel methods and deep neural networks to build new frameworks is therefore useful to benefit from both worlds.In this thesis, we build a general kernel-based framework for modeling structured data by leveraging prior knowledge from classical kernel methods and deep networks. Our framework provides efficient algorithmic tools for learning representations without annotations as well as for learning more compact representations in a task-driven way. Our framework can be used to efficiently model sequences and graphs with simple interpretation of predictions. It also offers new insights about designing more expressive kernels and neural networks for sequences and graphs
Martineau, Maxime. "Deep learning onto graph space : application to image-based insect recognition." Thesis, Tours, 2019. http://www.theses.fr/2019TOUR4024.
Повний текст джерелаThe goal of this thesis is to investigate insect recognition as an image-based pattern recognition problem. Although this problem has been extensively studied along the previous three decades, an element is to the best of our knowledge still to be experimented as of 2017: deep approaches. Therefore, a contribution is about determining to what extent deep convolutional neural networks (CNNs) can be applied to image-based insect recognition. Graph-based representations and methods have also been tested. Two attempts are presented: The former consists in designing a graph-perceptron classifier and the latter graph-based work in this thesis is on defining convolution on graphs to build graph convolutional neural networks. The last chapter of the thesis deals with applying most of the aforementioned methods to insect image recognition problems. Two datasets are proposed. The first one consists of lab-based images with constant background. The second one is generated by taking a ImageNet subset. This set is composed of field-based images. CNNs with transfer learning are the most successful method applied on these datasets
Sourty, Raphael. "Apprentissage de représentation de graphes de connaissances et enrichissement de modèles de langue pré-entraînés par les graphes de connaissances : approches basées sur les modèles de distillation." Electronic Thesis or Diss., Toulouse 3, 2023. http://www.theses.fr/2023TOU30337.
Повний текст джерелаNatural language processing (NLP) is a rapidly growing field focusing on developing algorithms and systems to understand and manipulate natural language data. The ability to effectively process and analyze natural language data has become increasingly important in recent years as the volume of textual data generated by individuals, organizations, and society as a whole continues to grow significantly. One of the main challenges in NLP is the ability to represent and process knowledge about the world. Knowledge graphs are structures that encode information about entities and the relationships between them, they are a powerful tool that allows to represent knowledge in a structured and formalized way, and provide a holistic understanding of the underlying concepts and their relationships. The ability to learn knowledge graph representations has the potential to transform NLP and other domains that rely on large amounts of structured data. The work conducted in this thesis aims to explore the concept of knowledge distillation and, more specifically, mutual learning for learning distinct and complementary space representations. Our first contribution is proposing a new framework for learning entities and relations on multiple knowledge bases called KD-MKB. The key objective of multi-graph representation learning is to empower the entity and relation models with different graph contexts that potentially bridge distinct semantic contexts. Our approach is based on the theoretical framework of knowledge distillation and mutual learning. It allows for efficient knowledge transfer between KBs while preserving the relational structure of each knowledge graph. We formalize entity and relation inference between KBs as a distillation loss over posterior probability distributions on aligned knowledge. Grounded on this finding, we propose and formalize a cooperative distillation framework where a set of KB models are jointly learned by using hard labels from their own context and soft labels provided by peers. Our second contribution is a method for incorporating rich entity information from knowledge bases into pre-trained language models (PLM). We propose an original cooperative knowledge distillation framework to align the masked language modeling pre-training task of language models and the link prediction objective of KB embedding models. By leveraging the information encoded in knowledge bases, our proposed approach provides a new direction to improve the ability of PLM-based slot-filling systems to handle entities
Constantin, Pierre-Louis. "La reconnaissance de caractères manuscrits par réseau neuronal à fonctions radiales de base munies d'états." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1997. http://www.collectionscanada.ca/obj/s4/f2/dsk2/tape16/PQDD_0012/MQ35726.pdf.
Повний текст джерелаRathelot, Jean-Alban. "Le réseau neuronal du noyau rouge magnocellulaire : exposé bibliographique et données expérimentales chez le chat." Aix-Marseille 1, 1997. http://www.theses.fr/1997AIX11042.
Повний текст джерелаPousse, Romain. "Caractérisation et modélisation du réseau viaire." Thesis, Université de Paris (2019-....), 2020. http://theses.md.univ-paris-diderot.fr/Pousse_Romain_va2.pdf.
Повний текст джерелаThe city is a system composed of multiple structures, activities, spaces or networks in constant evolution. In view of its complexity, city as a whole is an hard study object. On the contrary, taking an interest in one of its components has been at the origin of many scientific studies from all horizons and all fields. In this work, we keep the same approach and we are interested of the road network and more particulary the space trace. We make hypothesis this network is a sensible indicator of the urban form whose we research to understand the logic development. Therefore, an graph representation of this network and an ways reconstruction (continuity between segments) have permitted the development of analysis tools by means of graphs theory indicators or statistical indicators. For this last category, we observe a log-normal distribution for the ways length in many cities (London, Paris, San Francisco). Using artificials models, our goal is to understand the development of this distribution depending to city data and understanding of this graph. We first research to better characterize the observed distributions and then to develop several processes depend characteristics established on this graph in order to find this statistic. We based in particular on the principles of ways creation on the division of parcels related to their sizes or their network position. We note that strong influence of topologique distance in the choice of parcels cuts to form an log-normal distirbution
Jule, Alan. "Etude des codes en graphes pour le stockage de données." Thesis, Cergy-Pontoise, 2014. http://www.theses.fr/2014CERG0739.
Повний текст джерелаFor two decades, the numerical revolution has been amplified. The spread of digital solutions associated with the improvement of the quality of these products tends to create a growth of the amount of data stored. The cost per Byte reveals that the evolution of hardware storage solutions cannot follow this expansion. Therefore, data storage solutions need deep improvement. This is feasible by increasing the storage network size and by reducing data duplication in the data center. In this thesis, we introduce a new algorithm that combines sparse graph code construction and node allocation. This algorithm may achieve the highest performance of MDS codes in terms of the ratio R between the number of parity disks and the number of failures that can be simultaneously reconstructed. In addition, encoding and decoding with sparse graph codes helps lower the complexity. By this algorithm, we allow to generalize coding in the data center, in order to reduce the amount of copies of original data. We also study Spatially-Coupled LDPC (SC-LDPC) codes which are known to have optimal asymptotic performance over the binary erasure channel, to anticipate the behavior of these codes decoding for distributed storage applications. It is usually necessary to compromise between different parameters for a distributed storage system. To complete the state of the art, we include two theoretical studies. The first study deals with the computation complexity of data update and we determine whether linear code used for data storage are update efficient or not. In the second study, we examine the impact on the network load when the code parameters are changed. This can be done when the file status changes (from a hot status to a cold status for example) or when the size of the network is modified by adding disks. All these studies, combined with the new algorithm for sparse graph codes, could lead to the construction of new flexible and dynamical networks with low encoding and decoding complexities
Parey, Christine. "Logique majoritaire trivalente et réseaux neuronaux : application à l'analyse de fiabilité." Paris 11, 1988. http://www.theses.fr/1988PA112201.
Повний текст джерелаOsman, Ousama. "Méthodes de diagnostic en ligne, embarqué et distribué dans les réseaux filaires complexes." Thesis, Université Clermont Auvergne (2017-2020), 2020. http://www.theses.fr/2020CLFAC038.
Повний текст джерелаThe research conducted in this thesis focuses on the diagnosis of complex wired networks using distributed reflectometry. It aims to develop new distributed diagnostic techniques for complex networks that allow data fusion as well as communication between reflectometers to detect, locate and characterize electrical faults (soft and hard faults). This collaboration between reflectometers solves the problem of fault location ambiguity and improves the quality of diagnosis. The first contribution is the development of a graph theory-based method for combining data between distributed reflectometers, thus facilitating the location of the fault. Then, the amplitude of the reflected signal is used to identify the type of fault and estimate its impedance. The latter is based on the regeneration of the signal by compensating for the degradation suffered by the diagnosis signal during its propagation through the network. The second contribution enables data fusion between distributed reflectometers in complex networks affected by multiple faults. To achieve this objective, two methods have been proposed and developed: the first is based on genetic algorithms (GA) and the second is based on neural networks (RN). These tools combined with distributed reflectometryallow automatic detection, location, and characterization of several faults in different types and topologies of wired networks. The third contribution proposes the use of information-carrying diagnosis signal to integrate communication between distributed reflectometers. It properly uses the phases of the MCTDR multi-carrier signal to transmit data. This communication ensures the exchange of useful information (such as fault location and amplitude) between reflectometers on the state of the cables, thus enabling data fusion and unambiguous fault location. Interference problems between the reflectometers are also addressed when they simultaneously inject their test signals into the network. These studies illustrate the efficiency and applicability of the proposed methods. They also demonstrate their potential to improve the performance of the current wired diagnosis systems to meet the need and the problem of detecting and locating faults that manufacturers and users face today in electrical systems to improve their operational safety