Dissertations / Theses on the topic 'Apprentissage de représentations sur graphes'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 48 dissertations / theses for your research on the topic 'Apprentissage de représentations sur graphes.'
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.
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
Cuissart, Bertrand. "Plus grande structure commune à deux graphes : méthode de calcul et intérêt dans un contexte SAR." Caen, 2004. http://www.theses.fr/2004CAEN2043.
Full textCelikkanat, Abdulkadir. "Graph Representation Learning with Random Walk Diffusions." Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG030.
Full textGraph Representation Learning aims to embed nodes in a low-dimensional space. In this thesis, we tackle various challenging problems arising in the field. Firstly, we study how to leverage the inherent local community structure of graphs while learning node representations. We learn enhanced community-aware representations by combining the latent information with the embeddings. Moreover, we concentrate on the expressive- ness of node representations. We emphasize exponential family distributions to capture rich interaction patterns. We propose a model that combines random walks with kernelized matrix factorization. In the last part of the thesis, we study models balancing the trade-off between efficiency and accuracy. We propose a scalable embedding model which computes binary node representations
Vialatte, Jean-Charles. "Convolution et apprentissage profond sur graphes." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2018. http://www.theses.fr/2018IMTA0118/document.
Full textConvolutional neural networks have proven to be the deep learning model that performs best on regularly structured datasets like images or sounds. However, they cannot be applied on datasets with an irregular structure (e.g. sensor networks, citation networks, MRIs). In this thesis, we develop an algebraic theory of convolutions on irregular domains. We construct a family of convolutions that are based on group actions (or, more generally, groupoid actions) that acts on the vertex domain and that have properties that depend on the edges. With the help of these convolutions, we propose extensions of convolutional neural netowrks to graph domains. Our researches lead us to propose a generic formulation of the propagation between layers, that we call the neural contraction. From this formulation, we derive many novel neural network models that can be applied on irregular domains. Through benchmarks and experiments, we show that they attain state-of-the-art performances, and beat them in some cases
Amate, Laure. "Apprentissage de modèles de formes parcimonieux basés sur des représentations splines." Phd thesis, Université de Nice Sophia-Antipolis, 2009. http://tel.archives-ouvertes.fr/tel-00456612.
Full textAmate, Laure. "Apprentissage de modèles de formes parcimonieux basés sur les représentations splines." Nice, 2009. http://www.theses.fr/2009NICE4117.
Full textIn many contexts it is important to be able to find compact representations of the collective morphological properties of a set of objects. This is the case of autonomous robotic platforms operating in natural environments that must use the perceptual properties of the objects present in their workspace to execute their mission. This thesis is a contribution to the definition of formalisms and methods for automatic identification of such models. The shapes we want to characterize are closed curves corresponding to contours of objects detected in the scene. We begin with the formal definition of the notion of shape as classes of equivalence with respect to groups of basic geometric operators, introducing two distinct approaches that have been used in the literature: discrete and continuous. The discrete theory, admitting the existence of a finite number of recognizable landmarks, provides in an obvious manner a compact representation but is sensible to their selection. The continuous theory of shapes provides a more fundamental approach, but leads to shape spaces of infinite dimension, lacking the parsimony of the discrete representation. We thus combine in our work the advantages of both approaches representing shapes of curves with splines: piece-wise continuous polynomials defined by sets of knots and control points. We first study the problem of fitting free-knots splines of varying complexity to a single observed curve. The trade-o_ between the parsimony of the representation and its fidelity to the observations is a well known characteristic of model identification using nested families of increasing dimension. After presenting an overview of methods previously proposed in the literature, we single out a two-step approach which is formally sound and matches our specific requirements. It splits the identification, simulating a reversible jump Markov chain to select the complexity of the model followed by a simulated annealing algorithm to estimate its parameters. We investigate the link between Kendall's shape space and spline representations when we take the spline control points as landmarks. We consider now the more complex problem of modeling a set of objects with similar morphological characteristics. We equate the problem to finding the statistical distribution of the parameters of the spline representation, modeling the knots and control points as unobserved variables. The identified distribution is the maximizer of a marginal likelihood criterion, and we propose a new Expectation-Maximization algorithm to optimize it. Because we may want to treat a large number of curves observed sequentially, we adapt an iterative (on-line) version of the EM algorithm recently proposed in the literature. For the choice of statistical distributions that we consider, both the expectation and the maximization steps must resort to numerical approximations, leading to a stochastic/on-line variant of the EM algorithm that, as far as we know, is implemented here for the first time
Caron, Stéphane. "Détection d'anomalies basée sur les représentations latentes d'un autoencodeur variationnel." Master's thesis, Université Laval, 2021. http://hdl.handle.net/20.500.11794/69185.
Full textIn this master's thesis, we propose a methodology that aims to detect anomalies among complex data, such as images. In order to do that, we use a specific type of neural network called the varitionnal autoencoder (VAE). This non-supervised deep learning approach allows us to obtain a simple representation of our data on which we then use the Kullback-Leibler distance to discriminate between anomalies and "normal" observations. To determine if an image should be considered "abnormal", our approach is based on a proportion of observations to be filtered, which is easier and more intuitive to establish than applying a threshold based on the value of a distance metric. By using our methodology on real complex images, we can obtain superior anomaly detection performances in terms of area under the ROC curve (AUC),precision and recall compared to other non-supervised methods. Moreover, we demonstrate that the simplicity of our filtration level allows us to easily adapt the method to datasets having different levels of anomaly contamination.
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
Brissac, Olivier. "Contributions à l'étude des mécanismes d'apprentissage opérant sur des descriptions à base de graphes." La Réunion, 1996. http://elgebar.univ-reunion.fr/login?url=http://thesesenligne.univ.run/96_S003_Brissac.pdf.
Full textDos, Santos Ludovic. "Representation learning for relational data." Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066480/document.
Full textThe increasing use of social and sensor networks generates a large quantity of data that can be represented as complex graphs. There are many tasks from information analysis, to prediction and retrieval one can imagine on those data where relation between graph nodes should be informative. In this thesis, we proposed different models for three different tasks: - Graph node classification - Relational time series forecasting - Collaborative filtering. All the proposed models use the representation learning framework in its deterministic or Gaussian variant. First, we proposed two algorithms for the heterogeneous graph labeling task, one using deterministic representations and the other one Gaussian representations. Contrary to other state of the art models, our solution is able to learn edge weights when learning simultaneously the representations and the classifiers. Second, we proposed an algorithm for relational time series forecasting where the observations are not only correlated inside each series, but also across the different series. We use Gaussian representations in this contribution. This was an opportunity to see in which way using Gaussian representations instead of deterministic ones was profitable. At last, we apply the Gaussian representation learning approach to the collaborative filtering task. This is a preliminary work to see if the properties of Gaussian representations found on the two previous tasks were also verified for the ranking one. The goal of this work was to then generalize the approach to more relational data and not only bipartite graphs between users and items
Dos, Santos Ludovic. "Representation learning for relational data." Electronic Thesis or Diss., Paris 6, 2017. http://www.theses.fr/2017PA066480.
Full textThe increasing use of social and sensor networks generates a large quantity of data that can be represented as complex graphs. There are many tasks from information analysis, to prediction and retrieval one can imagine on those data where relation between graph nodes should be informative. In this thesis, we proposed different models for three different tasks: - Graph node classification - Relational time series forecasting - Collaborative filtering. All the proposed models use the representation learning framework in its deterministic or Gaussian variant. First, we proposed two algorithms for the heterogeneous graph labeling task, one using deterministic representations and the other one Gaussian representations. Contrary to other state of the art models, our solution is able to learn edge weights when learning simultaneously the representations and the classifiers. Second, we proposed an algorithm for relational time series forecasting where the observations are not only correlated inside each series, but also across the different series. We use Gaussian representations in this contribution. This was an opportunity to see in which way using Gaussian representations instead of deterministic ones was profitable. At last, we apply the Gaussian representation learning approach to the collaborative filtering task. This is a preliminary work to see if the properties of Gaussian representations found on the two previous tasks were also verified for the ranking one. The goal of this work was to then generalize the approach to more relational data and not only bipartite graphs between users and items
Palesi, Frédéric. "Dynamique sur les espaces de représentations de surfaces non-orientables." Phd thesis, Université Joseph Fourier (Grenoble), 2009. http://tel.archives-ouvertes.fr/tel-00443930.
Full textPalesi, Frédéric. "Dynamique sur les espaces de représentations de surfaces non-orientables." Phd thesis, Grenoble 1, 2009. http://www.theses.fr/2009GRE10317.
Full textWe consider the space of representations Hom(Pi,G) of a surface group Pi into a Lie group G, and the moduli space X(Pi,G) of G-conjugacy classes of such representations. These spaces admit a natural action of the mapping class group of the underlying surface S, and this actions displays very rich dynamics depending on the choice of the Lie group G, and on the connected component of the space that we consider. In this thesis, we focus on the case when S is a non-orientable surface. In the rst part, we study the dynamical properties of the mapping class group actions on the moduli space X(Pi,SU(2)) and prove that this action is ergodic when the Euler characteristic of the surface is less than -1 with respect to a natural measure on the space. In the second part, we show that the representation space Hom (Pi , PSL(2,R)) has two connected components indexed by a Stiefel-Whitney class
Sokol, Marina. "Méthodes d'apprentissage semi-supervisé basé sur les graphes et détection rapide des nœuds centraux." Phd thesis, Université Nice Sophia Antipolis, 2014. http://tel.archives-ouvertes.fr/tel-00998394.
Full textSokol, Marina. "Méthodes d’apprentissage semi-supervisé basé sur les graphes et détection rapide des nœuds centraux." Thesis, Nice, 2014. http://www.theses.fr/2014NICE4018/document.
Full textSemi-supervised learning methods constitute a category of machine learning methods which use labelled points together with unlabeled data to tune the classifier. The main idea of the semi-supervised methods is based on an assumption that the classification function should change smoothly over a similarity graph. In the first part of the thesis, we propose a generalized optimization approach for the graph-based semi-supervised learning which implies as particular cases the Standard Laplacian, Normalized Laplacian and PageRank based methods. Using random walk theory, we provide insights about the differences among the graph-based semi-supervised learning methods and give recommendations for the choice of the kernel parameters and labelled points. We have illustrated all theoretical results with the help of synthetic and real data. As one example of real data we consider classification of content and users in P2P systems. This application demonstrates that the proposed family of methods scales very well with the volume of data. The second part of the thesis is devoted to quick detection of network central nodes. The algorithms developed in the second part of the thesis can be applied for the selections of quality labelled data but also have other applications in information retrieval. Specifically, we propose random walk based algorithms for quick detection of large degree nodes and nodes with large values of Personalized PageRank. Finally, in the end of the thesis we suggest new centrality measure, which generalizes both the current flow betweenness centrality and PageRank. This new measure is particularly well suited for detection of network vulnerability
Aguerre, Sandrine. "Centration sur l'apprentissage d'une langue étrangère, le français : grammaires et représentations métalinguistiques." Phd thesis, Université Michel de Montaigne - Bordeaux III, 2010. http://tel.archives-ouvertes.fr/tel-00628351.
Full textGaüzère, Benoît. "Application des méthodes à noyaux sur graphes pour la prédiction des propriétés des molécules." Caen, 2013. http://www.theses.fr/2013CAEN2043.
Full textThis work deals with the application of graph kernel methods to the prediction of molecular properties. In this document, we first present a state of the art of graph kernels used in chemoinformatics and particurlarly those which are based on bags of patterns. Within this framework, we introduce the treelet kernel based on a set of trees which allows to encode most of the structural information encoded in molecular graphs. We also propose a combination of this kernel with multiple kernel learning methods in order to extract a subset of relevant patterns. This kernel is then extended by including cyclic information using two molecular representations defined by the relevant cycle graph and the relevant cycle hypergraph. Relevant cycle graph allows to encode the cyclic system of a molecule
Sevi, Harry. "Analyse harmonique sur graphes dirigés et applications : de l'analyse de Fourier aux ondelettes." Thesis, Lyon, 2018. http://www.theses.fr/2018LYSEN068/document.
Full textThe research conducted in this thesis aims to develop a harmonic analysis for functions defined on the vertices of an oriented graph. In the era of data deluge, much data is in the form of graphs and data on this graph. In order to analyze and exploit this graph data, we need to develop mathematical and numerically efficient methods. This development has led to the emergence of a new theoretical framework called signal processing on graphs, which aims to extend the fundamental concepts of conventional signal processing to graphs. Inspired by the multi-scale aspect of graphs and graph data, many multi-scale constructions have been proposed. However, they apply only to the non-directed framework. The extension of a harmonic analysis on an oriented graph, although natural, is complex. We, therefore, propose a harmonic analysis using the random walk operator as the starting point for our framework. First, we propose Fourier-type bases formed by the eigenvectors of the random walk operator. From these Fourier bases, we determine a frequency notion by analyzing the variation of its eigenvectors. The determination of a frequency analysis from the basis of the vectors of the random walk operator leads us to multi-scale constructions on oriented graphs. More specifically, we propose a wavelet frame construction as well as a decimated wavelet construction on directed graphs. We illustrate our harmonic analysis with various examples to show its efficiency and relevance
Al-Hammouri, Samer. "Enquête sur les représentations de la langue française et de son apprentissage chez les étudiants jordaniens." Thesis, Paris 3, 2009. http://www.theses.fr/2009PA030093.
Full textOur research is about the study of the representations of the French language and its learning by Jordanian students. We tried to discover the images concerning France and French people from a sample of Jordanian students. The purpose of this paper is to explore more the question of the representations of the Jordanian learners in a university bilingual context, little studied from an Arabophone context. We have studied a sample of 68 Jordanian students from the Yarmouk University by means of questionnaire. This study also reveals the representations - stereotypes of both mother and foreign tongues and their places in class of French language as a foreign language. The results of this study show that the students have a very well-balanced about the generally sight of the French language and its apprenticeship. The study also makes evident the existence of relationship between the representations of the target language and the motiv! ation for learning. Moreover; this study shows the importance of understanding the complex nature of the representations of learners towards their mother tongue and the first language learnt in the classroom of French as a Foreign Language
Lagrange, Jean-Baptiste. "Des situations connues aux traitements sur des données codifiées : représentations mentales et processus d'acquisition dans les premiers apprentissages en informatique." Paris 7, 1991. http://jb.lagrange.free.fr/Preprints/TheseLagrange.pdf.
Full textGaüzère, Benoit. "Application des méthodes à noyaux sur graphes pour la prédiction des propriétés des molécules." Phd thesis, Université de Caen, 2013. http://tel.archives-ouvertes.fr/tel-00933187.
Full textLi, Huihua. "Généralisation de l'ordre et des paramètres de macro-actions par apprentissage basé sur l'explication. Extension de l'apprentissage par explications sur l'ordre partiel." Paris 6, 1992. http://www.theses.fr/1992PA066233.
Full textTiré, Marianne. "Les pratiques effectives d'acculturation à l'écrit en classe de CP : impact sur les représentations des élèves et sur l'apprentissage du lire-écrire." Thesis, Université Grenoble Alpes (ComUE), 2017. http://www.theses.fr/2017GREAL022/document.
Full textSeveral national and international studies (reading writing numeracy, PISA, PIRLS) have shown that the gap in France between pupils from privileged sociocultural backgrounds and those from a disadvantaged background when it comes to reading and writing is on the increase. Our research focuses on written teaching. We are trying to demonstrate how teaching practices that favour writing cultural integration through technical learning of reading and writing can help reducing inequalities. In order to explore the connection between cultural integration practices for writing in CP classes and learning to read, a longitudinal study was undertaken in two CP classes within a priority education zone. Our ecological and ethnographic approach is based on qualitative and quantitative data collected from interviews with pupils and teachers and from questionnaire filled in by parents. Our own data were compounded with results from #LireEcrireCP research coordinated by R.Goigoux (evaluations, questionnaires, “coded tasks” records, class videos). Results show on one hand that moderate cultural integration practices are not sufficient for pupils’ progress to reduce inequalities. On the other hand, that in order to be efficient, not only acculturation practices must be used regularly and routinely, but they must also be used in conjunction with teaching practices that encourage language interaction in order to make sense of what has been learned, and to consider writing in its entirety and not only in a school context. Finally, analysis of two examples of cultural integration (written assignment and various reading practices) in two other classes taking part in the study #LireEcrireCP shows that cultural integration practices can be successful, even in priority education. Our research therefore demonstrates that cultural integration practices, along with efficient teaching methods, can contribute to a reduction in academic inequalities
Boudebia-Baala, Afaf. "L'impact des contextes sociolinguistique et scolaire sur l'enseignement/apprentissage du français dans le Souf à travers l'analyse des représentations comme outil de description." Phd thesis, Université de Franche-Comté, 2012. http://tel.archives-ouvertes.fr/tel-00942722.
Full textBoudebia-Baala, Afaf. "L'impact des contextes sociolinguistique et scolaire sur l'enseignement/apprentissage du français dans le Souf à travers l'analyse des représentations comme outil de description." Electronic Thesis or Diss., Besançon, 2012. http://indexation.univ-fcomte.fr/nuxeo/site/esupversions/a16ab6c1-551f-4c84-83f2-2dc7f158364f.
Full textTaking as anchor sociolinguistics and didactics, our study focuses on the context of teaching/learning of French in the South-Eastern Algeria: The Souf. The specificity of this context has been studied following two different but complementary axes: the sociolinguistic environment and the institutional framework. Both axes have been defined from the thematic analysis of declarative data gathered from a group of teachers and learners. In order to connect the views of teachers/learners, we chose to triangulate the data gathered using several tools: questionnaires, interviews, word association tests and writing. The thesis takes an approach that is both qualitative and quantitative. Our goal is to determine the impact of the sociolinguistic and educational contexts on the teaching/learning of French in the Souf using the representations as a tool of description. The results indicate that several parameters produce a negative impact on the teaching/learning of French. The most important are : the absence of linguistic practices in French, linguistic attitudes, social environment, representations of languages, inadequate academic curriculum, the reduced number of hours devoted to teaching/learning, reduced importance of the teaching of French in the educational system, and recruitment of unqualified teachers. Some of our findings can be used in order to contextualize means to influence teacher training and linguistic representations in the learners
Simonovsky, Martin. "Deep learning on attributed graphs." Thesis, Paris Est, 2018. http://www.theses.fr/2018PESC1133/document.
Full textGraph is a powerful concept for representation of relations between pairs of entities. Data with underlying graph structure can be found across many disciplines, describing chemical compounds, surfaces of three-dimensional models, social interactions, or knowledge bases, to name only a few. There is a natural desire for understanding such data better. Deep learning (DL) has achieved significant breakthroughs in a variety of machine learning tasks in recent years, especially where data is structured on a grid, such as in text, speech, or image understanding. However, surprisingly little has been done to explore the applicability of DL on graph-structured data directly.The goal of this thesis is to investigate architectures for DL on graphs and study how to transfer, adapt or generalize concepts working well on sequential and image data to this domain. We concentrate on two important primitives: embedding graphs or their nodes into a continuous vector space representation (encoding) and, conversely, generating graphs from such vectors back (decoding). To that end, we make the following contributions.First, we introduce Edge-Conditioned Convolutions (ECC), a convolution-like operation on graphs performed in the spatial domain where filters are dynamically generated based on edge attributes. The method is used to encode graphs with arbitrary and varying structure.Second, we propose SuperPoint Graph, an intermediate point cloud representation with rich edge attributes encoding the contextual relationship between object parts. Based on this representation, ECC is employed to segment large-scale point clouds without major sacrifice in fine details.Third, we present GraphVAE, a graph generator allowing to decode graphs with variable but upper-bounded number of nodes making use of approximate graph matching for aligning the predictions of an autoencoder with its inputs. The method is applied to the task of molecule generation
Poezevara, Guillaume. "Fouille de graphes pour la découverte de contrastes entre classes : application à l'estimation de la toxicité des molécules." Phd thesis, Université de Caen, 2011. http://tel.archives-ouvertes.fr/tel-01018425.
Full textCascioli, Fiammetta. "La performativité du MOOC sur les représentations de l’apprenant : le cas du parcours MOOCLead." Thesis, Paris, HESAM, 2020. http://www.theses.fr/2020HESAC010.
Full textMOOCs are innovative learning tools (Christensen, 2013), have an amplifying effect (Ceci, 2018) and have disrupted the world of in-company training (Karnouskos, 2017) On the basis of Cox's (2013) hypothesis, according to which digital technology allows the achievement of performativity on learner representations, research studies the performative impact of MOOC on the representations, "the world of descriptions" (Laurillard, 2002) of learners in companies. It thus analyses the dynamics of behavioural change and, consequently, managerial identities (Harding, 2003 cited by Aggeri, 2017). This work has thus made it possible to explain the key factors that enable the evolution of representations and the modification of behaviour in companies thanks to digital technology
Remila, Eric. "Pavage de figures par des barres et reconnaissance de graphes sous-jacents à des réseaux d'automates." Lyon 1, 1992. http://www.theses.fr/1992LYO10037.
Full textDhifli, Wajdi. "Fouille de Sous-graphes Basée sur la Topologie et la Connaissance du Domaine: Application sur les Structures 3D de Protéines." Phd thesis, Université Blaise Pascal - Clermont-Ferrand II, 2013. http://tel.archives-ouvertes.fr/tel-00922209.
Full textViswanathan, Jayalakshmi. "Quand le bruit nous éclaire : une étude sur les mécanismes de la perception et de la mémoire à long-terme pour des stimuli auditifs sans signification." Thesis, Toulouse 3, 2016. http://www.theses.fr/2016TOU30334/document.
Full textHumans are able to detect acoustic features in Gaussian noise. Researchers recently used repeating noise segments [cyclic noises (CNs), presenting a segment of noise several times back to back] to investigate long-term sensory memory (Agus et al., 2010). They asked participants to discriminate CNs from plain noise, while implicitly presenting them with a few target CNs several times. The results demonstrated long-term memory for such sounds, which have raised several further questions. First, the robustness of memory for implicitly learned Gaussian sounds was tested using a similar paradigm. Participants' recognition memory was tested by presenting them with looped and scrambled (10 or 20-ms bin size) versions of target CNs 4 weeks post-learning. Our results suggest that neurons might code for very small bits of acoustic information (10 ms). Next, the spatial correlates of memory, specifically, the role of subcortical areas in storing auditory patterns was investigated. Using the same paradigm, participants performed the testing session during fMRI scanning. Implicit memory for target CNs was demonstrated and functional contrasts implicate the Medial Geniculate body and hippocampus. Lastly, we explored the mechanisms and resolution limits of this memory. Participants were presented with CNs in one ear and plain noise in the other ear, and had to localize the CN. Implicit and explicit memory for target CNs was tested 4 weeks later. Although participants lacked conscious memory, they were better at localizing target 10-ms CNs than novel CNs, even with 8 repeats (80 ms). Altogether we demonstrate: 1) the ability to learn and store short acoustic patterns (10 ms); 2) this memory is sub-cortical, in regions implicated in perception of sounds; and 3) these results are compatible with an STDP model of learning
Haugeard, Jean-Emmanuel. "Extraction et reconnaissance de primitives dans les façades de Paris à l'aide d'appariement de graphes." Thesis, Cergy-Pontoise, 2010. http://www.theses.fr/2010CERG0497.
Full textThis last decade, modeling of 3D city became one of the challenges of multimedia search and an important focus in object recognition. In this thesis we are interested to locate various primitive, especially the windows, in the facades of Paris. At first, we present an analysis of the facades and windows properties. Then we propose an algorithm able to extract automatically window candidates. In a second part, we discuss about extraction and recognition primitives using graph matching of contours. Indeed an image of contours is readable by the human eye, which uses perceptual grouping and makes distinction between entities present in the scene. It is this mechanism that we have tried to replicate. The image is represented as a graph of adjacency of segments of contours, valued by information orientation and proximity to edge segments. For the inexact matching of graphs, we propose several variants of a new similarity based on sets of paths, able to group several contours and robust to scale changes. The similarity between paths takes into account the similarity of sets of segments of contours and the similarity of the regions defined by these paths. The selection of images from a database containing a particular object is done using a KNN or SVM classifier
Boujaada, Elhadi. "Les représentations du fonctionnement du système nerveux véhiculées par le discours d'un manuel de biologie marocain au secondaire, et leur incidence sur la conception de l'apprentissage." Master's thesis, Université Laval, 1988. http://hdl.handle.net/20.500.11794/29320.
Full textKahindo, Senge Muvingi Christian. "Analyse automatique de l’écriture manuscrite sur tablette pour la détection et le suivi thérapeutique de personnes présentant des pathologies." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLL016/document.
Full textWe present, in this thesis, a novel paradigm for assessing Alzheimer’s disease by analyzing impairment of handwriting (HW) on tablets, a challenging problem that is still in its infancy. The state of the art is dominated by methods that assume a unique behavioral trend for each cognitive profile, and that extract global kinematic parameters, assessed by standard statistical tests or classification models, for discriminating the neuropathological disorders (Alzheimer’s (AD), Mild Cognitive Impairment (MCI)) from Healthy Controls (HC). Our work tackles these two major limitations as follows. First, instead of considering a unique behavioral pattern for each cognitive profile, we relax this heavy constraint by allowing the emergence of multimodal behavioral patterns. We achieve this by performing semi-supervised learning to uncover homogeneous clusters of subjects, and then we analyze how much information these clusters carry on the cognitive profiles. Second, instead of relying on global kinematic parameters, mostly consisting of their average, we refine the encoding either by a semi-global parameterization, or by modeling the full dynamics of each parameter, harnessing thereby the rich temporal information inherently characterizing online HW. Thanks to our modeling, we obtain new findings that are the first of their kind on this research field. A striking finding is revealed: two major clusters are unveiled, one dominated by HC and MCI subjects, and one by MCI and ES-AD, thus revealing that MCI patients have fine motor skills leaning towards either HC’s or ES-AD’s. This thesis introduces also a new finding from HW trajectories that uncovers a rich set of features simultaneously like the full velocity profile, size and slant, fluidity, and shakiness, and reveals, in a naturally explainable way, how these HW features conjointly characterize, with fine and subtle details, the cognitive profiles
Ghoumari, Asmaa. "Métaheuristiques adaptatives d'optimisation continue basées sur des méthodes d'apprentissage." Thesis, Paris Est, 2018. http://www.theses.fr/2018PESC1114/document.
Full textThe problems of continuous optimization are numerous, in economics, in signal processing, in neural networks, and so on. One of the best-known and most widely used solutions is the evolutionary algorithm, a metaheuristic algorithm based on evolutionary theories that borrows stochastic mechanisms and has shown good performance in solving problems of continuous optimization. The use of this family of algorithms is very popular, despite the many difficulties that can be encountered in their design. Indeed, these algorithms have several parameters to adjust and a lot of operators to set according to the problems to solve. In the literature, we find a plethora of operators described, and it becomes complicated for the user to know which one to select in order to have the best possible result. In this context, this thesis has the main objective to propose methods to solve the problems raised without deteriorating the performance of these algorithms. Thus we propose two algorithms:- a method based on the maximum a posteriori that uses diversity probabilities for the operators to apply, and which puts this choice regularly in play,- a method based on a dynamic graph of operators representing the probabilities of transitions between operators, and relying on a model of the objective function built by a neural network to regularly update these probabilities. These two methods are detailed, as well as analyzed via a continuous optimization benchmark
Defrasne, Ait-Said Elise. "Perception et représentation du mouvement : influences de la verbalisation sur la reconnaissance de mouvements d'escrime en fonction de l'expertise." Thesis, Besançon, 2014. http://www.theses.fr/2014BESA1023/document.
Full textIs it necessary to verbalize in order to memorize and learn a material? According to the literature examining the influence of verbalizations on learning and memory, the answer to this question depends on the type of material used (conceptual material versus perceptive material) and on the learners’ level of expertise. In Study 1, we examined the influence of verbal descriptions on the visual recognition of sequences of fencing movements, with participants of the three levels of expertise (novices, intermediates, experts). In Study 2, we studied the influence of different content of verbal descriptions on the recognition of sequences of fencing movements, according to the level of expertise. The goal of Study 3 was to examine the effect on memory of a trace distinct from a verbal trace: a motor trace. The findings of Study 1 show that verbalizing improves novices’ recognition, impairs intermediates’ recognition and has no effect on experts’ recognition. The results of Study 2 show that the content of verbal descriptions has an effect on memory, according to the participants’ level of expertise. The findings of Study 3 show that duplicating the fencing movement, with no feedback, strongly impedes beginners’ visual recognition. These findings broaden the verbal overshadowing phenomena to a material distinctly more conceptual than the one classically used in this field of research. They bring strong support to the theoretical hypothesis of interference resulting from a verbal recoding (Schooler, 1990). They also show that an additional motor trace can harm visual recognition of movement sequences
Negreponti, Androniki Iliana. "La prise en compte de l'élève dyslexique dans l'enseignement/apprentissage de l'anglais : une étude qualitative sur les représentations et les points de vue des enseignants, des parents et des élèves dyslexiques en France et en Grèce." Nantes, 2014. http://www.theses.fr/2014NANT3009.
Full textGulikers, Lennart. "Sur deux problèmes d’apprentissage automatique : la détection de communautés et l’appariement adaptatif." Thesis, Paris Sciences et Lettres (ComUE), 2017. http://www.theses.fr/2017PSLEE062/document.
Full textIn this thesis, we study two problems of machine learning: (I) community detection and (II) adaptive matching. I) It is well-known that many networks exhibit a community structure. Finding those communities helps us understand and exploit general networks. In this thesis we focus on community detection using so-called spectral methods based on the eigenvectors of carefully chosen matrices. We analyse their performance on artificially generated benchmark graphs. Instead of the classical Stochastic Block Model (which does not allow for much degree-heterogeneity), we consider a Degree-Corrected Stochastic Block Model (DC-SBM) with weighted vertices, that is able to generate a wide class of degree sequences. We consider this model in both a dense and sparse regime. In the dense regime, we show that an algorithm based on a suitably normalized adjacency matrix correctly classifies all but a vanishing fraction of the nodes. In the sparse regime, we show that the availability of only a small amount of information entails the existence of an information-theoretic threshold below which no algorithm performs better than random guess. On the positive side, we show that an algorithm based on the non-backtracking matrix works all the way down to the detectability threshold in the sparse regime, showing the robustness of the algorithm. This follows after a precise characterization of the non-backtracking spectrum of sparse DC-SBM's. We further perform tests on well-known real networks. II) Online two-sided matching markets such as Q&A forums and online labour platforms critically rely on the ability to propose adequate matches based on imperfect knowledge of the two parties to be matched. We develop a model of a task / server matching system for (efficient) platform operation in the presence of such uncertainty. For this model, we give a necessary and sufficient condition for an incoming stream of tasks to be manageable by the system. We further identify a so-called back-pressure policy under which the throughput that the system can handle is optimized. We show that this policy achieves strictly larger throughput than a natural greedy policy. Finally, we validate our model and confirm our theoretical findings with experiments based on user-contributed content on an online platform
Halftermeyer, Pierre. "Connexité dans les Réseaux et Schémas d’Étiquetage Compact d’Urgence." Thesis, Bordeaux, 2014. http://www.theses.fr/2014BORD0140/document.
Full textWe aim at assigning each vertex x of a n-vertices graph G a compact O(log n)-bit label L(x) in order to :1. construct, from the labels of the vertices of a forbidden set X C V (G), a datastructure S(X)2. decide, from S(X), L(u) and L(v), whether two vertices u and v are connected in G n X.We give a solution to this problem for the family of 3-connected graphs whith bounded genus.— We obtain O(g log n)-bit labels.— S(X) is computed in O(Sort([X]; n)) time.— Connection between vertices is decided in O(log log n) optimal time.We finally extend this result to H-minor-free graphs. This scheme requires O(polylog n)-bit labels
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.
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
Kosowska-Stamirowska, Zuzanna. "Évolution et robustesse du réseau maritime mondial : une approche par les systèmes complexes." Thesis, Paris 1, 2020. http://www.theses.fr/2020PA01H022.
Full textOver 70% of the total value of international trade is carried by sea, accounting for 80% of all cargo in terms of volume. In 2016, the UN Secretary General drew attention to the role of maritime transport, describing it as “the backbone of global trade and of the global economy”. Maritime trade flows impact not only the economic development of the concerned regions, but also their ecosystems. Moving ships are an important vector of spread for bioinvasions. Shipping routes are constantly evolving and likely to be affected by the consequences of Climate Change, while at the same time ships are a considerable source of air pollution, with CO2 emissions at a level comparable to Germany, and NOx and SOx emissions comparable to the United States. With the development of Arctic shipping becoming a reality, the need to understand the behavior of this system and to forecast future maritime trade flows reasserts itself. Despite their scope and crucial importance, studies of maritime trade flows on a global scale, based on data and formal methods are scarce, and even fewer studies address the question of their evolution. In this thesis we use a unique database on daily movements of the world fleet between 1977 and 2008 provided by the maritime insurer Lloyd’s in order to build a complex network of maritime trade flows where ports stand for nodes and links are created by ship voyages. In this thesis we perform a data-driven analysis of the maritime trade network. We use tools from Complexity Science and Machine Learning applied on network data to study the network’s properties and develop models for predicting the opening of new shipping lines and for forecasting future trade volume on links. Applying Machine Learning to analyse networked trade flows appears to be a new approach with respect to the state-of-the-art, and required careful selection and customization of existing Machine Learning tools to make them fit networked data on physical flows. The results of the thesis suggest a hypothesis of trade following a random walk on the underlying network structure. [...] Thanks to a natural experiment, involving traffic redirection from the port of Kobe after the 1995 earthquake, we find that the traffic was redirected preferentially to ports which had the highest number of Common Neighbors with Kobe before the cataclysm. Then, by simulating targeted attacks on the maritime trade network, we analyze the best criteria which may serve to maximize the harm done to the network and analyse the overall robustness of the network to different types of attacks. All these results hint that maritime trade flows follow a form of random walk on the network of sea connections, which provides evidence for a novel view on the nature of trade flows
Allani, Atig Olfa. "Une approche de recherche d'images basée sur la sémantique et les descripteurs visuels." Thesis, Paris 8, 2017. http://www.theses.fr/2017PA080032.
Full textImage retrieval is a very active search area. Several image retrieval approaches that allow mapping between low-level features and high-level semantics have been proposed. Among these, one can cite object recognition, ontologies, and relevance feedback. However, their main limitation concern their high dependence on reliable external resources and lack of capacity to combine semantic and visual information.This thesis proposes a system based on a pattern graph combining semantic and visual features, relevant visual feature selection for image retrieval and improvement of results visualization. The idea is (1) build a pattern graph composed of a modular ontology and a graph-based model, (2) to build visual feature collections to guide feature selection during online retrieval phase and (3) improve the retrieval results visualization with the integration of semantic relations.During the pattern graph building, ontology modules associated to each domain are automatically built using textual corpuses and external resources. The region's graphs summarize the visual information in a condensed form and classify it given its semantics. The pattern graph is obtained using modules composition. In visual features collections building, association rules are used to deduce the best practices on visual features use for image retrieval. Finally, results visualization uses the rich information on images to improve the results presentation.Our system has been tested on three image databases. The results show an improvement in the research process, a better adaptation of the visual features to the domains and a richer visualization of the results
Bautista, Ruiz Esteban. "Laplacian Powers for Graph-Based Semi-Supervised Learning." Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEN081.
Full textGraph-Based Semi-Supervised Learning (G-SSL) techniques learn from both labelled and unla- belled data to build better classifiers. Despite successes, its performance can still be improved, particularly in cases of graphs with unclear clusters or unbalanced labelled datasets. To ad- dress such limitations, the main contribution of this dissertation is a novel method for G-SSL referred to as the Lγ -PageRank method. It consists of a generalization of the PageRank algo- rithm based on the positive γ-th powers of the graph Laplacian matrix. The theoretical study of Lγ -PageRank shows that (i) for γ < 1, it corresponds to an extension of the PageRank algo- rithm to L´evy processes: where random walkers can now perform far-distant jumps in a single step; and (ii) for γ > 1, it operates on signed graphs: where nodes belonging to one same class are more likely to share positive edges while nodes from different classes are more likely to be connected with negative edges. We show the existence of an optimal γ-th power that maximizes performance, for which a method for its automatic estimation is devised and assessed. Exper- iments on several datasets demonstrate that the L´evy flight random walkers can enhance the detection of classes with complex local structures and that the signed graphs can significantly improve the separability of data and also override the issue of unbalanced labelled data. In addition, we study efficient implementations of Lγ -PageRank. Extensions of Power Iteration and Gauss-Southwell, successful algorithms to efficiently compute the solution of the standard PageRank algorithm, are derived for Lγ -PageRank. Moreover, the dynamic versions of Power Iteration and Gauss-Southwell, which can update the solution of standard PageRank in sub- linear complexity when the graph evolves or new data arrive, are also extended to Lγ -PageRank. Lastly, we apply Lγ -PageRank in the context of Internet routing. We address the problem of identifying the Autonomous Systems (AS) of inter-AS links from the network of IP addresses and AS public registers. Experiments on tracerout measurements collected from the Internet show that Lγ -PageRank can solve this inference task with no errors, even when the expert does not provide labelled examples of all classes
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.
Full textThis 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
Viale, Benjamin. "Development of predictive analysis solutions for the ESD robustness of integrated circuits in advanced CMOS technologies." Thesis, Lyon, 2017. http://www.theses.fr/2017LYSEI117.
Full textAs Integrated Circuits (ICs) become more complex and susceptible to ElectroStatic Discharges (ESD), the ability to reliably verify the presence of ESD design weaknesses over a multi-billion transistor chip prior to the tape-out is a major topic in the semiconductor industry. Commercial tools dedicated to Electronic Design Automation (EDA) and related verification flows are in charge of providing checks that have been proven to be efficient for circuits with a mainstream architecture. However, they suffer limitations when confronted with custom designs. Moreover, these verification methods are often run late in the design flow, making any design re-spin costly in terms of corrective efforts and time. This Ph. D. thesis proposes a systematic and scalable ESD verification methodology embodied in a tool called ESD IP Explorer that has been specifically implemented to cover the entire design flow and to comply with custom circuit architectures. It is composed of a recognition module and a verification module. The recognition module first automatically identifies ESD protection structures, embedded in integrated circuits to enhance their ESD hardness, according to a topology-aware recognition mechanism. The verification module then converts the ESD protection network that is formed by ESD protection structures into a directed graph. There, technology-independent and graph-based verification mechanisms perform a chip-scale quasistatic ESD analysis. Machine learning algorithms have been used in order to infer the quasistatic behavior of ESD IPs from the netlist instance parameters of their primary devices. This approach has the advantage that no simulation is required during the execution of ESD IP Explorer, which makes the tool architecture simpler and improves execution times. Implementation efforts pertained to the compliance of ESD IP Explorer with the 28nm Fully Depleted Silicon On Insulator (FD-SOI) technology node. The developed verification tool has been used to successfully analyze a digital and mixed-signal circuit prototype counting more than 1.5 billion transistors in several hours, as well as custom designs that could not be analyzed by means of traditional verification tools due to incompatibility issues
Lajoie, Isabelle. "Apprentissage de représentations sur-complètes par entraînement d’auto-encodeurs." Thèse, 2009. http://hdl.handle.net/1866/3768.
Full textProgress in the machine learning domain allows computational system to address more and more complex tasks associated with vision, audio signal or natural language processing. Among the existing models, we find the Artificial Neural Network (ANN), whose popularity increased suddenly with the recent breakthrough of Hinton et al. [22], that consists in using Restricted Boltzmann Machines (RBM) for performing an unsupervised, layer by layer, pre-training initialization, of a Deep Belief Network (DBN), which enables the subsequent successful supervised training of such architecture. Since this discovery, researchers studied the efficiency of other similar pre-training strategies such as the stacking of traditional auto-encoder (SAE) [5, 38] and the stacking of denoising auto-encoder (SDAE) [44]. This is the context in which the present study started. After a brief introduction of the basic machine learning principles and of the pre-training methods used until now with RBM, AE and DAE modules, we performed a series of experiments to deepen our understanding of pre-training with SDAE, explored its different proprieties and explored variations on the DAE algorithm as alternative strategies to initialize deep networks. We evaluated the sensitivity to the noise level, and influence of number of layers and number of hidden units on the generalization error obtained with SDAE. We experimented with other noise types and saw improved performance on the supervised task with the use of pepper and salt noise (PS) or gaussian noise (GS), noise types that are more justified then the one used until now which is masking noise (MN). Moreover, modifying the algorithm by imposing an emphasis on the corrupted components reconstruction during the unsupervised training of each different DAE showed encouraging performance improvements. Our work also allowed to reveal that DAE was capable of learning, on naturals images, filters similar to those found in V1 cells of the visual cortex, that are in essence edges detectors. In addition, we were able to verify that the learned representations of SDAE, are very good characteristics to be fed to a linear or gaussian support vector machine (SVM), considerably enhancing its generalization performance. Also, we observed that, alike DBN, and unlike SAE, the SDAE had the potential to be used as a good generative model. As well, we opened the door to novel pre-training strategies and discovered the potential of one of them : the stacking of renoising auto-encoders (SRAE).
Habib, Maria. "Influence du français langue seconde sur les représentations identitaires des jeunes au Liban." Phd thesis, 2009. http://tel.archives-ouvertes.fr/tel-00411947.
Full textAssouel, Rim. "Entity-centric representations in deep learning." Thesis, 2020. http://hdl.handle.net/1866/24306.
Full textL'incroyable capacité des humains à modéliser la complexité du monde physique est rendue possible par la décomposition qu'ils en font en un ensemble d'entités et de règles simples. De nombreux travaux en sciences cognitives montre que la perception humaine et sa capacité à raisonner est essentiellement centrée sur la notion d'objet. Motivés par cette observation, de récents travaux se sont intéressés aux différentes approches d'apprentissage de représentations centrées sur des entités et comment ces représentations peuvent être utilisées pour résoudre plus facilement des tâches sous-jacentes. Dans la première contribution on montre comment une architecture centrée sur la notion d'entité va permettre d'extraire des entités visuelles interpretables et d'apprendre un modèle du monde plus robuste aux différentes configurations d'objets. Dans la deuxième contribution on s’intéresse à un modèle de génération de graphes dont l'architecture est également centrée sur la notion d'entités et comment cette architecture rend plus facile l'apprentissage d'une génération conditionelle à certaines propriétés du graphe. On s’intéresse plus particulièrement aux applications en découverte de médicaments. Dans cette tâche, on souhaite optimiser certaines propriétés physico-chmiques du graphe d'une molécule qui a été efficace in-vitro et dont on veut faire un médicament.