Dissertationen zum Thema „Apprentissage dynamique“
Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an
Machen Sie sich mit Top-50 Dissertationen für die Forschung zum Thema "Apprentissage dynamique" bekannt.
Neben jedem Werk im Literaturverzeichnis ist die Option "Zur Bibliographie hinzufügen" verfügbar. Nutzen Sie sie, wird Ihre bibliographische Angabe des gewählten Werkes nach der nötigen Zitierweise (APA, MLA, Harvard, Chicago, Vancouver usw.) automatisch gestaltet.
Sie können auch den vollen Text der wissenschaftlichen Publikation im PDF-Format herunterladen und eine Online-Annotation der Arbeit lesen, wenn die relevanten Parameter in den Metadaten verfügbar sind.
Sehen Sie die Dissertationen für verschiedene Spezialgebieten durch und erstellen Sie Ihre Bibliographie auf korrekte Weise.
Cleeremans, Axel. „Conscience et apprentissage: une perspective dynamique“. Doctoral thesis, Universite Libre de Bruxelles, 2001. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/211510.
Der volle Inhalt der QuelleQuoy, Mathias. „Apprentissage dans les réseaux neuromimétiques à dynamique chaotique“. Toulouse, ENSAE, 1994. http://www.theses.fr/1994ESAE0009.
Der volle Inhalt der QuelleNarassiguin, Anil. „Apprentissage Ensembliste, Étude comparative et Améliorations via Sélection Dynamique“. Thesis, Lyon, 2018. http://www.theses.fr/2018LYSE1075/document.
Der volle Inhalt der QuelleEnsemble methods has been a very popular research topic during the last decade. Their success arises largely from the fact that they offer an appealing solution to several interesting learning problems, such as improving prediction accuracy, feature selection, metric learning, scaling inductive algorithms to large databases, learning from multiple physically distributed data sets, learning from concept-drifting data streams etc. In this thesis, we first present an extensive empirical comparison between nineteen prototypical supervised ensemble learning algorithms, that have been proposed in the literature, on various benchmark data sets. We not only compare their performance in terms of standard performance metrics (Accuracy, AUC, RMS) but we also analyze their kappa-error diagrams, calibration and bias-variance properties. We then address the problem of improving the performances of ensemble learning approaches with dynamic ensemble selection (DES). Dynamic pruning is the problem of finding given an input x, a subset of models among the ensemble that achieves the best possible prediction accuracy. The idea behind DES approaches is that different models have different areas of expertise in the instance space. Most methods proposed for this purpose estimate the individual relevance of the base classifiers within a local region of competence usually given by the nearest neighbours in the euclidean space. We propose and discuss two novel DES approaches. The first, called ST-DES, is designed for decision tree based ensemble models. This method prunes the trees using an internal supervised tree-based metric; it is motivated by the fact that in high dimensional data sets, usual metrics like euclidean distance suffer from the curse of dimensionality. The second approach, called PCC-DES, formulates the DES problem as a multi-label learning task with a specific loss function. Labels correspond to the base classifiers and multi-label training examples are formed based on the ability of each classifier to correctly classify each original training example. This allows us to take advantage of recent advances in the area of multi-label learning. PCC-DES works on homogeneous and heterogeneous ensembles as well. Its advantage is to explicitly capture the dependencies between the classifiers predictions. These algorithms are tested on a variety of benchmark data sets and the results demonstrate their effectiveness against competitive state-of-the-art alternatives
Daucé, Emmanuel. „Adaptation dynamique et apprentissage dans les réseaux de neurones récurrents aléatoires“. Toulouse, ENSAE, 2000. https://tel.archives-ouvertes.fr/tel-01394004.
Der volle Inhalt der QuelleCordier, Pierre. „Statique et dynamique d'un apprentissage moteur analyse et trajectoires en escalade“. Paris, EPHE, 1995. http://www.theses.fr/1995EPHE3017.
Der volle Inhalt der QuelleHuet, Frédéric. „Apprentissage collectif et dynamique coopérative : Une étude empirique des PME françaises“. Compiègne, 2004. http://www.theses.fr/2004COMP1541.
Der volle Inhalt der QuelleResearch in Knowledge Based Economics brings to the fore the emergence of innovation as a new modality of competition, and the increasing role of cooperative relationships. The thesis questions this link between cooperation and innovation, based on a framework rooted in knowledge paradigm and an original empirical study encompassing data from more than 600 French SMEs. Statistical results (based on a questionnaire) and qualitative results (based on interviews) allow identifying the organisational and environrnental factors of innovation through cooperation. Far from being systematically a result of cooperation, innovation relies on firms' own capacities and (their) adopted cooperative configurations. Given the low rate of cooperation of French SMEs, the identification of cognitive and intentional dimensions of leaming takes us beyond the consideration of SMEs and cooperation as homogenous analysis categories in order to appreciate their diversity. Ln addition, self enforcing effects between the characteristics of firms and cooperation leads to relativize the effect of partnerships for innovation in SMEs
Amadou, Boubacar Habiboulaye. „Classification Dynamique de données non-stationnaires :Apprentissage et Suivi de Classes évolutives“. Phd thesis, Université des Sciences et Technologie de Lille - Lille I, 2006. http://tel.archives-ouvertes.fr/tel-00106968.
Der volle Inhalt der QuelleCentlivre-Petit, Dominique. „Outils de pilotage economique et dynamique d'apprentissage local dans une structure multidimensionnelle. Le cas du groupe danone“. Palaiseau, Ecole polytechnique, 1998. http://www.theses.fr/1998EPXX0055.
Der volle Inhalt der QuelleFirms are facing new constraints as regards innovation, value-added products to customers, flexible and cross-sectional management. Creating operational devices to deal with these constraints is a key managerial issue. The thesis puts forward a possible approach from two main assumptions : -specific management tools provide middle managers with strategic competence. They produce knowledge and generate learning processes within the firm. -the use of such specific management tools very much depends on the organizational structure of the firm. In the danone group, the relevant managerial level to study the implementation of these explanatory management tools are the middle managers in plants and functional departments the managers are required to co-ordinate with their counterparts on an horizontal basis and to manage with vertical management effectiveness. The exploratory management tools allow them to deal with the two requirements while keeping in mind the strategic objectives of the firm. Both assumptions are validated through a twofold examination : -on the one hand, from a theoretical perspective, the research makes use of the findings on organizational learning to comprehend the mechanisms by which management knowledge develops and spreads within the firm. -on the other hand, the research is based on experimental field work, the purpose of which was to elaborate specific management tools and devices in a multinational firm in the food industry. The thesis provides both practical and theoretical answers to the following questions : -what is or should be the task assigned to local managers in the management learning processes in multidivisional firms ? -to which extent the explanatory management tools participate to improving the strategy of the firm ? -under which circumstances can a learning process be set into motion ? -in a particular structural firm environment, how should the learning process be organised and dealt with ?
Cadet, Claire. „Adaptation à un environnement variable : dispersion, plasticité, apprentissage“. Paris 6, 2003. http://www.theses.fr/2003PA066038.
Der volle Inhalt der QuelleBen, Abdallah Emna. „Étude de la dynamique des réseaux biologiques : apprentissage des modèles, intégration des données temporelles et analyse formelle des propriétés dynamiques“. Thesis, Ecole centrale de Nantes, 2017. http://www.theses.fr/2017ECDN0041.
Der volle Inhalt der QuelleOver the last few decades, the emergence of a wide range of new technologies has produced a massive amount of biological data (genomics, proteomics...). Thus, a very large amount of time series data is now produced every day. The newly produced data can give us new ideas about the behavior of biological systems. This leads to considerable developments in the field of bioinformatics that could benefit from these enormous data. This justifies the motivation to develop efficient methods for learning Biological Regulatory Networks (BRN) modeling a biological system from its time series data. Then, in order to understand the nature of system functions, we study, in this thesis, the dynamics of their BRN models. Indeed, we focus on developing original and scalable logical methods (implemented in Answer Set Programming) to deciphering the emerging complexity of dynamics of biological systems. The main contributions of this thesis are enumerated in the following. (i) Refining the dynamics of the BRN, modeling with the automata Network (AN) formalism, by integrating a temporal parameter (delay) in the local transitions of the automata. We call the extended formalism a Timed Automata Network (T-AN). This integration allows the parametrization of the transitions between each automata local states as well as between the network global states. (ii) Learning BRNs modeling biological systems from their time series data. (iii) Model checking of discrete dynamical properties of BRN (modeling with AN and T-AN) by dynamical formal analysis : attractors identification (minimal trap domains from which the network cannot escape) and reachability verification of an objective from a network global initial state
Munos, Rémi. „Apprentissage par renforcement, étude du cas continu“. Paris, EHESS, 1997. http://www.theses.fr/1997EHESA021.
Der volle Inhalt der QuelleMegrot, Fabrice. „Une analyse dimensionnelle de l'équilibre précaire chez l'homme“. Paris 11, 2002. http://www.theses.fr/2002PA112319.
Der volle Inhalt der QuelleThe maintenance of an unstable equilibrium requires the coordination of multiple joints in order to maintain the centre of mass above the base of support. In the present study we aimed at discovering the underlying dynamics of local (centre of mass of trunk, hip, or head) and global (body centre of mass) components involved in balance control, and how these dynamics were affected by changes in the available information, sport expertise and by learning. Participants had to maintain their balance on an unstable platform. Using dimensional analyses (largest Liapunov exponent and correlation dimension), we examined the active degrees of freedom involved in balance control. Results indicated a similarity in dimension between local (local centres of mass) and global (body centre of mass) components, between a fixed point and a limit cycle. However, the behaviour of the centre of mass was found to be more predictable than the behaviour of its local constituents. In addition, the available visual information affected the predictability of the postural behaviour, suggesting that vision was used to stabilize the low-dimensional dynamics underlying balance control
Cao, Yi-Heng. „Apprentissage génératif pour la synthèse d'images médicales dynamiques 4D“. Electronic Thesis or Diss., Brest, 2024. http://www.theses.fr/2024BRES0004.
Der volle Inhalt der QuelleFour-dimensional computed tomography (4DCT) involves reconstructing an acquisition in multiple phases to track the movements of internal organs and tumors. It is used routinely for radiotherapy treatment planning of lung cancer, but it exposes patients to higher radiation doses, up to six times greater than those of a conventional threedimensional computed tomography (3DCT). Deep learning methods from the field of computer vision are gaining significant interest within the medical imaging community. Among these approaches, generative models stand out due to their ability to generate synthetic images that faithfully replicate the appearance and statistical characteristics of images acquired from real systems. In this thesis, we explore the use of a generative model for dynamic image generation. We propose a model capable of generating patient-specific respiratory motion from a diagnostic 3DCT image and respiratory data. The goal is to enable radiologists to delineate target volumes and organs at risk, as well as perform dose calculations on these dynamic synthetic images. This method would reduce the need for a 4DCT acquisition, thereby reducing the patient’s radiation exposure
Kozlova, Olga. „Apprentissage par renforcement hiérarchique et factorisé“. Phd thesis, Université Pierre et Marie Curie - Paris VI, 2010. http://tel.archives-ouvertes.fr/tel-00632968.
Der volle Inhalt der QuelleKlein, François. „Contrôle d'un Système Multi-Agents Réactif par Modélisation et Apprentissage de sa Dynamique Globale“. Phd thesis, Université Nancy II, 2009. http://tel.archives-ouvertes.fr/tel-00432354.
Der volle Inhalt der QuelleAuclair, Etienne. „Réseau bayésien dynamique étiqueté : cadre et apprentissage de structure pour application aux réseaux écologiques“. Thesis, Toulouse 3, 2019. http://www.theses.fr/2019TOU30002.
Der volle Inhalt der QuelleAn ecological network represents the interactions between living species within an ecosystem. The knowledge of the structure of such a network is an important challenge in the field of ecology.This task can be realized by inference methods : a set of methods that uses ecological observations data (species abundance, presence or absence of species...) in order to learn the interactions mathematically, by the exploitation of the effect of these interactions on the observed data.This thesis describes a case where the ecological data we dispose of are only data of presence/absence of species observed at different moments. The goal is to develop a method that exploits those kind of data in order to learn the interaction between these species. The main difficulty is that binary variables carry little information. Expert knowledge on the system is used to help learning the network's structure.We use the framework of dynamic Bayesian network : temporal presence/absence data are modeled as the realization of a set of dynamic random variables whose dependencies are described by an oriented graph. Such a model can be simplified using expert knowledge.This thesis describes a particular model of "labelled" dynamic Bayesian network. In this model, the graph is defined by a small number of different types of interactions that constitute a set of labels attributed to the edges of the graph.This model can describe several phenomena where an information or a perturbation can be propagated by contact (rumour, disease, forest fire....)This model describes the presence or absence probabilities of each species as a function of the number of interactions of each label this species is subject to. This model allows to describe every presence/absence probability of species using a small number of parameters independent from the network's structure. This is the framework used for the modeling of species dynamics within an ecological network : the information propagated is the presence or the absence of a species, knowing the interaction between the species of the network. Then, we describe the processes we use for learning the structure of a labelled dynamic Bayesian network using time series of binary variables. This 'Estimation-Restoration' algorithm alternates two steps : a phase of parameter estimation knowing the structure, and a phase of structure learning knowing the parameters. This last step can be complex. It is done by solving a integer linear programming problem. This allows to use efficient existing tools for solving those kind of problems. Moreover, we can easily add expert knowledge by the form of linear constraints. This process has been used on a particular case study :the observation of arthropods species trapped in experimental fields in the united kingdom. In order to highlight the differences between the different crops, different networks have been learnt. Finally, we compare the learnt network with others, learnt with different learning methods on the same data
Calvelo, Aros Daniel. „Apprentissage de modèles e la dynamique pour l'aide à la décision en monitorage clinique“. Lille 1, 1999. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/1999/50376-1999-351.pdf.
Der volle Inhalt der QuelleFaugloire, Elise. „Approche dynamique de l'apprentissage de coordinations posturales“. Phd thesis, Université Paris Sud - Paris XI, 2005. http://tel.archives-ouvertes.fr/tel-00128845.
Der volle Inhalt der QuelleKomar, John. „Dynamique de l'apprentissage moteur : apprendre loin de l'équilibre“. Rouen, 2013. http://www.theses.fr/2013ROUEL009.
Der volle Inhalt der QuelleBased on the theoretical background of Dynamical Systems Theory, the aim of this thesis is to analyze the temporal dynamics of motor coordination, in relation to the constraints acting on the learner. Specifically, this work investigates the learning process of arm-leg coordination in aquatic locomotion, notably in breaststroke swimming, which is a context where natural individual motor behavior is specifically constrained by environmental constraints. An emphasis is placed on the study of the functional rôle of coordination variability and the rôle of manipulating constraints as a way of promoting exploratory activity in order to investigate issues surrounding learning optimization. Through the use of 3-Dimensions video analysis and motion sensors, the arm-leg coordination has been studied based on the oscillations of knee and elbow angles. The stability and the flexibility of the expert pattern of coordination has been highlighted (study 1), as well as the effect of the level of environmental constraints on the expression of neurobiological degeneracy (study 2). The use of verbal instructions as temporary constraints acting on the learner has then been studied through his effect on the temporal dynamics of the coordination and the different search strategies exhibited by learners (studies 3 and 4). Overall, The results tend to show that in a specific environment as the aquatic environment, the to-be-learned pattern of coordination refers to a biomechanically expert coordination. Nevertheless, the qualitative changes during learning operate through periods of metastability, reflecting an active exploration of the perceptual-motor workspace. In addition, manipulating task constraints without prescribing the to-be-learned pattern can be useful in guiding the exploration (i. E. Proscribe what not to do rather than prescribe what to do). These results advocate for the use of a non-linear pedagogical approach that tends to encourage exploratory learning
Marciano, Paul. „L' accession de l'enfant à la Connaissance : psycho-dynamique de l'Epistémophilie“. Montpellier 3, 2006. http://www.theses.fr/2006MON30036.
Der volle Inhalt der QuelleChildren’s access to Knowledge is driven by epistemophilia. Epistemophilia is itself a function of the libidinal stages undergone. This is to say that psychodynamic conceptions constitute our principal system of reference. We have, accordingly, taken up the work of Mr Klein and his successors again, insofar as they sited the point of convergence of a child’s exploratory manoeuvres in the mother’s womb and in the mother herself. Children must, in fact, attempt to answer determining questions concerning their origins, in particular, the time before their birth, their creation and the understanding they may attempt to obtain of their life in the womb and the time thereafter. . . To us, these epistemophilial explorations in children seem to be driven by their combined desire and fear to confront their parents’ disillusionment, or even hatred, which, moreover, may be provoked to better assess its measure. However, more often than not, the determination to pacify prevails, thanks to this co-epistemophilia which, for parents as for children, amounts to recognising oneself in the other and the other in oneself. Thus Knowledge could essentially even be considered Sacred. Knowledge could encourage a child’s acceptance within the human community. . . Finally, our study material has been compiled through the clinical observation of children presenting cognitive difficulties, coupled or not with failures in school, who were monitored during the course of consultations with a doctor or treatment in hospital. We have therefore endeavoured this time to put epistemophobia, in its psychodynamic sense, back in context. Finally, we have attempted to suggest a few guiding principals for the reimbursement of medical expenses
Lee, Jong-Han. „Dynamique des formes de coordination interentreprises et sa pluralité“. Paris 10, 2001. http://www.theses.fr/2001PA100174.
Der volle Inhalt der QuelleThe subject of this thesis focuses on a dynamic analysis of forms of inter-firm coordination. It shows first the insufficiency of the standard economic theory to study the plurality of these forms of coordination. In the standard economic theory, the transaction cost theory and the incomplete contract theory in particular, the plurality is systematically reduced to a binary choice logique (make or buy logic) : market or organization. Our thesis demonstrates that the market and the organization are not mutually exclusive alternative coordination forms. Their mechanism of coordination is not directly comarable insofar as the coordination by market is achieved in evolutionary manner while the coordination in formal organisation is achieved by intentional plans. The time dimension is different in two cases. In addition, the hypothesis of the substantial rationality always reduce interpersonal interaction to merchant, purely cognitive calculations, all the real dynamics becoming thus a mental dynamics anticipated from the beginning of transaction. This thesis proposes then to study the dynamics of various forms of coordination by means of multi-agent simulation method. This method integrates the bounded rationality of agents and shows the dynamics of learning in inter-firm relationship. By taking « les modèles d'entreprise » developped by Eymard-Duvernay as our theoretical foundations, we integrate there a incentive system and a information structure to study dynamics in the inter-firm relationship. Our results of analysis obtained by multi-agent simulation demontrate well the diversity of forms of coordination
Lancia, Leonardo. „Dynamique non linéaire de la perception de la parole“. Aix-Marseille 1, 2009. http://www.theses.fr/2009AIX10007.
Der volle Inhalt der QuelleNemesin, Valérian. „Apprentissage non-supervisé dans les modèles linéaires gaussiens. Application à la biométrie dynamique de l’iris“. Thesis, Ecole centrale de Marseille, 2014. http://www.theses.fr/2014ECDM0006/document.
Der volle Inhalt der QuelleThe family of Kalman filter model allows to estimate the states of a dynamical system from a set of observations. Despite a simple model, these filters are used in a large field of applications: Radar, vision and communications. The success is mainly based on the existence of exact smoothing or filtering algorithms, \ie linear to the number of observations and which minimize the mean square error. In this thesis, we are concerned about the pairwise Kalman filter. This filter adds from the orignal model, new interactions between hidden states and obervations while keeping exact algorithms in the case of linear and Gaussian models. We studied particularly the problem of the unsupervised and robust estimation of a pairwise Kalman filter parameters from a limited set of observations. The manuscript describes several learning algorithms by the estimation of the likelihood maximum according to EM (\textit{Expectation-Maximization}) principle. These original algorithms allow to embed a-priori constraints on studied system parameters, like a knowledge about physical or sensors. These constrained systems reduce the ambiguity, linked to identifiability issue of the pairwise Kalman filter during the parameter estimation. They allow also to limit the number of local maxima of likelihood function with the reduction of the dimension of search space and avoid sometime the trapping of EM algorithm. It is important to note that all proposed algorithm of this manuscrit can be applied to the original Kalman filter, as a particular pairwise Kalman filter. All algorithm are made robust by the propagation of square root matrices instead of the covariance matrices, which allows to limit the numerical issues, linked to the loses of symetry or positivity of these matrices. These algorithm are finally evaluated and compared in the case of an iris biometry application from video sequences. Pupil tracking is used to enroll and recognize in real-time a person thanks to its iris-code
Mondou, Damien. „Gestion adaptative des contenus numériques : proposition d’un framework générique par apprentissage et re-scénarisation dynamique“. Thesis, La Rochelle, 2019. http://www.theses.fr/2019LAROS029.
Der volle Inhalt der QuelleThis thesis aims to propose an architecture that addresses the design, supervision, management and adaptation of an interactive experience. We therefore propose a complete framework to facilitate the modeling phase of an interactive system and guarantee sufficient flexibility to achieve the objectives of complexity, scalability, adaptability and improvement through automatic learning. For this purpose, the formal model, CIT, based on two layers of description was introduced. The dynamic supervision process consists in controlling the interactive experience with regard to the formal model, based on networks of timed input/output automata. Two softwares, CELTIC (Common Editor for Location Time Interaction and Content) and EDAIN (Execution Driver based on Artificial INtelligence), implementing the CIT model and the activity supervision engine respectively, were developed during this thesis
Gelly, Sylvain. „Une contribution à l'apprentissage par renforcement : application au Computer Go“. Paris 11, 2007. http://www.theses.fr/2007PA112227.
Der volle Inhalt der QuelleReinforcement Learning (RL) is at the interface of control theory, supervised and unsupervised learning, optimization and cognitive sciences. While RL addresses many objectives with major economic impact, it raises deep theoretical and practical difficulties. This thesis brings some contributions to RL, mainly on three axis. The first axis corresponds to environment modeling, i. E. Learning the transition function between two time steps. Factored approaches give an efficiently framework for the learning and use of this model. The Bayesian Networks are a tool to represent such a model, and this work brings new learning criterion, either in parametric learning (conditional probabilities) and non parametric (structure). The second axis is a study in continuous space and action RL, thanks to the dynamic programming algorithm. This analysis tackles three fundamental steps: optimization (action choice from the value function), supervised learning (regression) of the value function and choice of the learning examples (active learning). The third axis tackles the applicative domain of the game of Go, as a high dimensional discrete control problem, one of the greatest challenge in Machine Learning. The presented algorithms with their improvements made the resulting program, MoGo, win numerous international competitions, becoming for example the first go program playing at an amateur dan level on 9x9
Pina, Stranger Alvaro. „Apprentissage collectif à l’échelle inter-organisationnelle : Le cas des entrepreneurs en biotechnologie“. Paris 9, 2011. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=2011PA090066.
Der volle Inhalt der QuelleSurvival and professional performance of biotechnology entrepreneurs depend on their ability to capitalize knowledge collectively, i. E. To evaluate, validate and control this knowledge. This PhD dissertation examines the social mechanism of collective learning that reflects, at the inter-organization level, this collective work. We use a micro-political approach in which value and appropriateness of knowledge is defined by authority relationships and social criteria that actors use to manage these relationships. We show that the heterogeneity of sectors involved in the biotechnology industry and the absence of formal interdependencies among entrepreneurs lead to a controversy on the legitimacy of epistemic authorities. We describe this controversy by looking at the definitions of the situation (identity, rules and representatives of the authority) of entrepreneurs who do not share de same knowledge claims. Results identify a polarization movement where different communities seek to impose their respective definition of the situation. This polarization reduces the effectiveness of collective learning because it promotes the creation of rigid social boundaries between these epistemic communities. To mitigate the negative effects of polarization, actors participate in various specific integration processes: they build social niches, they coordinate at the level of regional clusters and they personalize their relationships with venture capitalists. Each integration process is characterized by a form of relational proximity that allows actors to articulate their epistemic claims and to resolve the conflicts associated with the construction of consensus on the legitimacy of their epistemic authorities
Qian, Xiaotong. „Apprentissage non supervisé pour l'analyse de données dynamiques et multi-vues : Application à l'étude des mécanismes cognitifs et linguistiques dans la production de textes humains“. Electronic Thesis or Diss., CY Cergy Paris Université, 2024. http://www.theses.fr/2024CYUN1320.
Der volle Inhalt der QuelleThis thesis, funded by the ANR ProTEXT project, is an interdisciplinary project that investigates the dynamic processes involved in text production from both linguistic and cognitive perspectives. It focuses on analyzing "bursts of writing", i.e. text segments produced between pauses, and understanding how these bursts, pauses and revisions reflect cognitive and linguistic mechanisms in text production. The aim is to apply unsupervised learning techniques to analyse multivariate data with complex spatial and temporal structures. The data has three main characteristics : Multi-view - each element can be described from different perspectives (linguistic structures, statistical properties and semantic content); Heterogeneous - data attributes vary widely across different views (textual information and numerical values, etc.); Dynamic - each burst is associated with a specific moment in time, allowing analysis of how writing patterns evolve across multiple documents created at different time.This thesis firstly proposes a new clustering framework called HistStream which adapts to static and dynamic data using histogram models based on Wasserstein distance. The process involves applying a clustering algorithm to each window, then merging clusters with similar distributions by their Wasserstein barycenter. This allows the model to be continually updated, while minimizing the computational cost. A series of experiments on artificial and real datasets has validated this approach, demonstrating its adaptability and efficiency in handling complex, high-dimensional data while reducing computing time compared with existing approaches.For multi-view clustering, this thesis proposes two approaches: BCmvlearn for static datasets and IMBC for dynamic environments. The barycentric coordinate (BC) representation is central to both. BCmvlearn builds on the RMKMC model by automatically updating the importance of views. It projects data points across views into a BC subspace, determines positions based on similarity to support points, and optimises a common clustering structure. Iterative updating of cluster centres, assignments and view weights maintains computational efficiency through sparse BC representations. IMBC, inspired by the IMSC model, dynamically integrates new data views by updating a fixed number of basic BC representations and using them to compute a consensus representation that adapts to new views without losing information, while reducing time and space complexity. Extensive experiments on real-world multi-view datasets validate these approaches. The results show superior clustering performance compared to state-of-the-art algorithms, achieving high clustering quality at low computational cost. BCmvlearn and IMBC also effectively handle multimodal datasets by using appropriate distance metrics for each modality.In the final chapter of this thesis, the proposed approaches have been applied to pre-processed Pro-TEXT datasets (including multi-view extraction, embedding, and standardization) to cluster "textual burst" and investigate the characteristics of the obtained clusters in relation to the duration of the following pauses. The results have been compared with other state-of-the-art algorithms and the proposed approaches provide flexible, efficient and robust solutions. The results of the theoretical evaluation are reviewed by psychological and linguistic experts from the Pro-TEXT project, providing insights that will guide future developments in their fields
Davidovici, Myriam. „Evolution de la déréglementation dans l'industrie gazière britannique : approche micro-économique en termes de dynamique d'apprentissage institutionnel“. Paris 9, 1997. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1997PA090048.
Der volle Inhalt der QuelleThe study of the deregulation of the british gas industry led us to introduce the concept of institutional dynamics in order to understand the evolution of the regulatory framework together with the development of competition. The modelling of the institutional dynamics using a model based on system dynamics theory enables to analyze the process of deregulation, I. E. The transition from the regulation of a monopoly to the regulation of competition. This research enables in particular: to articulate the microeconomic behaviours of economic, regulatory and political actors and to reconstruct the macroeconomic evolution of market shares; to suggest a new way of modelling competition in terms of entry and exit flows of firms; to consider the learning of the gas regulator and its lag to adjust the regulation as part of the institutional dynamics; to endogeneize the evolutions of the legal framework
Blais, Laurent-Bernard. „Analyse objective de deux techniques de projection en judo : seoi͏̈ nage et uchi mata de la réalité mécanique aux applications pédagogiques“. Poitiers, 2004. http://www.theses.fr/2004POIT2316.
Der volle Inhalt der QuelleThrough this work, we want to support the exchanges between sporting people and university research people, and we want to give to our work direct applications in term of formation and training. Beyond an intuitive approach based on empirical knowledge of the judo activity, we want to objectively understand the reality of the judo throw, from an analysis of the external and internal mechanical parameters. In the first part, we explain our method of research which tends to go beyond a reducing approach of considering the athlete in his complexity and to measure its segmentary parameters, by associating dynamographic and cinematographic measuring tools. In a second part, we present the results of the study carried out in collaboration with French champions, who allowed us to identify clearly common elements, constituting as many rules of action, whose acquisition by the athletes prove to be essential to realize a good movement. In the last part, we present the results of the calculation of the articular efforts of an athlete, carrying out a judo throw on an instrumented ergometer, like its total energy expenditure, for each phase of the movement or for each segmentary contribution
Bichindaritz, Isabelle. „Apprentissage de concepts dans une mémoire dynamique : raisonnement à partir de cas adaptable à la tâche cognitive“. Paris 5, 1994. http://www.theses.fr/1994PA05S004.
Der volle Inhalt der QuelleAllard, Frédérique. „La dynamique de l'intégration organisationnelle : approche constructiviste et étude de cas“. Toulouse 1, 1999. http://www.theses.fr/1999TOU10015.
Der volle Inhalt der QuelleHow is organisational integration produced? What are the forces which may affect its processes of production? This is the central question of this research. Based on effective coordination, it deals with solving the concrete problems of interdependence or coherence faced by actors. It thus explores the structuration of the common referential - the key condition of collective activity - but it also explores manifestations of differentiation which hinder the concretisation of coordination. The examination of Lawrence and Lorsch's original model results from a double reintegration: that of the constructed nature of social reality to understand its implications on those phenomena studied; that of the reciprocal influences between those processes analysed and their context to understand the effects on their development, their contents or their result. The objective is to grasp the meaning and the impact of organisational integration in the context of the decompartmentalised firm. The case study carried out to this end highlights the usefulness of this approach in describing and interpreting concrete situations of coordination. It particularly emphasises the effects of structuring the common referential on the learning processes and the development of competencies deployed in these situations. At the same time, it underscores the recurrent need to consolidate the integrative dynamic. The scheme of action capable of responding to this need results from the explicitation of these learning effects of coordination. This means of activating organisational integration targets the redundancy of functions. It constitutes the practical synthesis of the lessons of the case study
Shimada, Sakura. „L'apprentissage intergénérationnel dans la dynamique sratégique de l'entreprise : comparaison France-Japon“. Thesis, Paris 9, 2014. http://www.theses.fr/2014PA090072.
Der volle Inhalt der QuelleThis thesis is a comparative study of the relationships between intergenerational learning and the firm’s strategic dynamic, lead in France and Japan. The conceptual framework builds on the literature regarding generation, learning and dynamic capabilities. A qualitative multi-case study was conducted in France and Japan and fourteen cases of intergenerational learning were analyzed. The empirical results show that the relationships between intergenerational learning and the dynamic of the firm’s strategy vary between the state of stability and change. The cultural contexts influence the creation of the generations and intergenerational learning practices. These results highlight the role of organizations in the creation of generations, the strategic issue of intergenerational learning and give insights about the cultural embeddedness of managerial practices
Hoteit, Sanaa. „Enseignement - apprentissage du français au sud du Liban : didactique contextualisée et intégration dans une dynamique culturelle francophone ?“ Phd thesis, Université Rennes 2, 2010. http://tel.archives-ouvertes.fr/tel-00566397.
Der volle Inhalt der QuelleAlami, Réda. „Bandits à Mémoire pour la prise de décision en environnement dynamique. Application à l'optimisation des réseaux de télécommunications“. Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG063.
Der volle Inhalt der QuelleIn this PhD thesis, we study the non-stationary multi-armed bandit problem where the non-stationarity behavior of the environment is characterized by several abrupt changes called "change-points". We propose Memory Bandits: a combination between an algorithm for the stochastic multi-armed bandit and the Bayesian Online Change-Point Detector (BOCPD). The analysis of the latter has always been an open problem in the statistical and sequential learning theory community. For this reason, we derive a variant of the Bayesian Online Change-point detector which is easier to mathematically analyze in term of false alarm rateand detection delay (which are the most common criteria for online change-point detection). Then, we introduce the decentralized exploration problem in the multi-armed bandit paradigm where a set of players collaborate to identify the best arm by asynchronously interacting with the same stochastic environment. We propose a first generic solution called decentralized elimination: which uses any best arm identification algorithm as a subroutine with the guar-antee that the algorithm ensures privacy, with a low communication cost. Finally, we perform an evaluation of the multi-armed bandit strategies in two different context of telecommunication networks. First, in LoRaWAN (Long Range Wide Area Network) context, we propose to use multi-armed bandit algorithms instead of the default algorithm ADR (Adaptive Data Rate) in order to minimize the energy consumption and the packet losses of end-devices. Then, in a IEEE 802.15.4-TSCH context, we perform an evaluation of 9 multi-armed bandit algorithms in order to select the ones that choose high-performance channels, using data collected through the FIT IoT-LAB platform. The performance evaluation suggests that our proposal can significantly improve the packet delivery ratio compared to the default TSCH operation, thereby increasing the reliability and the energy efficiency of the transmissions
Liu, Zongyi. „Self-Adaptive Bandwidth Control for Balanced QoS and Energy Aware Optimization in Wireless Sensor Network“. Thesis, Toulouse, INSA, 2017. http://www.theses.fr/2017ISAT0034/document.
Der volle Inhalt der QuelleIn the Wireless Multimedia Sensor Networks (WMSNs) field, highly saturated flow increases the probability of collision and congestion in data transmission which dramatically degrade the performance of Quality of Service (QoS). Multi-channels deployment technique is often applied to parallel transmission for QoS guarantee. However, how to make trade-off between QoS requirement and energy efficiency is a challenges to energy-constrained WMSNs. Theoretical analysis of MAC layer and PHY layer structure based on IEEE 802.15.4 standard, aim to study on the cross-layer analytical model in order to provide stronger understanding on the relationship between sensor network parameters and performance, pave the way for new enhancements in succedent multi-channel optimization research. Find effective performance indicator and design efficient performance collection or estimation approach based on the corresponding metrics, which could be used as the parameter input of multi-channel assignment mechanism. Comprehensive dynamically control system is designed for multi-channel assignment task based on light weight and high efficient computation intelligence techniques. We present a fuzzy-based dynamic bandwidth multi-channel assignment mechanism (MCDB_FLS). Cross-layer proactive available bandwidth is estimated as parameters for multi-channel deployment admission control. Reinforcement learning-based approach is proposed for more wisely decision-making in multi- channel allocation mission. Furthermore, fuzzy logic-based bandwidth threshold model provides dynamic optimization on system admission control. Simulations show the MCDB_FLS performs better than benchmark on the metrics of QoS and energy efficiency, achieves the trade-off between energy efficiency and QoS improvement. Finally, we introduce the integration of incremental machine learning approach into multi-channel assignment mechanism with Deep Q Network reinforcement learning method (DQMC). Besides, fully action weight initialization is implemented based on multi-class supervised learning classifier with stacking ensemble approach. DQMC improve the ability of self-adaptive and smart control to learn pattern from different environment of multi-tasks WMSNs
Salaün, Camille. „Apprentissage De Modèles Pour La Commande De La Mobilité Interne En Robotique“. Phd thesis, Université Pierre et Marie Curie - Paris VI, 2010. http://tel.archives-ouvertes.fr/tel-00545534.
Der volle Inhalt der QuelleSoula, Hédi. „Dynamique et plasticité dans les réseaux de neurones à impulsions : étude du couplage temporel réseau / agent / environnement“. Lyon, INSA, 2005. http://theses.insa-lyon.fr/publication/2005ISAL0056/these.pdf.
Der volle Inhalt der QuelleAn «artificial life » approach is conducted in order to assess the neural basis of behaviours. Behaviour is the consequence of a good concordance between the controller, the agent’s sensori-motors capabilities and the environment. Within a dynamical system paradigm, behaviours are viewed as attractors in the perception/action space – derived from the composition of the internal and external dynamics. Since internal dynamics is originated by the neural dynamics, learning behaviours therefore consists on coupling external and internal dynamics by modifying network’s free parameters. We begin by introducing a detailed study of the dynamics of large networks of spiking neurons. In spontaneous mode (i. E. Without any input), these networks have a non trivial functioning. According to the parameters of the weight distribution and provided independence hypotheses, we are able to describe completely the spiking activity. Among other results, a bifurcation is predicted according to a coupling factor (the variance of the distribution). We also show the influence of this parameter on the chaotic dynamics of the network. To learn behaviours, we use a biologically plausible learning paradigm – the Spike-Timing Dependent Plasticity (STDP) that allows us to couple neural and external dynamics. Applying shrewdly this learning law enables the network to remain “at the edge of chaos” which corresponds to an interesting state of activity for learning. In order to validate our approach, we use these networks to control an agent whose task is to avoid obstacles using only the visual flow coming from its linear camera. We detail the results of the learning process for both simulated and real robotics platform
Soula, Hédi Favrel Joel Beslon Guillaume. „Dynamique et plasticité dans les réseaux de neurones à impulsions étude du couplage temporel réseau / agent / environnement /“. Villeurbanne : Doc'INSA, 2005. http://docinsa.insa-lyon.fr/these/pont.php?id=soula.
Der volle Inhalt der QuelleArouna-Hardouin, Julie. „Dynamique de constitution des compétences d'innovation dans une FMN. Le cas Valeo“. Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLX013.
Der volle Inhalt der QuelleThis thesis focuses on the way multinational corporations (MNCs) develop and manage the required competences to sustain their innovation strategy when their market dynamism is shifting towards Asia.The literature presents various models to organize innovation processes globally but does not answer the question of their dynamic constitution based on a given situation.Drawing upon an interactive research conducted within Valeo – a worldwide automotive supplier – this thesis focuses on that dynamic dimension. It sheds light on how (i) China constitutes a disruptive experience for the Western MNC because of the speed and scale of the phenomenon, as well as the context, (ii) the strategy implemented by the MNC in China from Europe has helped to deal with the difficult situation in the short term, but is not the best way to develop the necessary competences locally to enable the local teams to become autonomous.We thus suggest: (i) at the micro level, a new way of designing training programs that involves shifting from a teaching-centered approach to a learning-centered approach, (ii) at the macro level, a trajectory to improve the constitution of R-I-D (Research, Innovation, Development) competences in the global firm, on the one hand in China via the coaching of local trainers and the development of communities of practice, and on the other hand globally via the constitution of an organizational vehicle such as a Corporate University, to address simultaneously learning and talent management issues – both individually & collectively, locally & globally, in-house & in link with the outside world
Duarte-Colardelle, Cheila. „Analyse de la dynamique organisationnelle en temps de crise“. Phd thesis, École Nationale Supérieure des Mines de Paris, 2006. http://pastel.archives-ouvertes.fr/pastel-00005228.
Der volle Inhalt der QuelleTallet, Jessica. „Approche dynamique de la mémoire motrice humaine“. Toulouse 3, 2007. http://www.theses.fr/2007TOU30073.
Der volle Inhalt der QuelleHuman memory can be defined as the capacity to learn new elements, to retain some of them and to forget others. Although it is generally believed as extremely persistent, motor memory does not escape from forgetting. To date, its functioning remains obscure. Accordingly, this work aims to try to better understand how some perceptivo-motor behaviours can persist while some others are forgotten in spite of similar practice and retention conditions. More precisely, we try to identify one or some general principle(s) which would allow predicting one behaviour fate (persistence or forgetting) after its practice. After examining this question with respect to the traditional theories, memory is re-considered in the light of concepts and tools of the Dynamical Patterns Theory. This theory put forth the idea that the stable behaviours already existing in the coordination repertoire before any practice constrain the stabilization of a new required behaviour during practice and its persistence after practice. .
Bonny, Ludovic. „La dynamique innovation - apprentissage dans la transformation des configurations organisationnelles : le cas des fourth party logistics (4PL™)“. Electronic Thesis or Diss., Orléans, 2011. http://www.theses.fr/2011ORLE0509.
Der volle Inhalt der QuelleIn the 1990s, a major change occurred in logistics services. The «traditional» Third Party Logistics(3PL) moved towards a new version, the Fourth Party Logistics (4PL™), which differs from its predecessors by its expertise in design and operational management of supply chains. By focusing on their appearance, we sought to understand the emergence of new organizational configurations in the field of logistics. Originally, we assumed that the innovation - learning dynamic was the main reason for the emergence of 4PL™.To validate or refute this hypothesis, we were interested in relevant theories dealing with innovationand learning. We realized that we lacked a comprehensive theoretical framework that allowed us to discern the influence of innovation - learning dynamic.We found, after an exploratory study and the study of a single case, that the 4PL™ emerged gradually (in the supply chain under consideration) through a process of propagation of combustion involving knowledge and interactions of stakeholders
Bonny, Ludovic. „La dynamique innovation - apprentissage dans la transformation des configurations organisationnelles : le cas des fourth party logistics (4PL™)“. Thesis, Orléans, 2011. http://www.theses.fr/2011ORLE0509.
Der volle Inhalt der QuelleIn the 1990s, a major change occurred in logistics services. The «traditional» Third Party Logistics(3PL) moved towards a new version, the Fourth Party Logistics (4PL™), which differs from its predecessors by its expertise in design and operational management of supply chains. By focusing on their appearance, we sought to understand the emergence of new organizational configurations in the field of logistics. Originally, we assumed that the innovation - learning dynamic was the main reason for the emergence of 4PL™.To validate or refute this hypothesis, we were interested in relevant theories dealing with innovationand learning. We realized that we lacked a comprehensive theoretical framework that allowed us to discern the influence of innovation - learning dynamic.We found, after an exploratory study and the study of a single case, that the 4PL™ emerged gradually (in the supply chain under consideration) through a process of propagation of combustion involving knowledge and interactions of stakeholders
Rana, Aakanksha. „Analyse d'images haute gamme dynamique“. Electronic Thesis or Diss., Paris, ENST, 2018. http://www.theses.fr/2018ENST0015.
Der volle Inhalt der QuelleHigh Dynamic Range (HDR) imaging enables to capture a wider dynamic range and color gamut, thus enabling us to draw on subtle, yet discriminating details present both in the extremely dark and bright areas of a scene. Such property is of potential interest for computer vision algorithms where performance degrades substantially when the scenes are captured using traditional low dynamic range (LDR) imagery. While such algorithms have been exhaustively designed using traditional LDR images, little work has been done so far in contex of HDR content. In this thesis, we present the quantitative and qualitative analysis of HDR imagery for such task-specific algorithms. This thesis begins by identifying the most natural and important questions of using HDR content for low-level feature extraction task, which is of fundamental importance for many high-level applications such as stereo vision, localization, matching and retrieval. By conducting a performance evaluation study, we demonstrate how different HDR-based modalities enhance algorithms performance with respect to LDR on a proposed dataset. However, we observe that none of them can optimally to do so across all the scenes. To examine this sub-optimality, we investigate the importance of task-specific objectives for designing optimal modalities through an experimental study. Based on the insights, we attempt to surpass this sub-optimality by designing task-specific HDR tone-mapping operators (TMOs). In this thesis, we propose three learning based methodologies aimed at optimal mapping of HDR content to enhance the efficiency of local features extraction at each stage namely, detection, description and final matching
Pierrot, David. „Détection dynamique des intrusions dans les systèmes informatiques“. Thesis, Lyon, 2018. http://www.theses.fr/2018LYSE2077.
Der volle Inhalt der QuelleThe expansion and democratization of the digital world coupled with the effect of the Internet globalization, has allowed individuals, countries, states and companies to interconnect and interact at incidence levels never previously imagined. Cybercrime, in turn, is unfortunately one the negative aspects of this rapid global interconnection expansion. We often find malicious individuals and/or groups aiming to undermine the integrity of Information Systems for either financial gain or to serve a cause. The consequences of an intrusion can be problematic for the existence of a company or an organization. The impacts are synonymous with financial loss, brand image degradation and lack of seriousness. The detection of an intrusion is not an end in itself, the reduction of the delta detection-reaction has become a priority. The different existing solutions prove to be cumbersome to set up. Research has identified more efficient data mining methods, but integration into an information system remains difficult. Capturing and converting protected resource data does not allow detection within acceptable time frames. Our contribution helps to detect intrusions. Protect us against Firewall events which reduces the need for computing power while limiting the knowledge of the information system by intrusion detectors. We propose an approach taking into account the technical aspects by the use of a hybrid method of data mining but also the functional aspects. The addition of these two aspects is grouped into four phases. The first phase is to visualize and identify network activities. The second phase concerns the detection of abnormal activities using data mining methods on the source of the flow but also on the targeted assets. The third and fourth phases use the results of a risk analysis and a safety verification technique to prioritize the actions to be carried out. All these points give a general vision on the hygiene of the information system but also a direction on monitoring and corrections to be made.The approach developed to a prototype named D113. This prototype, tested on a platform of experimentation in two architectures of different size made it possible to validate our orientations and approaches. The results obtained are positive but perfectible. Prospects have been defined in this direction
Guechtouli, Widad. „Dynamique du processus de transfert de connaissances au sein d'une communauté de pratique : une modélisation multi-agents“. Aix-Marseille 3, 2009. http://www.theses.fr/2009AIX32004.
Der volle Inhalt der QuelleThe objective of this thesis is to study the process of knowledge transfer in the particular context of a community of practice. This type of community can be defined as a group which emerges from the will of certain individuals to work together for the development of a common practice. A community of practice is composed of a core made up of individuals that are expert in the practice of the community, while new comers are located at its periphery. We approach the process of knowledge transfer through communication structures and we try to determine which structures should be used in this type of communities in order to support such a process. In order to do that, we use agent-based simulations; we create artificial societies having the properties of communities of practices, where we study two types of knowledge transfer: direct transfer (where knowledge is transmitted directly, without intermediary) and indirect transfer (where knowledge is transferred by means of intermediate mediums). Results show that the structure of a community of practice as well as the part played by the new comers in this type of communities have an important influence on the process of direct knowledge transfer, but not on the process of indirect transfer of knowledge. Finally, these results enable us to formulate some policy design recommendations as for the management of both types of knowledge transfer within a community of practice
Musca, Geneviève. „La dynamique des compétences et des capacités dans l'organisation : le cas d'équipes en charge de projets innovants“. Paris 12, 2005. http://www.theses.fr/2005PA123014.
Der volle Inhalt der QuelleThis research focuses on understanding and explaining what are the competencies and capabilities conditions and processes of development in innovating project teams, in a context of uncertainty. This dynamic is viewed as a process of collective sensemaking (Weick, 1979, 1995). This research is exploratory and abductive, with a moderately positivist approach. We accomplished a longitudinal case study of an Internet project with two of its sub-units. Our empirical results suggest that competences dynamic is a variegated process, with great local differences between project teams and phases. From these insights and litterature, we induced propositions linking co-localisation, team heterogeneity, “psychological safety”, hybrid structure, experimentations with a group of two or three, with competencies and capabilities development
Poisson, Émilie. „Architecture et apprentissage d'un système hybride neuro-markovien pour la reconnaissance de l'écriture manuscrite en-ligne“. Nantes, 2005. http://www.theses.fr/2005NANT2082.
Der volle Inhalt der QuelleThis thesis deals with the study, the conception, the development and the test of an online unconstrained handwriting word recognition system for an omni-writer application. The proposed system is based on a hybrid architecture including on the one hand, a neural convolutional network (TDNN and/or SDNN), and on the other hand Hidden Markov Models (HMM). The neural network has a global vision and works at the character level, while the HMM works on a more local description and allows the extension from the character level to the word level. The system was first dedicated for processing isolated characters (digits, lowercase letters, uppercase letters). This architecture has been optimized in terms of performances and size. The second part of this work concerns the extension to the word level. In this case, we have defined a global training scheme directly at the word level. It allows to insure the global convergence of the system. It relies on an objective function that combines two main criteria: one based on generative models (typically by maximum likelihood estimation) and the second one based on discriminant criteria (maximum mutual information). Several results are presented on MNIST, IRONOFF and UNIPEN databases. They show the influence of the main parameters of the system, either in terms of topologies, information sources, and training models (number of states, criteria weighting, duration)
Boussair, Hakim. „Le processus d'apprentissage organisationnel : introduction d'une innovation managériale et dynamique de réseaux“. Paris 9, 2010. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=2010PA090007.
Der volle Inhalt der QuelleAtchy-Dalama, Patrice. „Approche dynamique de l'apprentissage : pratique variable et rôle des informations sensorielles“. Toulouse 3, 2005. http://www.theses.fr/2005TOU30168.
Der volle Inhalt der QuelleIn general, the process of learning implies that a pattern to-be-learned is integrated into an initial repertory. To gain further insight into this problematic of integration, we have developed two lines of research. The first one identifies the principles underlying the learning of several bimanual coordination patterns. Thus, we studied the evolution of the repertory due to such variable practice. We observed that the repertory constraints and structures the learning process following a symmetry conservation principle. The second axe concerns the mechanisms underlying the integration of a new coordination pattern. We studied the relation between the sensory consequences, the motor commands and the to-be-learned pattern. By an original used of the degree of asymmetry between the coordinated limbs, we showed that regardless of the motor outflow command, leaning is based on the sensory consequences related to the pattern to be learned. Set at two distinct levels of analysis (principle and mechanism), this two experiments are discussed from a dynamical systems perspective