Зміст
Добірка наукової літератури з теми "Sélection séquentielle"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Sélection séquentielle".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Статті в журналах з теми "Sélection séquentielle"
Pronzato, Luc. "Sélection séquentielle de conditions expérimentales non contrôlées." Journal Européen des Systèmes Automatisés 40, no. 2 (February 2006): 197–210. http://dx.doi.org/10.3166/jesa.40.197-210.
Повний текст джерелаNOIROT, V., I. BOUVAREL, B. BARRIER-GUILLOT, J. CASTAING, J. L. ZWICK, and M. PICARD. "Céréales entières pour les poulets de chair : le retour ?" INRAE Productions Animales 11, no. 5 (December 6, 1998): 349–57. http://dx.doi.org/10.20870/productions-animales.1998.11.5.3963.
Повний текст джерелаSalvia-Castellvi, M., C. Scholer, and L. Hoffmann. "Comparaison de différents protocoles de spéciation séquentielle du phosphore dans des sédiments de rivière." Revue des sciences de l'eau 15, no. 1 (April 12, 2005): 223–33. http://dx.doi.org/10.7202/705448ar.
Повний текст джерелаJAMMES, H., and J. P. RENARD. "Epigénétique et construction du phénotype, un enjeu pour les productions animales ?" INRAE Productions Animales 23, no. 1 (February 8, 2010): 23–42. http://dx.doi.org/10.20870/productions-animales.2010.23.1.3283.
Повний текст джерелаJOVANOVIC, B., O. DANEL, I. BAUDIN, J. REUNGOAT, L. GUEY, J. F. ROBIN, and A. BREHANT. "Évaluation d’un procédé d’affinage sur charbon actif en grains à l’échelle pilote pour le traitement d’une sélection de micropolluants peu adsorbables." Techniques Sciences Méthodes, no. 11 (November 20, 2020): 41–62. http://dx.doi.org/10.36904/tsm/202011041.
Повний текст джерелаДисертації з теми "Sélection séquentielle"
Caelen, Olivier. "Sélection séquentielle en environnement aléatoire appliquée à l'apprentissage supervisé." Doctoral thesis, Universite Libre de Bruxelles, 2009. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/210265.
Повний текст джерелаDans un premier cas, les tests viseront à maximiser la somme des gains collectés. Un juste compromis doit alors être trouvé entre l'exploitation et l'exploration. Ce problème est couramment dénommé dans la littérature scientifique "multi-armed bandit problem".
Dans un second cas, un nombre de sélections maximal est imposé et l'objectif consistera à répartir ces sélections de façon à augmenter les chances de trouver l'alternative présentant le gain moyen le plus élevé. Ce deuxième problème est couramment repris dans la littérature scientifique sous l'appellation "selecting the best".
La sélection de type gloutonne joue un rôle important dans la résolution de ces problèmes de décision et opère en choisissant l'alternative qui s'est jusqu'ici montrée optimale. Or, la nature généralement aléatoire de l'environnement rend incertains les résultats d'une telle sélection.
Dans cette thèse, nous introduisons une nouvelle quantité, appelée le "gain espéré d'une action gloutonne". Sur base de quelques propriétés de cette quantité, de nouveaux algorithmes permettant de résoudre les deux problèmes décisionnels précités seront proposés.
Une attention particulière sera ici prêtée à l'application des techniques présentées au domaine de la sélection de modèles en l'apprentissage artificiel supervisé.
La collaboration avec le service d'anesthésie de l'Hôpital Erasme nous a permis d'appliquer les algorithmes proposés à des données réelles, provenant du milieu médical. Nous avons également développé un système d'aide à la décision dont un prototype a déjà été testé en conditions réelles sur un échantillon restreint de patients.
Doctorat en Sciences
info:eu-repo/semantics/nonPublished
Stoltz, Gilles. "Information incomplète et regret interne en prédiction de suites inidividuelles." Paris 11, 2005. https://tel.archives-ouvertes.fr/tel-00009759.
Повний текст джерелаThis thesis takes place within the theory of prediction of individual sequences. The latter avoids any modelling of the data and aims at providing some techniques of robust prediction and discuss their possibilities, limitations, and difficulties. It considers issues arising from the machine learning as well as from the game-theory communities, and these are dealt with thanks to statistical techniques, including martingale concentration inequalities and minimax lower bound techniques. The obtained results consist, among others, in external and internal regret minimizing strategies for label-efficient prediction or in games with partial monitoring. Such strategies are valuable for the on-line pricing problem or for on-line bandwidth allocation. We then focus on internal regret for general convex losses. We consider first the case of on-line portfolio selection, for which simulations on real data are provided, and generalize later the results to show how players can learn correlated equilibria in games with compact sets of strategies
Stoltz, Gilles. "Information incomplète et regret interne en prédiction de suites individuelles." Phd thesis, Université Paris Sud - Paris XI, 2005. http://tel.archives-ouvertes.fr/tel-00009759.
Повний текст джерелаJuniarta, Nyoman. "Fouille de données complexes et biclustering avec l'analyse formelle de concepts." Electronic Thesis or Diss., Université de Lorraine, 2019. http://www.theses.fr/2019LORR0199.
Повний текст джерелаKnowledge discovery in database (KDD) is a process which is applied to possibly large volumes of data for discovering patterns which can be significant and useful. In this thesis, we are interested in data transformation and data mining in knowledge discovery applied to complex data, and we present several experiments related to different approaches and different data types. The first part of this thesis focuses on the task of biclustering using formal concept analysis (FCA) and pattern structures. FCA is naturally related to biclustering, where the objective is to simultaneously group rows and columns which verify some regularities. Related to FCA, pattern structures are its generalizations which work on more complex data. Partition pattern structures were proposed to discover constant-column biclustering, while interval pattern structures were studied in similar-column biclustering. Here we extend these approaches to enumerate other types of biclusters: additive, multiplicative, order-preserving, and coherent-sign-changes. The second part of this thesis focuses on two experiments in mining complex data. First, we present a contribution related to the CrossCult project, where we analyze a dataset of visitor trajectories in a museum. We apply sequence clustering and FCA-based sequential pattern mining to discover patterns in the dataset and to classify these trajectories. This analysis can be used within CrossCult project to build recommendation systems for future visitors. Second, we present our work related to the task of antibacterial drug discovery. The dataset for this task is generally a numerical matrix with molecules as rows and features/attributes as columns. The huge number of features makes it more complex for any classifier to perform molecule classification. Here we study a feature selection approach based on log-linear analysis which discovers associations among features. As a synthesis, this thesis presents a series of different experiments in the mining of complex real-world data
Bonidal, Rémi. "Sélection de modèle par chemin de régularisation pour les machines à vecteurs support à coût quadratique." Thesis, Université de Lorraine, 2013. http://www.theses.fr/2013LORR0066/document.
Повний текст джерелаModel selection is of major interest in statistical learning. In this document, we introduce model selection methods for bi-class and multi-class support vector machines. We focus on quadratic loss machines, i.e., machines for which the empirical term of the objective function of the learning problem is a quadratic form. For SVMs, model selection consists in finding the optimal value of the regularization coefficient and choosing an appropriate kernel (or the values of its parameters). The proposed methods use path-following techniques in combination with new model selection criteria. This document is structured around three main contributions. The first one is a method performing model selection through the use of the regularization path for the l2-SVM. In this framework, we introduce new approximations of the generalization error. The second main contribution is the extension of the first one to the multi-category setting, more precisely the M-SVM². This study led us to derive a new M-SVM, the least squares M-SVM. Additionally, we present new model selection criteria for the M-SVM introduced by Lee, Lin and Wahba (and thus the M-SVM²). The third main contribution deals with the optimization of the values of the kernel parameters. Our method makes use of the principle of kernel-target alignment with centered kernels. It extends it through the introduction of a regularization term. Experimental validation of these methods was performed on classical benchmark data, toy data and real-world data
Fekom, Mathilde. "Sequential Resource Allocation for network diffusion control." Thesis, université Paris-Saclay, 2021. http://www.theses.fr/2021UPASM008.
Повний текст джерелаThe dynamic containment of an undesired network diffusion process, such as an epidemic, requires a decision maker (DM) to be able to respond to its evo- lution by taking the right control actions at the right moments. This task can be seen as managing the alloca- tion of a limited amount of resources to the graph nodes, with the objective to reduce the effects of the process.In this thesis we extend the Dynamic Resource Alloca- tion (DRA) problem and propose a multi-round dynamic control framework, which we realize through two derived models: the Restricted and the Sequential DRA (RDRA, SDRA). Contrary to the standard full-information and full-access DRA considerations, these new models take into account possible access restrictions regarding the the available information about the network and/or the ability to act on its nodes. At each intervention round, the DM has limited access to information related to a fraction of the nodes, and is also gaining access to act on them in a sequential fashion. The latter sequential as- pect in the decision process offers a completely new per- spective to the dynamic diffusion process control, making this work the first to cast the dynamic control problem as a series of specially designed sequential selection pro- cesses.In the Sequential Selection Problem (SSP), immediate and irrevocable decisions need to be made by the DM as candidate items arrive randomly and get examined for one of the limited selection slots available. For the needs of network diffusion control, what we propose translatesinto selecting the right nodes to allocate the control re- sources in a multi-round sequential process. However, standard SSP variants, such as the very well-known sec- retary problem, begin with an empty selection set (cold- start) and perform the selection process once over a single candidate set (single-round). These two limita- tions are addressed in this thesis. First, we introduce the novel Warm-starting SSP setting that considers hav- ing at hand a reference set, which is a set of previously selected items of a given quality, and tries to update optimally that set while examining the sequence of ar- riving candidates, constrained by being able to update the assignment to each selection slot (resource) at most once. The Multi-round Sequential Selection Process, the new online-within-online problem, is then introduced as a natural extension of the warm-starting selection.Both rank-based and score-based ob jective functions over the final selection are considered. A cutoff-based approach is proposed for the former, while the optimal strategy based on dynamic thresholding is derived for the latter assuming that the score distribution is known. These strategies are then put in comparison for their efficiency in the traditional selection setting as well as in solving network control problems that motivated this thesis. The generality of the introduced models allow their application to a wide variety of fields and problems; for instance, reoccurring recruiting processes, manage- ment of resources (e.g. beds, staff) in healthcare units, as well as tackling difficult combinatorial problems under constrains, such as the b-diversification problem found in data-stream processing applications (e.g. in robotics)
Prémillieu, Nathanaël. "Améliorer la performance séquentielle à l'ère des processeurs massivement multicœurs." Phd thesis, Université Rennes 1, 2013. http://tel.archives-ouvertes.fr/tel-00914898.
Повний текст джерелаPrémillieu, Nathanaël. "Améliorer la performance séquentielle à l’ère des processeurs massivement multicœurs." Thesis, Rennes 1, 2013. http://www.theses.fr/2013REN1S071/document.
Повний текст джерелаComputers are everywhere and the need for always more computation power has pushed the processor architects to find new ways to increase performance. The today's tendency is to replicate execution core on the same die to parallelize the execution. If it goes on, processors will become manycores featuring hundred to a thousand cores. However, Amdahl's law reminds us that increasing the sequential performance will always be vital to increase global performance. A perfect way to increase sequential performance is to improve how branches are executed because they limit instruction level parallelism. The branch prediction is the most studied solution, its interest greatly depending on its accuracy. In the last years, this accuracy has been continuously improved up to reach a hardly exceeding limit. An other solution is to suppress the branches by replacing them with a construct based on predicated instructions. However, the execution of predicated instructions on out-of-order processors comes up with several problems like the multiple definition problem. This study investigates these two aspects of the branch treatment. The first part is about branch prediction. A way to improve it without increasing the accuracy is to reduce the coast of a branch misprediction. This is possible by exploiting control flow reconvergence and control independence. The work done on the wrong path on instructions common to the two paths is saved to be reused on the correct path. The second part is about predicated instructions. We propose a solution to the multiple definition problem by selectively predicting the predicate values. A selective replay mechanism is used to reduce the cost of a predicate misprediction
Courcoux-Caro, Milan. "Conception optimisée d’antenne pour de la localisation passive de sources acoustiques." Thesis, Brest, École nationale supérieure de techniques avancées Bretagne, 2022. http://www.theses.fr/2022ENTA0001.
Повний текст джерелаThe objective of this thesis work is to propose an approach of array design for the localization of aerial or underwater acoustic sources. First, we will see how to describe the propagation of waves emitted by the sources. Then we will draw up the different methods allowing to estimate the positions of the sources from the measurements acquired by the sensors and from the propagation model. The bibliographic work on the field of acoustic source localization will highlight the importance of the sensors’ positions in the performance of the source position estimators. This will lead to a second bibliographic work on antenna design, and more precisely on the selection of sensor positions. The state of the art on antenna design methods will allow us to propose the following method: a sequential Bayesian data-driven selection. This approach takes into account the information contained in the measurements previously acquired in the pre-designed antenna, in order to select the future sensors. The application of this approach is innovative in the context of acoustic source localization. In a second step, first results realized on synthetic data prove to be promising for the application of this approach in an underwater acoustic source localization context. The analyses provided in this manuscript will allow to judge the relevance of this approach in the tested context, as well as to evaluate and compare the performance of this antenna design with the literature. Finally, we will apply this approach on real data from an experiment set up during the thesis. The propagation environment will be aerial in a closed reverberant room with a large number of available sensors. Acquiring real data will allow, in addition to evaluating the performance of our approach, to provide a new antenna design. This is designed from synthetic data and then applied to real data
Estampes, Ludovic d'. "Traitement statistique des processus alpha-stables : mesures de dépendance et identification des AR stables : tests séquentiels tronqués." Toulouse, INPT, 2003. http://www.theses.fr/2003INPT031H.
Повний текст джерела