Contents
Academic literature on the topic 'Réseau neuronal RBF'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Réseau neuronal RBF.'
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.
Dissertations / Theses on the topic "Réseau neuronal RBF"
Pham, Hoang Anh. "Coordination de systèmes sous-marins autonomes basée sur une méthodologie intégrée dans un environnement Open-source." Electronic Thesis or Diss., Toulon, 2021. http://www.theses.fr/2021TOUL0020.
Full textThis thesis studies the coordination of autonomous underwater robots in the context of coastal seabed exploration or facility inspections. Investigating an integrated methodology, we have created a framework to design and simulate low-cost underwater robot controls with different model assumptions of increasing complexity (linear, non-linear, and finally non-linear with uncertainties). By using this framework, we have studied algorithms to solve the problem of formation control, collision avoidance between robots and obstacle avoidance of a group of underwater robots. More precisely, we first consider underwater robot models as linear systems of simple integrator type, from which we can build a formation controller using consensus and avoidance algorithms. We then extend these algorithms for the nonlinear dynamic model of a Bluerov robot in an iterative design process. Then we have integrated a Radial Basis Function neural network, already proven in convergence and stability, with the algebraic controller to estimate and compensate for uncertainties in the robot model. Finally, we have presented simulation results and real basin tests to validate the proposed concepts. This work also aims to convert a remotely operated ROV into an autonomous ROV-AUV hybrid
Mathivet, Virginie. "Evolution de second ordre et algorithmes évolutionnaires : l'algorithme RBF-Gened." Lyon, INSA, 2007. http://theses.insa-lyon.fr/publication/2007ISAL0042/these.pdf.
Full textSecond order evolution (or indirect selection) corresponds to a situation where the individuals are not only selected on their fitness to an environment, but also on their ability to evolve « better ». Even if such a mechanism seems a priori very interesting in artificial evolution, it is not permitted by the structure of evolutionary algorithms because the evolutionary processes are fixed. Therefore, we propose a new evolutionary algorithm, RBFGene. It includes an intermediate level, the proteom (made of « proteins »), between the phenotype of an individual and its genotype, that allows for changes in the structure of the genome without changing the phenotype. These modifications can thereafter have an influence on later reproductions. We show the existence of an indirect selection in our algorithm, acting on genomes by changing the size of the non coding sequences or the order of the genes
Demian, Vladimir. "Conception et analyse d'algorithmes parallèles pour les réseaux neuronaux de Kohonen et de fonctions à base radiale (RBF)." Lyon 1, 1995. http://www.theses.fr/1995LYO10167.
Full textLiu, Haoran. "Statistical and intelligent methods for default diagnosis and loacalization in a continuous tubular reactor." Phd thesis, INSA de Rouen, 2009. http://tel.archives-ouvertes.fr/tel-00560886.
Full textValencia, Garcia Sara. "Décryptage du réseau neuronal responsable de l’atonie musculaire pendant le sommeil paradoxal chez le rat : création d’un modèle rongeur du RBD (REM sleep Behavior Disorder)." Thesis, Lyon 1, 2014. http://www.theses.fr/2014LYO10324.
Full textA growing number of studies investigate the neuronal network responsible for paradoxical (PS) (or REM) sleep genesis and muscle atonia specific of this sleep state. The aim of this thesis was to characterize at the anatomical and functional levels the populations of neurons involved in generating muscle atonia during PS and their potential failure in REM sleep Behavior Disorder (RBD). For this purpose, we combined a large panel of experimental techniques such as functional neuroanatomy, retrograde tract-tracing, in situ hybridization, polysomnography and irreversible inactivation of genetically-targeted neurons with short-hairpin RNAs introduced in viral adenovectors (AAV-shRNA) in freely moving rats. We thus demonstrated for the first time that, in contrast to the currently admitted hypothesis, the pontine sublaterodorsal nucleus (SLD) is not the PS generator, since genetic inactivation of its glutamatergic neurons or its whole lesion diminish the quantities of but do not eliminate PS. This indicates that the SLD is not sufficient for PS generation. In contrast, our experiments clearly show that the SLD is responsible for muscle atonia because the specific inactivation of its glutamatergic neurons induces an irregular muscle tone concomitant to atypical motor behaviors during PS. In addition, we achieved original data about the location within the ventral medullary reticular formation, and not at spinal levels as often believed, of the glycine/GABA interneurons managing the sustained hyperpolarization of somatic motoneurons during PS. We indeed observed that these medullary neurons are selectively recruited during PS and send monosynaptic inhibitory efferents to the lumbar somatic motoneurons. Furthermore, their genetic inactivation is followed by an increase of abnormal motor behaviors underpinned by a sustained, although irregular, muscle tone. The actimetric analysis of these oneiric experimentally induced behaviors reveals that they are very similar to those observed after SLD inactivation or those reported in RBD patients. Taken together, data harvested during this Thesis help us to better understand the complex neurobiological mechanisms generating PS or specifically contributing to the control of the motor system during PS. At the same time, we validated two rodent models closely mimicking human RBD and thus opening new research fields for the development of targeted treatments for this pathology affecting REM sleep
Chikhaoui, Mohamed. "Apport des données ASTER et d'un réseau de neurones à rétropropagation à la modélisation de la dégradation du sol d'un bassin marneux du Rif marocain." Thèse, Université de Sherbrooke, 2005. http://savoirs.usherbrooke.ca/handle/11143/2747.
Full textMuyl, Frédérique. "Méthodes d'optimisation hybrides appliquées à l'optimisation de formes en aérodynamique automobile." Paris 6, 2003. http://www.theses.fr/2003PA066397.
Full textDesjardins, Guillaume. "Training deep convolutional architectures for vision." Thèse, 2009. http://hdl.handle.net/1866/3646.
Full textHigh-level vision tasks such as generic object recognition remain out of reach for modern Artificial Intelligence systems. A promising approach involves learning algorithms, such as the Arficial Neural Network (ANN), which automatically learn to extract useful features for the task at hand. For ANNs, this represents a difficult optimization problem however. Deep Belief Networks have thus been proposed as a way to guide the discovery of intermediate representations, through a greedy unsupervised training of stacked Restricted Boltzmann Machines (RBM). The articles presented here-in represent contributions to this field of research. The first article introduces the convolutional RBM. By mimicking local receptive fields and tying the parameters of hidden units within the same feature map, we considerably reduce the number of parameters to learn and enforce local, shift-equivariant feature detectors. This translates to better likelihood scores, compared to RBMs trained on small image patches. In the second article, recent discoveries in neuroscience motivate an investigation into the impact of higher-order units on visual classification, along with the evaluation of a novel activation function. We show that ANNs with quadratic units using the softsign activation function offer better generalization error across several tasks. Finally, the third article gives a critical look at recently proposed RBM training algorithms. We show that Contrastive Divergence (CD) and Persistent CD are brittle in that they require the energy landscape to be smooth in order for their negative chain to mix well. PCD with fast-weights addresses the issue by performing small model perturbations, but may result in spurious samples. We propose using simulated tempering to draw negative samples. This leads to better generative models and increased robustness to various hyperparameters.