Índice
Literatura académica sobre el tema "Humain-dans-la-boucle"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte las listas temáticas de artículos, libros, tesis, actas de conferencias y otras fuentes académicas sobre el tema "Humain-dans-la-boucle".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Artículos de revistas sobre el tema "Humain-dans-la-boucle"
Obame, Fabiola. "Transmission initiatique et conscience écologique dans les nouvelles de Ludovic Obiang". Voix Plurielles 16, n.º 2 (29 de noviembre de 2019): 74–87. http://dx.doi.org/10.26522/vp.v16i2.2310.
Texto completoTesis sobre el tema "Humain-dans-la-boucle"
Pichard, Véronique. "Rôle des récepteurs de l'EGF et des intégrines dans l'adhérence, la croissance et la différenciation cellulaires d'un adénocarcinome de colôn humain : implication de la FAK, de ERK1/2 et d'une boucle autocrine dans ces phénomènes biologiques". Aix-Marseille 2, 2002. http://theses.univ-amu.fr.lama.univ-amu.fr/2002AIX22951.pdf.
Texto completoLenczner, Gaston. "Interactive semantic segmentation of aerial images with deep neural networks". Electronic Thesis or Diss., université Paris-Saclay, 2022. http://www.theses.fr/2022UPASG067.
Texto completoWe propose in this thesis to build up a collaboration between a deep neural network and a human in the loop to swiftly collect accurate segmentation maps of remote sensing images. In a nutshell, the user iteratively interacts with the network to correct its initially flawed predictions. Concretely, these interactions are annotations representing the semantic labels. Our contributions are fourfold. First, we propose two interactive learning schemes to integrate user inputs into deep neural networks. The first one concatenates the user annotations with the other inputs of the network (e.g. RGB image). We apply it both to convolutional architectures and to Transformers. The second one uses the annotations as a sparse ground-truth to retrain the network. Then, we propose an active learning strategy to guide the user towards the most relevant areas to annotate. To this purpose, we adapt different state-of-the-art acquisition functions to evaluate the neural network uncertainty. Finally, we propose to modify the algorithm output space to swiftly adapt it to new classes under weak supervision. To alleviate the background shift and the catastrophic forgetting issues inherent to this problem, we compare different regularization terms and leverage a pseudo-label strategy. Through experiments on multiple remote sensing datasets, we show the effectiveness of the proposed methods and analyze them extensively. Combining these different components results in a robust and versatile framework to interactively correct semantic segmentation maps produced by deep learning algorithms in remote sensing
Michel, Pauline. "Simulateurs de conduite et adéquation architecture / modèles : impact sur le « mal du simulateur »". Electronic Thesis or Diss., université Paris-Saclay, 2022. http://www.theses.fr/2022UPAST173.
Texto completo“Simulator sickness,” which is to some extent similar to motion sickness, is particularly problematic. Understanding the causes of simulator sickness and identifying ways to reduce its occurrence are important issues insofar as, on the one hand, the “at the door” filtering of the population studied on the simulator (people who are not susceptible) introduces bias in the results acquired and, on the other hand, a driver who suffers from simulator sickness is likely to behave differently in terms of their driving, which also introduces bias.The hypothesis we defend in this thesis concerns the relationship between the "controllability" of the system (the simulator) and simulator sickness.In driving simulation, the driver is an integral part of the loop: they initiate the movements and receive the system responses. Our hypothesis is that, in this context, a poor control of the simulated vehicle movement induces erratic movements, perceived by the driver as not corresponding to their expectations (because of their previous driving experience) and therefore unacceptable.To evaluate this hypothesis, we have redesigned the rider/simulator interfacing modalities of a pre- existing motorcycle simulator: hardware and software architecture, sensor/actuator structure of the steering column, and implemented vehicle model. In its current version, the simulator allows a higher degree of controllability by the driver for medium to high speeds
Senova, Yann Suhan. "Caractérisation anatomo-fonctionnelle du faisceau cortico-subthalamique moteur chez le primate non humain : étude par optogénétique, électrophysiologie, histologie-3D, et tractographie. Implications pour les stratégies de neuromodulation dans le traitement de la maladie de Parkinson". Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066678.
Texto completoParkinson’s Disease (PD) is the second most widespread neurodegenerative disease. Motor symptoms initially respond well to dopaminergic medecines ; however, motor complications will eventually occur. Some patients are then proposed a neurosurgical treatment by chronical electrical deep brain stimulation (DBS) of the subthalamic nucleus (STN). Several studies suggested that the modulation of the motor cortico-subthalamic bundle might explain the efficacy of STN DBS, at least to a certain extent. A better understanding of the mechanism of action of DBS of the STN in order to treat PD should help to optimize the safety/efficacy of this surgical procedure from which tens of thousands of patients could benefit all over the world.The main purpose of the present thesis is to characterize, both anatomically and functionally, the motor cortico-subthalamic bundle in non-human primates. Secundary objectives are : (1) to allow the direct visualization, under stereotactic conditions, of the STN of non-human primates and of patients with PD ; (2) to develop a methodology enabling to characterize, both anatomically and functionally, any fiber bundle between two anatomically distinct cerebral areas, in non-human primates ; (3) to establish a command law for closed-loop stimulation of STN by optogenetics, in order to selectively destroy beta-oscillations and assess the hypothesis of their role in the occurrence of motor symptoms in PD