Dissertations / Theses on the topic 'Réseau de neurone réccurent'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 25 dissertations / theses for your research on the topic 'Réseau de neurone réccurent.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Messaoud, Kaouther. "Deep learning based trajectory prediction for autonomous vehicles." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS048.
Full textThe trajectory prediction of neighboring agents of an autonomous vehicle is essential for autonomous driving in order to perform trajectory planning in an efficient manner. In this thesis, we tackle the problem of predicting the trajectory of a target vehicle in two different environments; a highway and an urban area (intersection, roundabout, etc.). To this end, we develop solutions based on deep machine learning by phasing the interactions between the target vehicle and the static and dynamic elements of the scene. In addition, in order to take into account the uncertainty of the future, we generate multiple plausible trajectories and the probability of occurrence of each. We also make sure that the predicted trajectories are realistic and conform to the structure of the scene. The solutions developed are evaluated using real driving datasets
Nkeumaleu, Guy-Merlin. "Propagation d'informations le long d'une ligne de transmission non linéaire structurée en super réseau et simulant un neurone myélinisé." Thesis, Bourgogne Franche-Comté, 2019. http://www.theses.fr/2019UBFCK006/document.
Full textNon-linear systems are almostly described by partial differential equations that characterize them. We have some systems such as the chain of coupled pebdelums, the protein chain comprising molecules with hydrogen bonds, atomic lattice, and so on .These systems are most often characterized by anharmonic inter particulate interactions and and then immersed in deformable potential substrates. In addition to nonlinearity and dispersion, these other phenomena namely anharmonicity and deformability are responsible for certain properties of propagation of solitary waves such as (compactons, kinks and anti-kinks, peackons, ...etc) and also the ability of the systems to transmit a signal . We used the bifurcation method to plot the different phase portraits obtained . For various parameters of such systems , we have highlighted the influence of anharmonicity on transmissivity and bistability of the system: It appears that the amplitude of the input signal which produces bistability increases with anharmonicity and the bistability is delayed.To considering these important properties generated by such systems, it seemed interesting to buildin an electrical line characterized by the same equations of the system. By alternately doubling the capacitance of the capacitors of a section of this line, we have realised a super-lattice that simulates a myelinised neuron. The types of solitons we get from this line are better adapted to describe the electrical signal which characterizes the neuron impulse located in space with a compact support
Duhr, Fanny. "Voies de signalisation associées au récepteur 5-HT6 et développement neuronal." Thesis, Montpellier, 2015. http://www.theses.fr/2015MONTT042/document.
Full textBrain circuitry patterning is a complex, highly regulated process. Alteration of this process is affected gives rise to various neurodevelopmental disorders such as schizophrenia or Autism Spectrum Disorders (ASD), which are both characterized by a wide spectrum of deficits. Serotonin 6 receptor (5-HT6 receptor), which is known for its implication in neuronal migration process, has been identified as a key therapeutic target for the treatment of cognitive deficits observed in schizophrenia, but also in neurodegenerative pathologies such as Alzheimer's disease. However, the signalling mechanisms knowned to be activated by the 5-HT6 receptor do not explain its involvement in neurodevelopmental processes. My thesis project therefore aimed at characterizing the signalling pathways engaged by 5-HT6 receptor during neural development. A proteomic approach allowed me to show that the 5-HT6 receptor was interacting with several proteins playing crucial roles in neurodevelopmental processes such as Cdk5 or WAVE-1. I then demonstrated that, besides its role in neuronal migration, the 5-HT6 receptor was also involved in neurite growth through constitutive phosphorylation of 5-HT6 receptor at Ser350 by associated Cdk5, a process leading to an increase in Cdc42 activity. The second part of my work aimed at understanding the role of 5-HT6 receptor in dendritic spines morphogenesis, and the involvement of WAVE-1 and Cdk5 in this process. These results provide new insights into the control of neurodevelopemental processes by 5-HT6 receptor. Thus, 5-HT6 receptor appears to be a key therapeutic target for neurodevelopmental disorders by contributing to the development of cognitive circuitry related to the pathophysiology of ASD or schizophrenia
Combes, Denis. "Processus d'intégration dans un système sensori-moteur simple : mécanismes cellulaires impliqués dans le contrôle d'un réseau moteur par un neurone mécanorécepteur primaire chez le homard." Bordeaux 1, 1993. http://www.theses.fr/1993BOR10634.
Full textKosmidis, Efstratios. "Effets du bruit dans le système nerveux central : du neurone au réseau de neurones : fiabilité des neurones, rythmogenèse respiratoire, information visuelle : étude par neurobiologie numérique." Paris 6, 2002. http://www.theses.fr/2002PA066199.
Full textChauvet, Pierre. "Sur la stabilité d'un réseau de neurones hiérarchique à propos de la coordination du mouvement." Angers, 1993. http://www.theses.fr/1993ANGE0011.
Full textWauquier, Pauline. "Task driven representation learning." Thesis, Lille 3, 2017. http://www.theses.fr/2017LIL30005/document.
Full textMachine learning proposes numerous algorithms to solve the different tasks that can be extracted from real world prediction problems. To solve the different concerned tasks, most Machine learning algorithms somehow rely on relationships between instances. Pairwise instances relationships can be obtained by computing a distance between the vectorial representations of the instances. Considering the available vectorial representation of the data, none of the commonly used distances is ensured to be representative of the task that aims at being solved. In this work, we investigate the gain of tuning the vectorial representation of the data to the distance to more optimally solve the task. We more particularly focus on an existing graph-based algorithm for classification task. An algorithm to learn a mapping of the data in a representation space which allows an optimal graph-based classification is first introduced. By projecting the data in a representation space in which the predefined distance is representative of the task, we aim at outperforming the initial vectorial representation of the data when solving the task. A theoretical analysis of the introduced algorithm is performed to define the conditions ensuring an optimal classification. A set of empirical experiments allows us to evaluate the gain of the introduced approach and to temper the theoretical analysis
Mayorquim, Jorge Luiz. "Étude en vue de la réalisation d'un réseau de neurones binaires logiques : détection de contours en temps réel." Compiègne, 1996. http://www.theses.fr/1996COMPD893.
Full textPalluat, Nicolas. "Méthodologie de surveillance dynamique à l'aide des réseaux neuro-flous temporels." Phd thesis, Université de Franche-Comté, 2006. http://tel.archives-ouvertes.fr/tel-00217474.
Full textA partir de l'observation de données capteurs, l'outil de détection détermine l'état du système en associant un degré de possibilité à chacun des modes de fonctionnement. A partir de ces informations, l'outil de diagnostic recherche les causes les plus probables (diagnostic abductif) pondérées par un degré de confiance. En complément et dans une optique à la décision, nous avons veillé à ce que l'opérateur puisse ajouter des informations supplémentaires. Notons que la configuration et l'initialisation des outils implique de connaître l'historique et les données de maintenance du système. Nous exploitons pour cela les AMDEC et Arbres de Défaillance des équipements surveillés. La partie applicative de cette thèse se décompose en deux points : l'intégration logicielle de l'ensemble du travail sur un ordinateur industriel (démarche UML + implémentation) ainsi que l'application sur un système de transfert flexible de production.
Tran, Ngoc Tiem. "Recherche des oscillations de neutrinos par apparition du τ avec désintégration muonique du vτ dans l'expérience OPERA." Phd thesis, Université Claude Bernard - Lyon I, 2010. http://tel.archives-ouvertes.fr/tel-00534753.
Full textTran, Ngoc Tiem. "Recherche des oscillations de neutrinos par apparition du τ avec désintégration muonique du vτ dans l’expérience OPERA." Thesis, Lyon 1, 2010. http://www.theses.fr/2010LYO10203/document.
Full textThe physics of neutrino oscillations plays a major role in studies concerned with cetteparticule. The mechanism of oscillations, based on a change of state of a neutrino flavor during sapropagation, elucidates the deficits observed solar and atmospheric neutrinos and provides indicationsintéressantes of physics beyond the Standard Model by studying the angles mixtures and mass desneutrinos.OPERA scheme is a hybrid sensor combining both latechnique an electronic real-time detection technology and the cloud chamber emulsion or ECC (EmulsionCloud chamber). The ECC is a solid detector detector (target) consisting of bricks dontchacune 150000 consists of sheets of lead, used as a target, with alternate nuclear emulsion whose traces laprécision reconstruction is of the order of one micron. The detector also includes two spectromètresavec magnetized iron plates 5 cm alternating with RPC (Resistive Plate Chamber) detectors associated with six sets of drift tubes (PT) to measure the charge and momentum of the muon thickness and plan vetoservant the rejection of foreign particles to the target
Hardy, Olivier. "Le toit optique du pigeon : propriétés fonctionnelles et organisation neuronale." Paris 6, 1986. http://www.theses.fr/1986PA066028.
Full textBoucenna, Sofiane. "De la reconnaissance des expressions faciales à une perception visuelle partagée : une architecture sensori-motrice pour amorcer un référencement social d'objets, de lieux ou de comportements." Phd thesis, Université de Cergy Pontoise, 2011. http://tel.archives-ouvertes.fr/tel-00660120.
Full textDolz, Jose. "Vers la segmentation automatique des organes à risque dans le contexte de la prise en charge des tumeurs cérébrales par l’application des technologies de classification de deep learning." Thesis, Lille 2, 2016. http://www.theses.fr/2016LIL2S059/document.
Full textBrain cancer is a leading cause of death and disability worldwide, accounting for 14.1 million of new cancer cases and 8.2 million deaths only in 2012. Radiotherapy and radiosurgery are among the arsenal of available techniques to treat it. Because both techniques involve the delivery of a very high dose of radiation, tumor as well as surrounding healthy tissues must be precisely delineated. In practice, delineation is manually performed by experts, or with very few machine assistance. Thus, it is a highly time consuming process with significant variation between labels produced by different experts. Radiation oncologists, radiology technologists, and other medical specialists spend, therefore, a substantial portion of their time to medical image segmentation. If by automating this process it is possible to achieve a more repeatable set of contours that can be agreed upon by the majority of oncologists, this would improve the quality of treatment. Additionally, any method that can reduce the time taken to perform this step will increase patient throughput and make more effective use of the skills of the oncologist.Nowadays, automatic segmentation techniques are rarely employed in clinical routine. In case they are, they typically rely on registration approaches. In these techniques, anatomical information is exploited by means of images already annotated by experts, referred to as atlases, to be deformed and matched on the patient under examination. The quality of the deformed contours directly depends on the quality of the deformation. Nevertheless, registration techniques encompass regularization models of the deformation field, whose parameters are complex to adjust, and its quality is difficult to evaluate. Integration of tools that assist in the segmentation task is therefore highly expected in clinical practice.The main objective of this thesis is therefore to provide radio-oncology specialists with automatic tools to delineate organs at risk of patients undergoing brain radiotherapy or stereotactic radiosurgery. To achieve this goal, main contributions of this thesis are presented on two major axes. First, we consider the use of one of the latest hot topics in artificial intelligence to tackle the segmentation problem, i.e. deep learning. This set of techniques presents some advantages with respect to classical machine learning methods, which will be exploited throughout this thesis. The second axis is dedicated to the consideration of proposed image features mainly associated with texture and contextual information of MR images. These features, which are not present in classical machine learning based methods to segment brain structures, led to improvements on the segmentation performance. We therefore propose the inclusion of these features into a deep network.We demonstrate in this work the feasibility of using such deep learning based classification scheme for this particular problem. We show that the proposed method leads to high performance, both in accuracy and efficiency. We also show that automatic segmentations provided by our method lie on the variability of the experts. Results demonstrate that our method does not only outperform a state-of-the-art classifier, but also provides results that would be usable in the radiation treatment planning
Yang, Lixuan. "Structuring of image databases for the suggestion of products for online advertising." Thesis, Paris, CNAM, 2017. http://www.theses.fr/2017CNAM1102/document.
Full textThe topic of the thesis is the extraction and segmentation of clothing items from still images using techniques from computer vision, machine learning and image description, in view of suggesting non intrusively to the users similar items from a database of retail products. We firstly propose a dedicated object extractor for dress segmentation by combining local information with a prior learning. A person detector is applied to localize sites in the image that are likely to contain the object. Then, an intra-image two-stage learning process is developed to roughly separate foreground pixels from the background. Finally, the object is finely segmented by employing an active contour algorithm that takes into account the previous segmentation and injects specific knowledge about local curvature in the energy function.We then propose a new framework for extracting general deformable clothing items by using a three stage global-local fitting procedure. A set of template initiates an object extraction process by a global alignment of the model, followed by a local search minimizing a measure of the misfit with respect to the potential boundaries in the neighborhood. The results provided by each template are aggregated, with a global fitting criterion, to obtain the final segmentation.In our latest work, we extend the output of a Fully Convolution Neural Network to infer context from local units(superpixels). To achieve this we optimize an energy function,that combines the large scale structure of the image with the locallow-level visual descriptions of superpixels, over the space of all possiblepixel labellings. In addition, we introduce a novel dataset called RichPicture, consisting of 1000 images for clothing extraction from fashion images.The methods are validated on the public database and compares favorably to the other methods according to all the performance measures considered
Barrachina, Jose Agustin. "Complex-valued neural networks for radar applications." Electronic Thesis or Diss., université Paris-Saclay, 2022. http://www.theses.fr/2022UPASG094.
Full textRadar signal and SAR image processing generally require complex-valued representations and operations, e.g., Fourier, wavelet transforms, Wiener, matched filters, etc. However, the vast majority of architectures for deep learning are currently based on real-valued operations, which restrict their ability to learn from complex-valued features. Despite the emergence of Complex-Valued Neural Networks (CVNNs), their application on radar and SAR still lacks study on their relevance and efficiency. And the comparison against an equivalent Real-Valued Neural Network (RVNN) is usually biased.In this thesis, we propose to investigate the merits of CVNNs for classifying complex-valued data. We show that CVNNs achieve better performance than their real-valued counterpart for classifying non-circular Gaussian data. We also define a criterion of equivalence between feed-forward fully connected and convolutional CVNNs and RVNNs in terms of trainable parameters while keeping a similar architecture. We statistically compare the performance of equivalent Multi-Layer Perceptrons (MLPs), Convolutional Neural Networks (CNNs), and Fully Convolutional Neural Networks (FCNNs) for polarimetric SAR image segmentation. SAR image splitting and balancing classes are also studied to avoid learning biases. In parallel, we also proposed an open-source toolbox to facilitate the implementation of CVNNs and the comparison with real-equivalent networks
Séguin-Godin, Guillaume. "Simulateur matériel à événements discrets de réseaux de neurones à décharges avec application en traitement d’images." Mémoire, Université de Sherbrooke, 2016. http://hdl.handle.net/11143/10600.
Full textForoughmand, Aarabi Hadrien. "Towards global tempo estimation and rhythm-oriented genre classification based on harmonic characteristics of rhythm." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS018.
Full textAutomatic detection of the rhythmic structure within music is one of the challenges of the "Music Information Retrieval" research area. The advent of technology dedicated to the arts has allowed the emergence of new musical trends generally described by the term "Electronic/Dance Music" (EDM) which encompasses a plethora of sub-genres. This type of music often dedicated to dance is characterized by its rhythmic structure. We propose a rhythmic analysis of what defines certain musical genres including those of EDM. To do so, we want to perform an automatic global tempo estimation task and a genre classification task based on rhythm. Tempo and genre are two intertwined aspects since genres are often associated with rhythmic patterns that are played in specific tempo ranges. Some so-called "handcrafted" tempo estimation systems have been shown to be effective based on the extraction of rhythm-related characteristics. Recently, with the appearance of annotated databases, so-called "data-driven" systems and deep learning approaches have shown progress in the automatic estimation of these tasks. In this thesis, we propose methods at the crossroads between " handcrafted " and " data-driven " systems. The development of a new representation of rhythm combined with deep learning by convolutional neural network is at the basis of all our work. We present in detail our Deep Rhythm method in this thesis and we also present several extensions based on musical intuitions that allow us to improve our results
Martinez, Coralie. "Classification précoce de séquences temporelles par de l'apprentissage par renforcement profond." Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAT123.
Full textEarly classification (EC) of time series is a recent research topic in the field of sequential data analysis. It consists in assigning a label to some data that is sequentially collected with new data points arriving over time, and the prediction of a label has to be made using as few data points as possible in the sequence. The EC problem is of paramount importance for supporting decision makers in many real-world applications, ranging from process control to fraud detection. It is particularly interesting for applications concerned with the costs induced by the acquisition of data points, or for applications which seek for rapid label prediction in order to take early actions. This is for example the case in the field of health, where it is necessary to provide a medical diagnosis as soon as possible from the sequence of medical observations collected over time. Another example is predictive maintenance with the objective to anticipate the breakdown of a machine from its sensor signals. In this doctoral work, we developed a new approach for this problem, based on the formulation of a sequential decision making problem, that is the EC model has to decide between classifying an incomplete sequence or delaying the prediction to collect additional data points. Specifically, we described this problem as a Partially Observable Markov Decision Process noted EC-POMDP. The approach consists in training an EC agent with Deep Reinforcement Learning (DRL) in an environment characterized by the EC-POMDP. The main motivation for this approach was to offer an end-to-end model for EC which is able to simultaneously learn optimal patterns in the sequences for classification and optimal strategic decisions for the time of prediction. Also, the method allows to set the importance of time against accuracy of the classification in the definition of rewards, according to the application and its willingness to make this compromise. In order to solve the EC-POMDP and model the policy of the EC agent, we applied an existing DRL algorithm, the Double Deep-Q-Network algorithm, whose general principle is to update the policy of the agent during training episodes, using a replay memory of past experiences. We showed that the application of the original algorithm to the EC problem lead to imbalanced memory issues which can weaken the training of the agent. Consequently, to cope with those issues and offer a more robust training of the agent, we adapted the algorithm to the EC-POMDP specificities and we introduced strategies of memory management and episode management. In experiments, we showed that these contributions improved the performance of the agent over the original algorithm, and that we were able to train an EC agent which compromised between speed and accuracy, on each sequence individually. We were also able to train EC agents on public datasets for which we have no expertise, showing that the method is applicable to various domains. Finally, we proposed some strategies to interpret the decisions of the agent, validate or reject them. In experiments, we showed how these solutions can help gain insight in the choice of action made by the agent
Yang, Lixuan. "Structuring of image databases for the suggestion of products for online advertising." Electronic Thesis or Diss., Paris, CNAM, 2017. http://www.theses.fr/2017CNAM1102.
Full textThe topic of the thesis is the extraction and segmentation of clothing items from still images using techniques from computer vision, machine learning and image description, in view of suggesting non intrusively to the users similar items from a database of retail products. We firstly propose a dedicated object extractor for dress segmentation by combining local information with a prior learning. A person detector is applied to localize sites in the image that are likely to contain the object. Then, an intra-image two-stage learning process is developed to roughly separate foreground pixels from the background. Finally, the object is finely segmented by employing an active contour algorithm that takes into account the previous segmentation and injects specific knowledge about local curvature in the energy function.We then propose a new framework for extracting general deformable clothing items by using a three stage global-local fitting procedure. A set of template initiates an object extraction process by a global alignment of the model, followed by a local search minimizing a measure of the misfit with respect to the potential boundaries in the neighborhood. The results provided by each template are aggregated, with a global fitting criterion, to obtain the final segmentation.In our latest work, we extend the output of a Fully Convolution Neural Network to infer context from local units(superpixels). To achieve this we optimize an energy function,that combines the large scale structure of the image with the locallow-level visual descriptions of superpixels, over the space of all possiblepixel labellings. In addition, we introduce a novel dataset called RichPicture, consisting of 1000 images for clothing extraction from fashion images.The methods are validated on the public database and compares favorably to the other methods according to all the performance measures considered
Azouz, Nesrine. "Approches intelligentes pour le pilotage adaptatif des systèmes en flux tirés dans le contexte de l'industrie 4.0." Thesis, Université Clermont Auvergne (2017-2020), 2019. http://www.theses.fr/2019CLFAC028/document.
Full textToday, many production systems are managed in "pull" control system and used "card-based" methods such as: Kanban, ConWIP, COBACABANA, etc. Despite their simplicity and efficiency, these methods are not suitable when production is not stable and customer demand varies. In such cases, the production systems must therefore adapt the “tightness” of their production flow throughout the manufacturing process. To do this, we must determine how to dynamically adjust the number of cards (or e-card) depending on the context. Unfortunately, these decisions are complex and difficult to make in real time. In addition, in some cases, changing too often the number of kanban cards can disrupt production and cause a nervousness problem. The opportunities offered by Industry 4.0 can be exploited to define smart flow control strategies to dynamically adapt this number of kanban cards.In this thesis, we propose, firstly, an adaptive approach based on simulation and multi-objective optimization technique, able to take into account the problem of nervousness and to decide autonomously (or to help managers) when and where adding or removing Kanban cards. Then, we propose a new adaptive and intelligent approach based on a neural network whose learning is first realized offline using a twin digital model (simulation) and exploited by a multi-objective optimization method. Then, the neural network could be able to decide in real time, when and at which manufacturing stage it is relevant to change the number of kanban cards. Comparisons made with the best methods published in the literature show better results with less frequent changes
Gueye, Ndiouga. "Exploration des liens formels entre les méthodes statistiques et neuronales en classification." Thèse, 2019. http://depot-e.uqtr.ca/id/eprint/9416/1/eprint9416.pdf.
Full textMatcha, Wyao. "Identification des composants prioritaires pour les tests unitaires dans les systèmes OO : une approche basée sur l'apprentissage profond." Thèse, 2020. http://depot-e.uqtr.ca/id/eprint/9420/1/eprint9420.pdf.
Full textZumer, Jeremie. "Influencing the Properties of Latent Spaces." Thèse, 2016. http://hdl.handle.net/1866/18767.
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.