Rozprawy doktorskie na temat „Compression par réseau de neurones”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych rozpraw doktorskich naukowych na temat „Compression par réseau de neurones”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj rozprawy doktorskie z różnych dziedzin i twórz odpowiednie bibliografie.
Fernandez, Brillet Lucas. "Réseaux de neurones CNN pour la vision embarquée". Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM043.
Pełny tekst źródłaRecently, Convolutional Neural Networks have become the state-of-the-art soluion(SOA) to most computer vision problems. In order to achieve high accuracy rates, CNNs require a high parameter count, as well as a high number of operations. This greatly complicates the deployment of such solutions in embedded systems, which strive to reduce memory size. Indeed, while most embedded systems are typically in the range of a few KBytes of memory, CNN models from the SOA usually account for multiple MBytes, or even GBytes in model size. Throughout this thesis, multiple novel ideas allowing to ease this issue are proposed. This requires to jointly design the solution across three main axes: Application, Algorithm and Hardware.In this manuscript, the main levers allowing to tailor computational complexity of a generic CNN-based object detector are identified and studied. Since object detection requires scanning every possible location and scale across an image through a fixed-input CNN classifier, the number of operations quickly grows for high-resolution images. In order to perform object detection in an efficient way, the detection process is divided into two stages. The first stage involves a region proposal network which allows to trade-off recall for the number of operations required to perform the search, as well as the number of regions passed on to the next stage. Techniques such as bounding box regression also greatly help reduce the dimension of the search space. This in turn simplifies the second stage, since it allows to reduce the task’s complexity to the set of possible proposals. Therefore, parameter counts can greatly be reduced.Furthermore, CNNs also exhibit properties that confirm their over-dimensionment. This over-dimensionement is one of the key success factors of CNNs in practice, since it eases the optimization process by allowing a large set of equivalent solutions. However, this also greatly increases computational complexity, and therefore complicates deploying the inference stage of these algorithms on embedded systems. In order to ease this problem, we propose a CNN compression method which is based on Principal Component Analysis (PCA). PCA allows to find, for each layer of the network independently, a new representation of the set of learned filters by expressing them in a more appropriate PCA basis. This PCA basis is hierarchical, meaning that basis terms are ordered by importance, and by removing the least important basis terms, it is possible to optimally trade-off approximation error for parameter count. Through this method, it is possible to compress, for example, a ResNet-32 network by a factor of ×2 both in the number of parameters and operations with a loss of accuracy <2%. It is also shown that the proposed method is compatible with other SOA methods which exploit other CNN properties in order to reduce computational complexity, mainly pruning, winograd and quantization. Through this method, we have been able to reduce the size of a ResNet-110 from 6.88Mbytes to 370kbytes, i.e. a x19 memory gain with a 3.9 % accuracy loss.All this knowledge, is applied in order to achieve an efficient CNN-based solution for a consumer face detection scenario. The proposed solution consists of just 29.3kBytes model size. This is x65 smaller than other SOA CNN face detectors, while providing equal detection performance and lower number of operations. Our face detector is also compared to a more traditional Viola-Jones face detector, exhibiting approximately an order of magnitude faster computation, as well as the ability to scale to higher detection rates by slightly increasing computational complexity.Both networks are finally implemented in a custom embedded multiprocessor, verifying that theorical and measured gains from PCA are consistent. Furthermore, parallelizing the PCA compressed network over 8 PEs achieves a x11.68 speed-up with respect to the original network running on a single PE
Boukli, Hacene Ghouthi. "Processing and learning deep neural networks on chip". Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2019. http://www.theses.fr/2019IMTA0153/document.
Pełny tekst źródłaIn the field of machine learning, deep neural networks have become the inescapablereference for a very large number of problems. These systems are made of an assembly of layers,performing elementary operations, and using a large number of tunable variables. Using dataavailable during a learning phase, these variables are adjusted such that the neural networkaddresses the given task. It is then possible to process new data.To achieve state-of-the-art performance, in many cases these methods rely on a very largenumber of parameters, and thus large memory and computational costs. Therefore, they are oftennot very adapted to a hardware implementation on constrained resources systems. Moreover, thelearning process requires to reuse the training data several times, making it difficult to adapt toscenarios where new information appears on the fly.In this thesis, we are first interested in methods allowing to reduce the impact of computations andmemory required by deep neural networks. Secondly, we propose techniques for learning on thefly, in an embedded context
Mahé, Pierre. "Codage ambisonique pour les communications immersives". Thesis, La Rochelle, 2022. http://www.theses.fr/2022LAROS011.
Pełny tekst źródłaThis thesis takes place in the context of the spread of immersive content. For the last couple of years, immersive audio recording and playback technologies have gained momentum and have become more and more popular. New codecs are needed to handle those spatial audio formats, especially for communication applications. There are several ways to represent spatial audio scenes. In this thesis, we focused on First Order Ambisonic. The first part of our research focused on improving multi-monocoding by decorrelated each ambisonic signal component before the multi-mono coding. To guarantee signal continuity between frames, efficient quantization new mechanisms are proposed. In the second part of this thesis, we proposed a new coding concept using a power map to recreate the original spatial image. With this concept, we proposed two compressing methods. The first one is a post-processing focused on limiting the spatial distortion of the decoded signal. The spatial correction is based on the difference between the original and the decoded spatial image. This post-processing is later extended to a parametric coding method. The last part of this thesis presents a more exploratory method. This method studied audio signal compression by neural networks inspired by image compression models using variational autoencoders
Jouffroy, Guillaume. "Contrôle oscillatoire par réseau de neurones récurrents". Paris 8, 2008. http://www.theses.fr/2008PA082918.
Pełny tekst źródłaIn the control field, most of the applications need a non-oscillatory continuous control. This work focuses instead on controllers with recurrent neural networks (RNN) which generate a periodic oscillatory control. The purpose of the present work is to study stochastic optimisation methods which can be used to discover the parameters of a network so that it generates a cyclic input. First we take a look at the knowledge about biological oscillators. Tthen we describe the mathematical tools to be able to guarantee the stability oscillators. The potential of RNN, especially applied to dynamical systems being still poorly used, we propose for each method, a general detailed matrix formalization and we precise the computational complexity of the methods. We validate each method using a simple example of oscillator, and we demonstrate analytically the stability of the resulting oscillator, but also how it is robust to parameters perturbations. We then compare these different methods with these criteria and the speed of convergence. We finish this thesis with an illustration, where we take all the steps of the construction of an oscillatory neural controller, to control the axis of direction of a particular vehicle. This will let us discuss how realistic is the use of recurrent neural networks in the field of control, and propose interesting questions
Carpentier, Mathieu. "Classification fine par réseau de neurones à convolution". Master's thesis, Université Laval, 2019. http://hdl.handle.net/20.500.11794/35835.
Pełny tekst źródłaArtificial intelligence is a relatively recent research domain. With it, many breakthroughs were made on a number of problems that were considered very hard. Fine-grained classification is one of those problems. However, a relatively small amount of research has been done on this task even though itcould represent progress on a scientific, commercial and industrial level. In this work, we talk about applying fine-grained classification on concrete problems such as tree bark classification and mould classification in culture. We start by presenting fundamental deep learning concepts at the root of our solution. Then, we present multiple experiments made in order to try to solve the tree bark classification problem and we detail the novel dataset BarkNet 1.0 that we made for this project. With it, we were able to develop a method that obtains an accuracy of 93.88% on singlecrop in a single image, and an accuracy of 97.81% using a majority voting approach on all the images of a tree. We conclude by demonstrating the feasibility of applying our method on new problems by showing two concrete applications on which we tried our approach, industrial tree classification and mould classification.
Cayouette, Philippe. "Aérocapture martienne par réseau de neurones entraîné par algorithme génétique". Mémoire, Université de Sherbrooke, 2006. http://savoirs.usherbrooke.ca/handle/11143/1372.
Pełny tekst źródłaCharpentier, Éric. "Repérage d'un faisceau à l'aide d'un réseau d'antennes, guidé par un réseau de neurones". Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/tape17/PQDD_0001/MQ37437.pdf.
Pełny tekst źródłaLiu, Xiaoqing. "Analyse d'images couleur en composantes indépendantes par réseau de neurones". Grenoble INPG, 1991. http://www.theses.fr/1991INPG0120.
Pełny tekst źródłaGoulet-Fortin, Jérôme. "Modélisation des rendements de la pomme de terre par réseau de neurones". Thesis, Université Laval, 2009. http://www.theses.ulaval.ca/2009/26556/26556.pdf.
Pełny tekst źródłaLaurent, Rémy. "Simulation du mouvement pulmonaire personnalisé par réseau de neurones artificiels pour la radiothérapie externe". Phd thesis, Université de Franche-Comté, 2011. http://tel.archives-ouvertes.fr/tel-00800360.
Pełny tekst źródłaBergeron, Jocelyn. "Reconnaissance accélérée de formes par un réseau optimisé avec neurones à champs récepteurs synchrones". Mémoire, Université de Sherbrooke, 2008. http://savoirs.usherbrooke.ca/handle/11143/1595.
Pełny tekst źródłaBongono, Julien. "Caracterisation des suspensions par des methodes optiques. modelisation par reseaux de neurones". Phd thesis, Ecole Nationale Supérieure des Mines de Saint-Etienne, 2010. http://tel.archives-ouvertes.fr/tel-00666171.
Pełny tekst źródłaBal, Lyes. "Modélisation du retrait et du fluage du béton par réseaux de neurones". Thesis, Lille 1, 2009. http://www.theses.fr/2009LIL10112/document.
Pełny tekst źródłaConcrete is the material the most used in construction works for a century. After establishment and setting, various physical and mechanical dimensional developments. Occur drying is developing with hardening of concrete and leads to significant dimensional changes, that can induce cracking, pre judiciable at the durability of the civil engineering works. This study aims to demonstrate the application of a nonparametric approach called Artificial Neural Networks to provide effective spontaneous and differed dimensional variations (drying shrinkage and drying creep). Using this approach allows the development of predicting models. These models use a multi layer back propagation. They also rely on a very large database of experimental results obtained in the literature and an appropriate choice of architectures and learning process. These models take into account the different parameters of preservation and making that affect drying shrinkage and creep of concrete. To appreciate the validity of our models, we have compared with other existing models : B3, ACI 209, CEB and GL2000. In these comparisons, it appears that our models are correctly adapted to describe the time evolution of drying shrinkage and creep
Tay, Yong Haur. "Reconnaissance de l'écriture manuscrite hors-ligne par réseau de neurones artificiels et modèles de Markov cachés". Nantes, 2002. http://www.theses.fr/2002NANT2106.
Pełny tekst źródłaKharroubi, Ouissem. "Prévision des crues par modèle de réseau de neurones artificiels : application au bassin versant de l’Eure". Thesis, Lille 1, 2013. http://www.theses.fr/2013LIL10034/document.
Pełny tekst źródłaThe growth of riparian populations generates an increase in vulnerability of our societies to flood. Therefore, a high social demand to prevent and predict these natural disasters must be tacking to protect the population against floods. To achieve this objective, the provision of flood forecasting tools, operational and reliable, is primordial. But the flood forecasting still an exercise far from being evident. Firstly, because the forecast requirements (precision and time anticipation) are becoming more and more higher. And secondly, because the physical flood forecasting tools is limited by the relative knowledge of floods hydro-systems. In this context, this thesis presents the work done to produce rainfall-runoff flood forecasting models based on artificial neural networks (ANN) in the Eure watershed (and two sub-basins) up to a 48 hours horizon forecasting. Firstly, an analysis of the geographical complexity of studied basins will be conducted in order to determine the different factors that influencing the hydrological Eure watershed regime. Then, a methodological process to data statistical analysis, has allowed a synthesis on the hydrological nature of the watersheds studied and brings the elements needed to the definition of the non-linear relations rainfall-runoff. This contribution has allowed the creation of a rainfall-runoff nonlinear model for flood forecasting. ANN model able to perform a reliable forecasting of flood up to a 48 hours horizon forecasting. This process has been tested on three watersheds and the test results show a reliable forecasts as well as an ability of generalization to other hydro-systems
Herry, Sébastien. "Détection automatique de langue par discrimination d'experts". Paris 6, 2007. http://www.theses.fr/2007PA066101.
Pełny tekst źródłaThe purpose of the presented work in this memoir is to automatically detect language in audio stream. For this we suggest a model which, like bilingual expert, done an discrimination by language pair with only acoustic information. The system have constraint : Operating in real time, Use database without phonetic information, Able to add a new language without retrain all the model In a first time we have done an Automatic language detection system derived from the stat of the art. The results obtained by this system are used as reference for the rest of memoir, and we compare those results with the results obtained by the developed model. In a first time, we propose a set of discriminator, by pair of language, based on neural network. The treatment is done on the whole duration of speech segment. The results of these discriminators are fused to create de detection. This model has a patent. We have study more precisely the influence of different parameter as the number of locator, the variation intra and inter corpus or the hardiness. Next we have compared the proposed modelling based on discrimination, with modelling auto regressive or predictive. This system has been tested with our participation of the international campaign organised by NIST in December 2005. To conclude on this campaign where 17 international teams have participated, we have proposed several improvements as: A normalisation of database, A modification of speaker database for learning only, Increase scores with segment duration. To conclude, the system proposed fulfils the constraints because the system is real time, and use only acoustic information. More over the system is more efficient than the derived model from the stat of the art. At last the model is hardiness for noise, for unknown language, for new evaluation database
Kosmidis, 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.
Pełny tekst źródłaBongono, Juilien. "Caracterisation des suspensions par des methodes optiques. modelisation par reseaux de neurones". Thesis, Saint-Etienne, EMSE, 2010. http://www.theses.fr/2010EMSE0577/document.
Pełny tekst źródłaThe sedimentation of aqueous suspensions of micron-sized mineral particles, polydisperses and concentrated, was analyzed using the Turbiscan MA 2000 based on the multiple light scattering in order to establish the procedure to detect the presence of a fractal morphology, and then to deduce the set of laws of fractal behavior of suspensions by modeling with neural networks. The methodology for determining the multifractal structure of agglomerates and the suspension was proposed. The structural modifications of the agglomerates at the origin of the nonlinear behavior of suspensions and which depends on cohesive properties of primary particles, is interpreted by the change of the electrophoretic mobility of suspended particles. The estimation by neural networks of these structural changes, through the fractal dimension has been presented. The limits of the model to learn these specific behaviors have been explained as resulting from the low number of examples and the great variability in the measurements at low volume fractions of solid
Legrand, Jean-François. "Prédiction de trafic dans les réseaux de téléphonie mobile par des méthodes statistiques et neuronales". Paris 6, 2003. http://www.theses.fr/2003PA066543.
Pełny tekst źródłaRuichek, Yassine. "Stéréovision linéaire par réseau de neurones de Hopfield : application à la détection d'obstacles à l'avant des véhicules routiers". Lille 1, 1997. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/1997/50376-1997-43.pdf.
Pełny tekst źródłaKhoyratee, Farad. "Conception d’une plateforme modulable de réseau de neurones biomimétiques pour l’étude des maladies neurodégénératives". Thesis, Bordeaux, 2019. http://www.theses.fr/2019BORD0351.
Pełny tekst źródłaNeuroscience has been the subject of many studies and has seen new fields of research emerge where technology and biology can be used to find solutions to understand and cure neurological diseases. These illness affect millions of people around the world. The World Health Organization (WHO) predicts a 3 fold increase in the number of patients in the next 30 years.Advances in neuroscience have led to the development of models describing the physiology of neurons and also methods of hardware implementation of these models. Among these methods, neuroprosthesis are devices for restoring certain neuronal functions through communication with the nervous system.This thesis work show that the realization of the biomimetic system was carried out thanks to digital components such as Field Programmable Gate Array (FPGA) which allows to benefit from the flexibility and speed of prototyping of these technologies. The real-time platform of biologically realistic neural networks developed is configurable. It becomes a neuro-computational tool allowing the realization of bio-hybrid experiments for the study of the behavior of the nervous system and more particularly of the neurodegenerative diseases.This work was placed in a larger context. The FPGA digital operator library developed for the platform has been reused for the study of dynamics similar to neural networks such as biochemical network simulation or combinatorial optimization problem solving
Taver, Virgile. "Caractérisation et modélisation hydrodynamique des karsts par réseaux de neurones : application à l'hydrosystème du Lez". Thesis, Montpellier 2, 2014. http://www.theses.fr/2014MON20169/document.
Pełny tekst źródłaImproving knowledge of karst hydrodynamics represents a global challenge for water resource because karst aquifers provide approximately 25% of the world population in fresh water. Nevertheless, complexity, anisotropy, heterogeneity, non-linearity and possible non-stationarity of these aquifers makes them underexploited objects due to the difficulty to characterize their morphology and hydrodynamics. In this context, the systemic paradigm proposes others methods by studying these hydrosystems through input-output (rainfall-runoff) relations.This work covers the use of: i) correlation and spectral analysis to characterize response of karst aquifers, ii) neural networks to study and model linear and non-linear relations of these hydrosystems. In order to achieve this, different types of neural networks model configurations are explored to compare behavior and performances of these models. We are looking to constrain these models to make them interpretable in terms of hydrodynamic processes by making the operation of the model closer to the natural system in order to obtain a good representation and extract knowledge from the model parameters.The results obtained by correlation and spectral analysis are used to manage the configuration of neural networks models. Applied on the Lez hydrosystem over the period 1950-1967, results show that neural networks models are capable to model non-linear operation of the karst.Application of neural modelling on two non stationary hydrosystems (Durance in France and Fernow in the the USA) proved the ability of neural networks to model satisfactorily non-stationary conditions. Moreover, two real-time adjustment methods (adaptativity and data assimilation) enhanced the performance of neural network models face to changing conditions of the inputs or of the system itself.Finally, these various methods to analyze and model allow improving knowledge of the rainfall-runoff relationship. Methodological tools developed in this thesis were developed thanks to the application on Lez hydrosystem which has been studied for decades. This study and modeling methodology have the advantage of being applicable to other systems provided the availability of a sufficient database
Pérez, Chavarría Miguel Angel. "Restitution de paramètres atmosphériques hydrologiques sur l'océan, par radiométrie hyperfréquence spatiale : méthodologie neuronale". Paris 6, 2007. http://www.theses.fr/2007PA066487.
Pełny tekst źródłaTheilliol, Didier. "Identification de systèmes siso linéaires et non linéaires par réseaux de neurones multicouches". Nancy 1, 1993. http://www.theses.fr/1993NAN10261.
Pełny tekst źródłaGeoffroy, Charles. "Récupération en temps réel de coïncidences diffuses triples dans un scanner TEP à l'aide d'un réseau de neurones artificiels". Mémoire, Université de Sherbrooke, 2013. http://hdl.handle.net/11143/6177.
Pełny tekst źródłaDugas, Alexandre. "Architecture de transformée de cosinus discrète sur deux dimensions sans multiplication et mémoire de transposition". Mémoire, Université de Sherbrooke, 2012. http://hdl.handle.net/11143/6174.
Pełny tekst źródłaLefort, Mathieu. "Apprentissage spatial de corrélations multimodales par des mécanismes d'inspiration corticale". Phd thesis, Université Nancy II, 2012. http://tel.archives-ouvertes.fr/tel-00756687.
Pełny tekst źródłaCherkashyn, Valeriy. "Représentation adaptative d'images de télédétection à très haute résolution spatiale une nouvelle approche hybride (la décomposition pyramidale avec des réseaux de neurones)". Thèse, Université de Sherbrooke, 2011. http://hdl.handle.net/11143/5831.
Pełny tekst źródłaMayorquim, 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.
Pełny tekst źródłaHamachi, Mourad. "Mesure dynamique de l'épaisseur du dépôt à l'aide d'un capteur optique et modélisation par réseau de neurones de la microfiltration tangentielle de suspensions". Toulouse, INPT, 1997. http://www.theses.fr/1997INPT035G.
Pełny tekst źródłaFrämling, Kary. "Modélisation et apprentissage des préférences par réseaux de neurones pour l'aide à la décision multicritère". Phd thesis, INSA de Lyon, 1996. http://tel.archives-ouvertes.fr/tel-00825854.
Pełny tekst źródłaMercadier, Yves. "Classification automatique de textes par réseaux de neurones profonds : application au domaine de la santé". Thesis, Montpellier, 2020. http://www.theses.fr/2020MONTS068.
Pełny tekst źródłaThis Ph.D focuses on the analysis of textual data in the health domain and in particular on the supervised multi-class classification of data from biomedical literature and social media.One of the major difficulties when exploring such data by supervised learning methods is to have a sufficient number of data sets for models training. Indeed, it is generally necessary to label manually the data before performing the learning step. The large size of the data sets makes this labellisation task very expensive, which should be reduced with semi-automatic systems.In this context, active learning, in which the Oracle intervenes to choose the best examples to label, is promising. The intuition is as follows: by choosing the smartly the examples and not randomly, the models should improve with less effort for the oracle and therefore at lower cost (i.e. with less annotated examples). In this PhD, we will evaluate different active learning approaches combined with recent deep learning models.In addition, when small annotated data set is available, one possibility of improvement is to artificially increase the data quantity during the training phase, by automatically creating new data from existing data. More precisely, we inject knowledge by taking into account the invariant properties of the data with respect to certain transformations. The augmented data can thus cover an unexplored input space, avoid overfitting and improve the generalization of the model. In this Ph.D, we will propose and evaluate a new approach for textual data augmentation.These two contributions will be evaluated on different textual datasets in the medical domain
Gaudier, Fabrice. "Modélisation par réseaux de neurones : application à la gestion du combustible dans un réacteur". Cachan, Ecole normale supérieure, 1999. http://www.theses.fr/1999DENS0009.
Pełny tekst źródłaKirchhofer, Simon. "Conception d'une prothèse bio-inspirée commandée par réseaux de neurones exploitant les signaux électromyographiques". Thesis, Université Clermont Auvergne (2017-2020), 2020. http://www.theses.fr/2020CLFAC058.
Pełny tekst źródłaResearch on upper-body prosthetic device is commonly divided in two categories: The prosthesis mechatronic conception and the human-machine interface dedicated to the control. This PhD thesis aims to bring together these two fields of research. The first step deals with control signals. Thus, a database containing electromyographic sequences and vision based joint coordinate measurements was created. Then, an artificial neural network achieves the motion estimation from electromyographic sequences. Accordingly, an under-actuated bio-inspired hand architecture is proposed to copy an organic hand motion while ensuring a grasping force distribution. This innovative approach allows to optimize the synergies imitation and proposes a control more intuitive for active prosthesis users
Rivollet, Fabien. "Etude des propriétés volumétriques (PVT) d'hydrocarbures légers (C1-C4), du dioxyde de carbone et de l'hydrogène sulfuré. Mesures par densimétrie à tube vibrant et modélisation". Phd thesis, École Nationale Supérieure des Mines de Paris, 2005. http://pastel.archives-ouvertes.fr/pastel-00002603.
Pełny tekst źródłaMichaud, Jean-Baptiste. "Efficacité de détection en tomographie d'émission par positrons: une approche par intelligence artificielle". Thèse, Université de Sherbrooke, 2014. http://savoirs.usherbrooke.ca/handle/11143/5284.
Pełny tekst źródłaThiaw, Lamine. "Identification de systèmes dynamiques non linéaires par réseaux de neurones et multimodèles". Phd thesis, Université Paris XII Val de Marne, 2008. http://tel.archives-ouvertes.fr/tel-00399469.
Pełny tekst źródłaVIALA, JEAN-RENAUD. "Apprentissage de reseaux de neurones en couches par la regle de retropropagation du gradient : developpement d'un algorithme competitif pour la compression et la segmentation d'images". Paris 6, 1990. http://www.theses.fr/1990PA066802.
Pełny tekst źródłaCharest, Jonathan. "Système intelligent de détection et diagnostic de fautes en tomographie d'émission par positrons". Thèse, Université de Sherbrooke, 2017. http://hdl.handle.net/11143/11628.
Pełny tekst źródłaLauret, Pierre. "Modélisation de la dispersion atmosphérique sur un site industriel par combinaison d’automates cellulaires et de réseaux de neurones". Thesis, Saint-Etienne, EMSE, 2014. http://www.theses.fr/2014EMSE0745/document.
Pełny tekst źródłaAtmospheric dispersion of hazardous materials is an event that could lead to serious consequences. Atmospheric dispersion is studied in particular in this work. Modeling of atmospheric dispersion is an important tool to anticipate industrial accidents. The objective of this work was to develop a model that is both fast and accurate, considering the dispersion in the near field on an industrial site. The approach developed is based on models from artificial intelligence: neural networks and cellular automata. Using neural networks requires training a database typical of the phenomenon, CFD k-ϵ simulations in this work. Training the neural network is carried out by identifying the important parameters: database sampling and network architecture. Three methodologies are developed:The first method estimates the continuous dispersion in free field by neural networks.The second method uses the neural network as a transition rule of the cellular automaton to estimate puff evolution in the free field.The third method divides the problem: the flow calculation is performed by the neural network and the calculation of the dispersion is realized by solving the advection diffusion equation to estimate the evolution of a cloud around a cylindrical obstacle. For the three methods, assessment of the generalization capabilities of the neural network has been validated on a test database and on unlearned cases. A comparison between developed method and CFD simulations is done on unlearned cases in order to validate them. Simulations computing time are low according to crisis duration. Application to real data should be developed to make these models operational
Chane, Kuang Sang Laurent. "Stratégie de contrôle hybride d'un magnétron verrouillé par injection pour un Transport d'Energie Sans Fil par onde hyperfréquence". Phd thesis, Université de la Réunion, 2002. http://tel.archives-ouvertes.fr/tel-00464105.
Pełny tekst źródłaRude, Julien. "Développement d'un modèle statistique neuronal pour la description fine de la pollution atmosphérique par le dioxyde d'azote : application à la région parisienne". Thesis, Paris Est, 2008. http://www.theses.fr/2008PEST0005.
Pełny tekst źródłaRésumé anglais manquant
Bouju, Alain. "Etiquetage et poursuite de points caractéristiques d'un objet 3D par des méthodes connexionistes". Toulouse, ENSAE, 1993. http://www.theses.fr/1993ESAE0017.
Pełny tekst źródłaMalo, Alexandre. "Chargement dynamique par composants pour réseaux de capteurs adaptables". Mémoire, Université de Sherbrooke, 2013. http://hdl.handle.net/11143/6194.
Pełny tekst źródłaMorozkin, Pavel. "Design and implementation of image processing and compression algorithms for a miniature embedded eye tracking system". Electronic Thesis or Diss., Sorbonne université, 2018. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2018SORUS435.pdf.
Pełny tekst źródłaHuman-Machine Interaction (HMI) progressively becomes a part of coming future. Being an example of HMI, embedded eye tracking systems allow user to interact with objects placed in a known environment by using natural eye movements. The EyeDee™ portable eye tracking solution (developed by SuriCog) is an example of an HMI-based product, which includes Weetsy™ portable wire/wireless system (including Weetsy™ frame and Weetsy™ board), π-Box™ remote smart sensor and PC-based processing unit running SuriDev eye/head tracking and gaze estimation software, delivering its result in real time to a client’s application through SuriSDK (Software Development Kit). Due to wearable form factor developed eye-tracking system must conform to certain constraints, where the most important are low power consumption, low heat generation low electromagnetic radiation, low MIPS (Million Instructions per Second), as well as support wireless eye data transmission and be space efficient in general. Eye image acquisition, finding of the eye pupil ROI (Region Of Interest), compression of ROI and its wireless transmission in compressed form over a medium are very beginning steps of the entire eye tracking algorithm targeted on finding coordinates of human eye pupil. Therefore, it is necessary to reach the highest performance possible at each step in the entire chain. In contrast with state-of-the-art general-purpose image compression systems, it is possible to construct an entire new eye tracking application-specific image processing and compression methods, approaches and algorithms, design and implementation of which are the goal of this thesis
Cappelaere, Charles-Henri. "Estimation du risque de mort subite par arrêt cardiaque a l'aide de méthodes d'apprentissage artificiel". Thesis, Paris 6, 2014. http://www.theses.fr/2014PA066014/document.
Pełny tekst źródłaImplantable cardioverter defibrillators (ICD) have been prescribed for prophylaxis since the early 2000?s, for patients at high risk of SCD. Unfortunately, most implantations to date appear unnecessary. This result raises an important issue because of the perioperative and postoperative risks. Thus, it is important to improve the selection of the candidates to ICD implantation in primary prevention. Risk stratification for SCD based on Holter recordings has been extensively performed in the past, without resulting in a significant improvement of the selection of candidates to ICD implantation. The present report describes a nonlinear multivariate analysis of Holter recording indices. We computed all the descriptors available in the Holter recordings present in our database. The latter consisted of labelled Holter recordings of patients equipped with an ICD in primary prevention, a fraction of these patients received at least one appropriate therapy from their ICD during a 6-month follow-up. Based on physiological knowledge on arrhythmogenesis, feature selection was performed, and an innovative procedure of classifier design and evaluation was proposed. The classifier is intended to discriminate patients who are really at risk of sudden death from patients for whom ICD implantation does not seem necessary. In addition, we designed an ad hoc classifier that capitalizes on prior knowledge on arrhythmogenesis. We conclude that improving prophylactic ICD-implantation candidate selection by automatic classification from Holter recording features may be possible. Nevertheless, that statement should be supported by the study of a more extensive and appropriate database
Abou, Rjeily Yves. "Management and sustainability of urban drainage systems within smart cities". Thesis, Lille 1, 2016. http://www.theses.fr/2016LIL10085/document.
Pełny tekst źródłaThis work presents the Real Time Control (RTC) of Urban Drainage Systems (UDS) within smart cities. RTC requires to understand the UDS operation and to perform simulations on measured, forecasted and synthetic events. Therefore, a Real Time Monitoring system (RTM) was implemented on the experimental site, and combined to a simulation model. A model auto-calibration process and hydraulic boundary conditions forecast system were developed, in order to simulate the hydrologic-hydraulic response. Aiming to protect the citizens and mitigate flooding consequences, the RTC was composed of a flooding forecast system followed by a dynamic management strategy. The proposed concept and methodologies were applied and evaluated on the Lille 1 University Campus, within the SunRise project. RTM was found very helpful in understanding the system operation and calibrating the simulation model. Genetic Algorithm followed by Pattern Search formed an effective auto-calibration procedure for the simulation model. NARX Neural Network was developed and validated for forecasting hydraulic boundary conditions. Once understanding the UDS operations, the RTC was developed. NARX Neural Network was found capable to forecast flooding events. A dynamic management for increasing a tank retention capacity, was studied based on calculating a Valve State Schedule, and results were satisfying by using Genetic Algorithm and a modified form of Artificial Bee Colony, as optimization methods. A qualitative management was also proposed and tested for verifying its potential in reducing flooding volumes
Dambreville, Romain. "Prévision du rayonnement solaire global par télédétection pour la gestion de la production d’énergie photovoltaïque". Thesis, Grenoble, 2014. http://www.theses.fr/2014GRENT078/document.
Pełny tekst źródłaTo handle the integration of intermittent energies to the existing grid,managers require more and more acurate tools to forecast the primary resources. This thesisfocuses on the very short term forecast of the global horizontal irradiance (GHI), maininput for most photovoltaic power plant. We chose to use both ground based images fromhemispherical cameras and satellite images to provide a forecating tool. In the first handwe present a novel appraoch to estimate the GHI using ground based images. On secondhand, we propose several satellite based methods to forecast the GHI up to one hour. Finally,we developp a new method allowing us to merge both data in order to benefit from theirrespective advantages. All the methods were tested against real data acquired on the SIRTAsite, Polytechnique campus
Belhadj-Mohamed, Bilel. "Systèmes neuromorphiques temps réel : contribution à l’intégration de réseaux de neurones biologiquement réalistes avec fonctions de plasticité". Thesis, Bordeaux 1, 2010. http://www.theses.fr/2010BOR14051/document.
Pełny tekst źródłaThis work has been supported by the European FACETS project. Within this project, we contribute in developing hardware mixed-signal devices for real-time spiking neural network simulation. These devices may potentially contribute to an improved understanding of learning phenomena in the neo-cortex. Neuron behaviours are reproduced using analog integrated circuits which implement Hodgkin-Huxley based models. In this work, we propose a digital architecture aiming to connect many neuron circuits together, forming a network. The inter-neuron connections are reconfigurable and can be ruled by a plasticity model. The architecture is mapped onto a commercial programmable circuit (FPGA). Many methods are developed to optimize the utilisation of hardware resources as well as to meet real-time constraints. In particular, a token-passing communication protocol has been designed and developed to guarantee real-time aspects of the dialogue between several FPGAs in a multiboard system allowing the integration of a large number of neurons. The global system is able to run neural simulations in biological real-time with high degree of realism, and then can be used by neurobiologists and computer scientists to carry on neural experiments
Lafont, Damien. "Prise en compte des hétérogénéités dans la restitution de l'eau nuageuse et des précipitations par radiométrie micro-onde passive". Phd thesis, Université Blaise Pascal - Clermont-Ferrand II, 2005. http://tel.archives-ouvertes.fr/tel-00009275.
Pełny tekst źródła