Dissertations / Theses on the topic 'Réseaux de neurones embarqués'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Réseaux de neurones embarqués.'
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.
Pompougnac, Hugo. "Spécification et compilation de réseaux de neurones embarqués." Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS436.
Full textIn this thesis, we propose an approach for the joint specification and compilation of both High-Performance Computing (HPC) and Real-Time Embedded (RTE) aspects of a system. Our approach is based on a formal, algorithmic and tooled integration between two formalisms underlying a large part of works in HPC and RTE fields: the SSA formalism and the synchronous dataflow language Lustre. The SSA formalism is a key component of many HPC compilers, including those used by Machine Learning frameworks such as TensorFlow or PyTorch. The Lustre language is a key component of implementation processes of critical embedded systems in avionics or rail transportation
Fernandez, Brillet Lucas. "Réseaux de neurones CNN pour la vision embarquée." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM043.
Full textRecently, 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
Godin, Christelle. "Contributions à l'embarquabilité et à la robustesse des réseaux de neurones en environnement radiatif : apprentissage constructif : neurones à impulsions." École nationale supérieure de l'aéronautique et de l'espace (Toulouse ; 1972-2007), 2000. http://www.theses.fr/2000ESAE0013.
Full textMamalet, Franck. "Adéquation algorithme-architecture pour les réseaux de neurones à convolution : application à l'analyse de visages embarquée." Thesis, Lyon, INSA, 2011. http://www.theses.fr/2011ISAL0068.
Full textProliferation of image sensors in many electronic devices, and increasing processing capabilities of such sensors, open a field of exploration for the implementation and optimization of complex image processing algorithms in order to provide embedded vision systems. This work is a contribution in the research domain of algorithm-architecture matching. It focuses on a class of algorithms called convolution neural network (ConvNet) and its applications in embedded facial analysis. The facial analysis framework, introduced by Garcia et al., was chosen for its state of the art performances in detection/recognition, and also for its homogeneity based on ConvNets. The first contribution of this work deals with an adequacy study of this facial analysis framework with embedded processors. We propose several algorithmic adaptations of ConvNets, and show that they can lead to significant speedup factors (up to 700) on an embedded processor for mobile phone, without performance degradation. We then present a study of ConvNets parallelization capabilities, through N. Farrugia's PhD work. A coarse-grain parallelism exploration of ConvNets, followed by study of internal scheduling of elementary processors, lead to a parameterized parallel architecture on FPGA, able to detect faces at more than 10 VGA frames per second. Finally, we propose an extension of these studies to the learning phase of neural networks. We analyze several hypothesis space restrictions for ConvNets, and show, on a case study, that classification rate performances are almost the same with a training time divided by up to five
Abderrahmane, Nassim. "Impact du codage impulsionnel sur l’efficacité énergétique des architectures neuromorphiques." Thesis, Université Côte d'Azur, 2020. http://www.theses.fr/2020COAZ4082.
Full textNowadays, Artificial Intelligence (AI) is a widespread concept applied to many fields such as transportation, medicine and autonomous vehicles. The main AI algorithms are artificial neural networks, which can be divided into two families: Spiking Neural Networks (SNNs), which are bio-inspired models resulting from neuroscience, and Analog Neural Networks (ANNs), which result from machine learning. The ANNs are experiencing unprecedented success in research and industrial fields, due to their recent successes in many application contexts such as image classification and object recognition. However, they require considerable computational capacity for their deployment which is not adequate to very constrained systems such as 'embedded systems'. To overcome these limitations, many researchers are interested in brain-inspired computing, which would be the perfect alternative to conventional computers based on the Von Neumann architecture (CPU/GPU). This paradigm meets computing performance but not energy efficiency requirements. Hence, it is necessary to design neuromorphic hardware circuits adaptable to parallel and distributed computing. In this context, we have set criteria in terms of accuracy and hardware implementation cost to differentiate the two neural families (SNNs and ANNs). In the case of simple network topologies, we conducted a study that has shown that the spiking models have significant gains in terms of hardware cost when compared to the analog networks, with almost similar prediction accuracies. Therefore, the objective of this thesis is to design a generic neuromorphic architecture that is based on spiking neural networks. To this end, we have set up a three-level design flow for exploring and implementing neuromorphic architectures.In an energy efficiency context, a thorough exploration of different neural coding paradigms for neural data representation in SNNs has been carried out. Moreover, new derivative versions of rate-based coding have been proposed that aim to get closer to the activity produced by temporal coding, which is characterized by a reduced number of spikes propagating in the network. In this way, the number of spikes can be reduced so that the number of events to be processed in the SNNs gets smaller. The aim in doing this approach is to reduce the hardware architecture's energy consumption. The proposed coding approaches are: First Spike, which is characterized using at most one single spike to present an input data, and Spike Select, which allows to regulate and minimize the overall spiking activity in the SNN.In the RTL design exploration, we quantitatively compared three SNN architectural models having different levels of computing parallelism and multiplexing. Using Spike Select coding results in a distribution regulation of the spiking data, with most of them generated within the first layer and few of them propagate into the deep layers. Such distribution benefits from a so-called 'hybrid architecture' that includes a fully-parallel part for the first layer and multiplexed parts to the other layers. Therefore, combining the Spike Select and the Hybrid Architecture would be an effective solution for embedded AI applications, with an efficient hardware and latency trade-off.Finally, based on the architectural and neural choices resulting from the previous exploration, we have designed a final event-based architecture dedicated to SNNs supporting different neural network types and sizes. The architecture supports the most used layers: convolutional, pooling and fully-connected. Using this architecture, we will be able to compare analog and spiking neural networks on realistic applications and to finally conclude about the use of SNNs for Embedded Artificial Intelligence
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.
Full textIn 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
Pinna, Andrea. "Conception d'une rétine connexionniste : du capteur au système de vision sur puce." Paris 6, 2003. http://www.theses.fr/2003PA066566.
Full textVeniat, Tom. "Neural Architecture Search under Budget Constraints." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS443.
Full textThe recent increase in computation power and the ever-growing amount of data available ignited the rise in popularity of deep learning. However, the expertise, the amount of data, and the computing power necessary to build such algorithms as well as the memory footprint and the inference latency of the resulting system are all obstacles preventing the widespread use of these methods. In this thesis, we propose several methods allowing to make a step towards a more efficient and automated procedure to build deep learning models. First, we focus on learning an efficient architecture for image processing problems. We propose a new model in which we can guide the architecture learning procedure by specifying a fixed budget and cost function. Then, we consider the problem of sequence classification, where a model can be even more efficient by dynamically adapting its size to the complexity of the signal to come. We show that both approaches result in significant budget savings. Finally, we tackle the efficiency problem through the lens of transfer learning. Arguing that a learning procedure can be made even more efficient if, instead of starting tabula rasa, it builds on knowledge acquired during previous experiences. We explore modular architectures in the continual learning scenario and present a new benchmark allowing a fine-grained evaluation of different kinds of transfer
Osman, Ousama. "Méthodes de diagnostic en ligne, embarqué et distribué dans les réseaux filaires complexes." Thesis, Université Clermont Auvergne (2017-2020), 2020. http://www.theses.fr/2020CLFAC038.
Full textThe research conducted in this thesis focuses on the diagnosis of complex wired networks using distributed reflectometry. It aims to develop new distributed diagnostic techniques for complex networks that allow data fusion as well as communication between reflectometers to detect, locate and characterize electrical faults (soft and hard faults). This collaboration between reflectometers solves the problem of fault location ambiguity and improves the quality of diagnosis. The first contribution is the development of a graph theory-based method for combining data between distributed reflectometers, thus facilitating the location of the fault. Then, the amplitude of the reflected signal is used to identify the type of fault and estimate its impedance. The latter is based on the regeneration of the signal by compensating for the degradation suffered by the diagnosis signal during its propagation through the network. The second contribution enables data fusion between distributed reflectometers in complex networks affected by multiple faults. To achieve this objective, two methods have been proposed and developed: the first is based on genetic algorithms (GA) and the second is based on neural networks (RN). These tools combined with distributed reflectometryallow automatic detection, location, and characterization of several faults in different types and topologies of wired networks. The third contribution proposes the use of information-carrying diagnosis signal to integrate communication between distributed reflectometers. It properly uses the phases of the MCTDR multi-carrier signal to transmit data. This communication ensures the exchange of useful information (such as fault location and amplitude) between reflectometers on the state of the cables, thus enabling data fusion and unambiguous fault location. Interference problems between the reflectometers are also addressed when they simultaneously inject their test signals into the network. These studies illustrate the efficiency and applicability of the proposed methods. They also demonstrate their potential to improve the performance of the current wired diagnosis systems to meet the need and the problem of detecting and locating faults that manufacturers and users face today in electrical systems to improve their operational safety
Castellanos, SÁnchez Claudio. "Modèle connexionniste neuromimétique pour la perception visuelle embarquée du mouvement." Phd thesis, Université Henri Poincaré - Nancy I, 2005. http://tel.archives-ouvertes.fr/tel-00011483.
Full textLe modèle connexionniste proposé pour la perception visuelle du mouvement est constitué de trois modules : le premier opère un filtrage spatio-temporel causal issu des filtres de Gabor et inspiré des réponses des cellules simples du cortex visuel primaire, V1. Le deuxième met en place un mécanisme distribué de fortes interactions localisées fondé sur un principe antagoniste inspiré de l'organisation en colonnes d'orientation dans V1. Finalement, en nous inspirant des propriétés des champs récepteurs des neurones de MT et MST (aire temporelle moyenne et supérieur moyenne, respectivement), nous intégrons les réponses du second module et les envoyons au troisième. Ce dernier fait émerger un seul objet en mouvement à travers l'évolution en différentes cartes des interactions latérales, en pro-action et en retro-action d'une population neuronale densément interconnectée selon le principe de la CNFT (Continuum Neural Field Theory). L'attention sur l'objet émergé nous permet donc de le suivre.
Abernot, Madeleine. "Digital oscillatory neural network implementation on FPGA for edge artificial intelligence applications and learning." Electronic Thesis or Diss., Université de Montpellier (2022-....), 2023. http://www.theses.fr/2023UMONS074.
Full textIn the last decades, the multiplication of edge devices in many industry domains drastically increased the amount of data to treat and the complexity of tasks to solve, motivating the emergence of probabilistic machine learning algorithms with artificial intelligence (AI) and artificial neural networks (ANNs). However, classical edge hardware systems based on von Neuman architecture cannot efficiently handle this large amount of data. Thus, novel neuromorphic computing paradigms with distributed memory are explored, mimicking the structure and data representation of biological neural networks. Lately, most of the neuromorphic paradigm research has focused on Spiking neural networks (SNNs), taking inspiration from signal transmission through spikes in biological networks. In SNNs, information is transmitted through spikes using the time domain to provide a natural and low-energy continuous data computation. Recently, oscillatory neural networks (ONNs) appeared as an alternative neuromorphic paradigm for low-power, fast, and efficient time-domain computation. ONNs are networks of coupled oscillators emulating the collective computational properties of brain areas through oscillations. The recent ONN implementations combined with the emergence of low-power compact devices for ONN encourage novel attention over ONN for edge computing. State-of-the-art ONN is configured as an oscillatory Hopfield network (OHN) with fully coupled recurrent connections to perform pattern recognition with limited accuracy. However, the large number of OHN synapses limits the scalability of ONN implementation and the ONN application scope. The focus of this thesis is to study if and how ONN can solve meaningful AI edge applications using a proof-of-concept of the ONN paradigm with a digital implementation on FPGA. First, it explores novel learning algorithms for OHN, unsupervised and supervised, to improve accuracy performances and to provide continual on-chip learning. Then, it studies novel ONN architectures, taking inspiration from state-of-the-art layered ANN models, to create cascaded OHNs and multi-layer ONNs. Novel learning algorithms and architectures are demonstrated with the digital design performing edge AI applications, from image processing with pattern recognition, image edge detection, feature extraction, or image classification, to robotics applications with obstacle avoidance
Seznec, Mickaël. "From the algorithm to the targets, optimization flow for high performance computing on embedded GPUs." Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG074.
Full textCurrent digital processing algorithms require more computing power to achieve more accurate results and process larger data. In the meantime, hardware architectures are becoming more specialized, with highly efficient accelerators designed for specific tasks. In this context, the path of deployment from the algorithm to the implementation becomes increasingly complex. It is, therefore, crucial to determine how algorithms can be modified to take advantage of new hardware capabilities. Our study focused on graphics processing units (GPUs), a massively parallel processor. Our algorithmic work was done in the context of radio-astronomy or optical flow estimation and consisted of finding the best adaptation of the software to the hardware. At the level of a mathematical operator, we modified the traditional image convolution algorithm to use the matrix units and showed that its performance doubles for large convolution kernels. At a broader method level, we evaluated linear solvers for the combined local-global optical flow to find the most suitable one on GPU. With additional optimizations, such as iteration fusion or memory buffer re-utilization, the method is twice as fast as the initial implementation, running at 60 frames per second on an embedded platform (30 W). Finally, we also pointed out the interest of this hardware-aware algorithm design method in the context of deep neural networks. For that, we showed the hybridization of a convolutional neural network for optical flow estimation with a pre-trained image classification network, MobileNet, that was initially designed for efficient image classification on low-power platforms
Courdouan, Elie. "Développement d'un module BMS multi-sources harvesting." Electronic Thesis or Diss., Aix-Marseille, 2019. http://www.theses.fr/2019AIXM0633.
Full textWith the development of mobile applications, such as telecoms, IoT and home automation, embedded systems have shown an exponential growth over the past years. The main characteristic of these newly build systems is to combine high processing capabilities and extended operational autonomy. Unfortunately, these parameters are fundamentally opposed and hardware designer facing this issue by limiting processing capability to ensure enough autonomy. To solve this autonomy problem, newly architectures choose to implement an energy harvesting stage with one or more sources. As part of this industrial thesis, the study has been carried out on the design of an optimized energy harvesting module using one or more sources. Two directions were found to increase the quantity of harvested energy: - Interfacing multiple harvester from complementary source in an industrialized architecture - Optimization of produced energy from each source by using next-generation algorithms of Maximum Power Point Tracking. These algorithms are optimized thanks to technical advances made in the field of Deep Learning and the availability of more efficient low power microcontroller. The final goal of this study is to deploy a low cost wide area network of sensors with enhanced or infinite autonomy
Masure, Loïc. "Towards a better comprehension of deep learning for side-channel analysis." Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS443.
Full textThe recent improvements in deep learning (DL) have reshaped the state of the art of side-channel attacks (SCA) in the field of embedded security. Yet, their ``black-box'' aspect nowadays prevents the identification of the vulnerabilities exploited by such adversaries. Likewise, it is hard to conclude from the outcomes of these attacks about the security level of the target device. All those reasons have made the SCA community skeptical about the interest of such attack techniques in terms of security evaluation. This thesis proposes to draw a better understanding of deep learning for SCA. We show how the training of such estimators can be analyzed through the security evaluation prism, in order to estimate a priori the complexity of an SCA, without necessarily mounting the attack. We also remark on simulated experiments that those models, trained without prior knowledge about the counter-measures added to protect the target device, can reach the theoretical security bounds expected by the literature. This validates the relevance or not of some counter-measures such as secret-sharing or hiding, against DL-based SCA. Furthermore, we explain how to exploit a trained neural network to efficiently characterize the information leakage in the observed traces, even in presence of counter-measures making other classical charactertization techniques totally inefficient. This enables a better understanding of the leakage implicitly exploited by the neural network, and allows to refine the evaluator's diagnosis, in order to propose corrections to the developer
Morozkin, 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.
Full textHuman-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
Caron, Louis-Charles. "Implémentation matérielle d'un réseau de neurones à décharges pour synchronisation rapide." Mémoire, Université de Sherbrooke, 2011. http://savoirs.usherbrooke.ca/handle/11143/1603.
Full textAles, Achour. "Etude CEM des réseaux embarqués." Thesis, Université Grenoble Alpes (ComUE), 2015. http://www.theses.fr/2015GREAT051.
Full textToday normative LISN EMC does not guarantee the proper functioning systematically. Safety is ensured by EMC margins often excessive. The system is therefore suboptimal Furthermore, the operation of the converters on the AN is not necessarily representative of the actual operation : the AN is not necessarily representative of the impedances of embedded networks . Thus , filtering of a converter can be optimized but on the AN is not necessarily optimal since it is a real network . The objective of this thesis is to advance the EMC modeling of embedded systems in order to predict behavior, and optimize the filter means
Wenzek, Didier. "Construction de réseaux de neurones." Phd thesis, Grenoble INPG, 1993. http://tel.archives-ouvertes.fr/tel-00343569.
Full textTsopze, Norbert. "Treillis de Galois et réseaux de neurones : une approche constructive d'architecture des réseaux de neurones." Thesis, Artois, 2010. http://www.theses.fr/2010ARTO0407/document.
Full textThe artificial neural networks are successfully applied in many applications. But theusers are confronted with two problems : defining the architecture of the neural network able tosolve their problems and interpreting the network result. Many research works propose some solutionsabout these problems : to find out the architecture of the network, some authors proposeto use the problem domain theory and deduct the network architecture and some others proposeto dynamically add neurons in the existing networks until satisfaction. For the interpretabilityproblem, solutions consist to extract rules which describe the network behaviour after training.The contributions of this thesis concern these problems. The thesis are limited to the use of theartificial neural networks in solving the classification problem.In this thesis, we present a state of art of the existing methods of finding the neural networkarchitecture : we present a theoritical and experimental study of these methods. From this study,we observe some limits : difficulty to use some method when the knowledges are not available ;and the network is seem as ’black box’ when using other methods. We a new method calledCLANN (Concept Lattice-based Artificial Neural Network) which builds from the training dataa semi concepts lattice and translates this semi lattice into the network architecture. As CLANNis limited to the two classes problems, we propose MCLANN which extends CLANN to manyclasses problems.A new method of rules extraction called ’MaxSubsets Approach’ is also presented in thisthesis. Its particularity is the possibility of extracting the two kind of rules (If then and M-of-N)from an internal structure.We describe how to explain the MCLANN built network result aboutsome inputs
Valenti, Giacomo. "Secure, efficient automatic speaker verification for embedded applications." Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS471.
Full textThis industrial CIFRE PhD thesis addresses automatic speaker verification (ASV) issues in the context of embedded applications. The first part of this thesis focuses on more traditional problems and topics. The first work investigates the minimum enrolment data requirements for a practical, text-dependent short-utterance ASV system. Contributions in part A of the thesis consist in a statistical analysis whose objective is to isolate text-dependent factors and prove they are consistent across different sets of speakers. For very short utterances, the influence of a specific text content on the system performance can be considered a speaker-independent factor. Part B of the thesis focuses on neural network-based solutions. While it was clear that neural networks and deep learning were becoming state-of-the-art in several machine learning domains, their use for embedded solutions was hindered by their complexity. Contributions described in the second part of the thesis comprise blue-sky, experimental research which tackles the substitution of hand-crafted, traditional speaker features in favour of operating directly upon the audio waveform and the search for optimal network architectures and weights by means of genetic algorithms. This work is the most fundamental contribution: lightweight, neuro-evolved network structures which are able to learn from the raw audio input
Boisard, Olivier. "Optimization and implementation of bio-inspired feature extraction frameworks for visual object recognition." Thesis, Dijon, 2016. http://www.theses.fr/2016DIJOS016/document.
Full textIndustry has growing needs for so-called “intelligent systems”, capable of not only ac-quire data, but also to analyse it and to make decisions accordingly. Such systems areparticularly useful for video-surveillance, in which case alarms must be raised in case ofan intrusion. For cost saving and power consumption reasons, it is better to perform thatprocess as close to the sensor as possible. To address that issue, a promising approach isto use bio-inspired frameworks, which consist in applying computational biology modelsto industrial applications. The work carried out during that thesis consisted in select-ing bio-inspired feature extraction frameworks, and to optimize them with the aim toimplement them on a dedicated hardware platform, for computer vision applications.First, we propose a generic algorithm, which may be used in several use case scenarios,having an acceptable complexity and a low memory print. Then, we proposed opti-mizations for a more global framework, based on precision degradation in computations,hence easing up its implementation on embedded systems. Results suggest that whilethe framework we developed may not be as accurate as the state of the art, it is moregeneric. Furthermore, the optimizations we proposed for the more complex frameworkare fully compatible with other optimizations from the literature, and provide encourag-ing perspective for future developments. Finally, both contributions have a scope thatgoes beyond the sole frameworks that we studied, and may be used in other, more widelyused frameworks as well
Ahmed, Nacer Abdelaziz. "Analyse et dimensionnement de réseaux hétérogènes embarqués." Phd thesis, Toulouse, INPT, 2018. http://oatao.univ-toulouse.fr/20115/1/AHMEDNACER_Abdelaziz.pdf.
Full textVoegtlin, Thomas. "Réseaux de neurones et auto-référence." Lyon 2, 2002. http://theses.univ-lyon2.fr/documents/lyon2/2002/voegtlin_t.
Full textThe purpose of this thesis is to present a class of unsupervised learning algorithms for recurrent networks. In the first part (chapters 1 to 4), I propose a new approach to this question, based on a simple principle: self-reference. A self-referent algorithm is not based on the minimization of an objective criterion, such as an error function, but on a subjective function, that depends on what the network has previously learned. An example of a supervised recurrent network where learning is self-referent is the Simple Recurrent Network (SRN) by Elman (1990). In the SRN, self-reference is applied to the supervised error back-propagation algorithm. In this aspect, the SRN differs from other generalizations of back-propagation to recurrent networks, that use an objective criterion, such as Back-Propagation Through Time, or Real-Time Recurrent Learning. In this thesis, I show that self-reference can be combined with several well-known unsupervised learning methods: the Self-Organizing Map (SOM), Principal Components Analysis (PCA), and Independent Components Analysis (ICA). These techniques are classically used to represent static data. Self-reference allows one to generalize these techniques to time series, and to define unsupervised learning algorithms for recurrent networks
Teytaud, Olivier. "Apprentissage, réseaux de neurones et applications." Lyon 2, 2001. http://theses.univ-lyon2.fr/documents/lyon2/2001/teytaud_o.
Full textCôté, Marc-Alexandre. "Réseaux de neurones génératifs avec structure." Thèse, Université de Sherbrooke, 2017. http://hdl.handle.net/11143/10489.
Full textCagli, Eleonora. "Feature Extraction for Side-Channel Attacks." Electronic Thesis or Diss., Sorbonne université, 2018. http://www.theses.fr/2018SORUS295.
Full textCryptographic integrated circuits may be vulnerable to attacks based on the observation of information leakages conducted during the cryptographic algorithms' executions, the so-called Side-Channel Attacks. Nowadays the presence of several countermeasures may lead to the acquisition of signals which are at the same time highly noisy, forcing an attacker or a security evaluator to exploit statistical models, and highly multi-dimensional, letting hard the estimation of such models. In this thesis we study preprocessing techniques aiming at reducing the dimension of the measured data, and the more general issue of information extraction from highly multi-dimensional signals. The first works concern the application of classical linear feature extractors, such as Principal Component Analysis and Linear Discriminant Analysis. Then we analyse a non-linear generalisation of the latter extractor, obtained through the application of a « Kernel Trick », in order to let such preprocessing effective in presence of masking countermeasures. Finally, further generalising the extraction models, we explore the deep learning methodology, in order to reduce signal preprocessing and automatically extract sensitive information from rough signal. In particular, the application of the Convolutional Neural Network allows us to perform some attacks that remain effective in presence of signal desynchronisation
Mauclair, Cédric. "Une approche statistique des réseaux temps réel embarqués." Thesis, Toulouse, ISAE, 2013. http://www.theses.fr/2013ESAE0016/document.
Full textSince a few years, communication networks deployed in aircrafts are ever larger and ever more complex. These digital buses multiplex different data streams in order to save cabling, but this causes delays on transmissions.The work presented here is based on a statistical evaluation of the worst case transit time of an embedded network of the AFDX type. It consists in associating a worst case computation with a complete distribution of the transit times in order, among other things, to appreciatethe pessimism of worst case approaches. The methods are also applicable to a set of realtime tasks. This work contributes three major results. First, an original method to evaluate the distribution of the transit time through an AFDX switch, based on the symbolic enumeration of the scheduling scenarios in the waiting queues of the switch. Second, an effective algorithm to compute the delays encountered by periodic messages/ tasks when initial offsets are known. Delays thus computed are exact and so is the delays distribution. Third, the computation of the delays distribution encountered by messages/tasks in a general case using a Monte Carlo based statistical method. Initial offsets are randomised and feed the preceding algorithm
Mezni, Anis. "Ordonnancement des réseaux de capteurs sans fil embarqués." Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI030.
Full textWireless Sensor networks are attracted many activities of research and development during the last decade. Yet, the distributed behavior of a WSN remains centered on two main objectives: sensing and routing. This thesis advocates the introduction of an additional feature, which can be considered interesting from a functional point of view and potentially from the power consumption one: starting from a designer-specified requirement, implement a multiple level synergy between (groups of) nodes, based on adequate interaction. This is achieved by automatic generation and distribution of correct-by-construction code, relying on the Supervisory Control Theory. The Discrete Controller Synthesis (DCS) technique is an application of this theoretic framework. In this thesis, we show how DCS can be used for WSN. Thus, its potential is at two levels. The intra-cluster scheduling of a redundant group of sensors with specifications expressing the mutual exclusion during the activation of a sensor within a cluster, essential to save the energy within the network and then a multicriteria automatic generation of an optimal routing functionality. Specifically, an optimal path should have both a minimal length and go through nodes having maximal residual energy. The cited formal tools lean on a modelling approach based on communicating finite state machines (CFSM). The scientific challenges are generally related to the nature of the WSN as well as to its size. The DCS can only generates a monoblock controllers, while the WSN’s behavior is essentially distributed. The issue is how to distribute a global controller, who appears in the form of a logical constraint expressed on the global state of the network, into local controllers while adding the necessary synchronization to guarantee a distributed functioning equivalent to the initially generated controller
Liutanakul, Pisit. "Stabilité des réseaux embarqués : interactions Puissance - Structure - Commande." Thesis, Vandoeuvre-les-Nancy, INPL, 2007. http://www.theses.fr/2007INPL006N/document.
Full textBecause of the high efficiency of the power electronic converters, ideal regulation of their outputs makes the converter appears as a constant power load seen by its front end power stage. So they can be modeled as a negative resistance around an operating point. As a result, when such a converter is connected to a controlled or uncontrolled power source subsystem, the risk of instability has to be unpacked. To study the stability issue taken by such a system, we have detailed in a first step how to prove the local stability of Distributed Power System. The impedance criterions which are used to analysis the stability of cascaded systems are described. These criterions are applied in the case of two power electronics applications. The first one corresponds to a DC/DC switching converter with its input filter. The second one deals with the stability issues of a system constituted by an input filter and an inverter-motor drive system. In the second part of the thesis, a non linear global control of a cascaded power electronic system is investigated in order to ensure the stability of the whole system with a minimization of its passive components. To uncouple the control of all the outputs variables and ensure the system stability, an I/O linearization technique is proposed. Thanks to the use of a sliding controller, the resulting control architecture is robust as regard to parameters variations and allows a significant diminution of the passive component size
Jodouin, Jean-François. "Réseaux de neurones et traitement du langage naturel : étude des réseaux de neurones récurrents et de leurs représentations." Paris 11, 1993. http://www.theses.fr/1993PA112079.
Full textBrette, Romain. "Modèles Impulsionnels de Réseaux de Neurones Biologiques." Phd thesis, Université Pierre et Marie Curie - Paris VI, 2003. http://tel.archives-ouvertes.fr/tel-00005340.
Full textTardif, Patrice. "Autostructuration des réseaux de neurones avec retards." Thesis, Université Laval, 2007. http://www.theses.ulaval.ca/2007/24240/24240.pdf.
Full textMaktoobi, Sheler. "Couplage diffractif pour réseaux de neurones optiques." Thesis, Bourgogne Franche-Comté, 2020. http://www.theses.fr/2020UBFCD019.
Full textPhotonic networks with high performance can be considered as substrates for future computing systems. In comparison with electronics, photonic systems have substantial privileges, for instance the possibility of a fully parallel implementation of networks. Recently, neural networks have moved into the center of attention of the photonic community. One of the most important requirements for parallel large-scale photonic networks is to realize the connectivities. Diffraction is considered as a method to process the connections between the nodes (coupling) in optical neural networks. In the current thesis, we evaluate the scalability of a diffractive coupling in more details as follow:First, we begin with a general introductions for artificial intelligence, machine learning, artificial neural network and photonic neural networks. To establish a working neural network, learning rules are an essential part to optimize a configuration for obtaining a low error from the system, hence learning rules are introduced (Chapter 1). We investigate the fundamental concepts of diffractive coupling in our spatio-temporal reservoir. In that case, theory of diffraction is explained. We use an analytical scheme to provide the limits for the size of diffractive networks which is a part of our photonic neural network (Chapter 2). The concepts of diffractive coupling are investigated experimentally by two different experiments to confirm the analytical limits and to obtain maximum number of nodes which can be coupled in the photonic network (Chapter 3). Numerical simulations for such an experimental setup is modeled in two different schemes to obtain the maximum size of network numerically, which approaches a surface of 100 mm2 (Chapter 4). Finally, the complete photonic neural network is demonstrated. We design a spatially extended reservoir for 900 nodes. Consequently, our system generalizes the prediction for the chaotic Mackey–Glass sequence (Chapter 5)
Ouali, Jamel. "Architecture intégrée flexible pour réseaux de neurones." Grenoble INPG, 1991. http://www.theses.fr/1991INPG0035.
Full textCharara, Hussein. "Évaluation des performances temps réel de réseaux embarqués avioniques." Toulouse, INPT, 2007. http://ethesis.inp-toulouse.fr/archive/00000527/.
Full textThe recent aircrafts need to accommodate more passengers or freight, with increasing safety and comfort conditions. The new embedded systems imply a large burst in the number and the volume of exchanged data. The avionic data buses cannot cope anymore with these new communications needs. Both Airbus and Boeing made the choice to replace these buses with a network using the Switched Ethernet technology. The main contribution of this thesis is a method, based on a simulation model, which evaluates the performances of this type of networks. We also propose approaches for the traffic classification allowing the reduction of the simulation space, in order to lead to a more refined analysis of the network behaviour. The results of these simplifications enabled us to establish a generic simulation model and to acquire distributions of the end to end delay for the majority of the virtual links, having to be studied on the selected real avionic configuration
Sambou, Bafing Cyprien. "Systèmes communicants sans fil pour les réseaux avioniques embarqués." Thesis, Toulouse, INPT, 2012. http://www.theses.fr/2012INPT0040/document.
Full textThe object of our works concerns at the suggestion of hybrid architecture IEEE 802.11e / AFDX (Avionics Full Duplex switched ethernet) and the study of techniques allowing the interconnection of a wired avionic network AFDX and a wireless network IEEE802.11e for applications of maintenance the ground
Bigot, Pascal. "Utilisation des réseaux de neurones pour la télégestion des réseaux techniques urbains." Lyon 1, 1995. http://www.theses.fr/1995LYO10036.
Full textBeyrouthy, Taha. "Logique programmable asynchrone pour systèmes embarqués sécurisés." Grenoble INPG, 2009. http://www.theses.fr/2009INPG0137.
Full textThis thesis focuses on the design and the validation of an embedded FPGA dedicated to critical applications which require a high level of security and confidentiality. Nowadays FPGAs exhibit many weaknesses toward security: 1- They are not intended to efficiently support alternative styles of circuits such as asynchronous circuits. 2- The place and route flow is not completely manageable by the user in order to target our security goal. 3- They are not protected against side channel attacks such as DP A, EMA or DF A. Ln order to overcome these technological problems, the work presented in this thesis proposes an architecture that supports the programming of different styles of asynchronous circuits. Ln addition, it presents a secure programming system and a design that ensurcs a high-Ievel of security against the attacks mentioned above. Finally, the circuit prototype has been evaluated in order to validate the relevance of the proposed solutions
Koiran, Pascal. "Puissance de calcul des réseaux de neurones artificiels." Lyon 1, 1993. http://www.theses.fr/1993LYO19003.
Full textGraïne, Slimane. "Inférence grammaticale régulière par les réseaux de neurones." Paris 13, 1994. http://www.theses.fr/1994PA132020.
Full textLe, Fablec Yann. "Prévision de trajectoires d'avions par réseaux de neurones." Toulouse, INPT, 1999. http://www.theses.fr/1999INPT034H.
Full textCorne, Christophe. "Parallélisation de réseaux de neurones sur architecture distribuée." Mulhouse, 1999. http://www.theses.fr/1999MULH0583.
Full textHe, Bing. "Estimation paramétrique du signal par réseaux de neurones." Lille 1, 2002. https://pepite-depot.univ-lille.fr/RESTREINT/Th_Num/2002/50376-2002-75.pdf.
Full textGodary, Karen. "Validation temporelle de réseaux embarqués critiques et fiables pour l'automobiles." Lyon, INSA, 2004. http://theses.insa-lyon.fr/publication/2004ISAL0068/these.pdf.
Full textIn the automotive domain, the current tendency for the manufacturers is to replace hydraulic and mechanical systems by x-by-wire systems : electronic components communicating through a network. Two particular aspects of the reliability of this architectures are studied in this work: the temporal aspect and its fault tolerance. In order to guarantee the reliability of this critical systems, it is necessary to verify the respect of their constraints by validation. Works of this thesis is devoted to the temporal validation in presence of faults of a specific architecture dedicated to these systems: TTA (Time-Triggered Structure), and propose a methodology of validation for this architecture. For that, it was necessary to choose a modelling formalism which fits well to the characteristics of the architecture and its constraints, in particular on the temporal domain. A theoretical and experimental comparative study of several formalisms led us to choose the TSA (Time Safety Automata), extension of the timed automata implemented in the UPPAAL tool. The obtained model is then analysed by model-checking. This methodology allowed the validation of the temporal bounds of the TTA services, i. E. Their worst execution time, under different faults hypotheses. It completes the existent validation processes for TTA, on the one hand the approaches such as test, simulation and fault injection which are not exhaustive, and on the other hand formal approaches (proof of theorems) which did not allow to take into account the temporal bounds or the interaction of the algorithms
Killian, Cédric. "Réseaux embarqués sur puce reconfigurable dynamiquement et sûrs de fonctionnement." Thesis, Université de Lorraine, 2012. http://www.theses.fr/2012LORR0396.
Full textThe need of performance of embedded Syxtena-on-Chlps (Socs) are increasing constantly to meet the requirements of applications becoming more and more complexes, and new processing architectures and new computing paradigms have emerged. The integration within a single chip of dozens, or hundreds of computing and processing elements has given birth to Mukt1 Pmcesmr Systena-on-Chp (MPSoC) allowing to feature a high level of parallel processing. Nowaday s, the performance of these systems rely on the communication medium between the interconnected processing elements. The problematic of the communication medium to feature a high bandwidth and flexibility is primordial in order to efficiently use the parallel processing capacity of the MPSoC In this context, Network-on-Chlps (NoCs) are developed where the aim is to allow the interconnection of a large number of elements in the same device while maintaining a tradeoff between performance and logical resources. Moreover, the emergence of the partial reconfigurable FPGA technology allows to the MPSoC to adapt their elements during its operation in order to meet the system requirements. Given this increasing complexity of the electronic systems and the shrinking size of the devices, the sensibility of the chip against phenomena generating fault has increased. Thereby, to design efficient and reliable Socs, new error detection and localization techniques must be proposed for the dynamic NoCs where the main difficulty is the identification and the distinction between real errors and adaptive behavior of the NoCs. In this context, we present new mechanisms and architectural solutions allowing to check during the system operation the correctness of dynamic NoCs in order to locate and isolate efficiently the faulty components avoiding a failure of the system
Bénédic, Yohann. "Approche analytique pour l'optimisation de réseaux de neurones artificiels." Phd thesis, Université de Haute Alsace - Mulhouse, 2007. http://tel.archives-ouvertes.fr/tel-00605216.
Full textGatet, Laurent. "Intégration de Réseaux de Neurones pour la Télémétrie Laser." Phd thesis, Toulouse, INPT, 2007. http://oatao.univ-toulouse.fr/7595/1/gatet.pdf.
Full textRobitaille, Benoît. "Contrôle adaptatif par entraînement spécialisé de réseaux de neurones." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1997. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp02/NQ35778.pdf.
Full textDucom, Jean-Christophe. "Codage temporel et apprentissage dans les réseaux de neurones." Aix-Marseille 1, 1996. http://www.theses.fr/1996AIX11041.
Full textBenaïm, Michel. "Dynamiques d'activation et dynamiques d'apprentissage des réseaux de neurones." Toulouse, ENSAE, 1992. http://www.theses.fr/1992ESAE0001.
Full text