Dissertations / Theses on the topic 'Accélérateur de réseau de neurones'
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 'Accélérateur de réseau de neurones.'
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.
Li, Zhuoer. "Étude de l'accélération matérielle reconfigurable pour les réseaux de neurones embarqués faible consommation." Electronic Thesis or Diss., Université Côte d'Azur, 2024. http://www.theses.fr/2024COAZ4025.
Full textThe Artificial Intelligence (AI) application landscape is undergoing a significant transformation as AI continues to permeate various fields, from healthcare to the automotive industry, leading to a surge in the demand for deploying neural networks directly on edge devices. This shift towards edge computing presents a set of challenges and requirements, particularly in terms of latency and energy efficiency. However, as deep learning evolves to address increasingly complex tasks, the complexity and depth of neural network models have also grown. Given that edge devices often operate in environments where energy consumption is limited, it becomes crucial to maximize energy efficiency while ensuring the complex functionalities of deep neural networks. Despite the evident demand, there remains a relative lack of efforts for strategies specifically aimed at reducing the energy cost of neural networks.This thesis aims to address these questions by investigating and evaluating methodologies for low-power neural network implementations on Field-Programmable Gate Arrays (FPGAs), known for their advantageous performance-to-power ratio and adaptability. This work implements various CNN topologies on FPGA platforms using High-Level Synthesis (HLS) methods in cooperation with other existing design and exploration approaches. This thesis then delves into a detailed comparison of the performance and energy efficiency of Artificial Neural Networks (ANNs) and their corresponding Spiking Neural Networks (SNNs) implemented on FPGA platforms. This comparison reveals an unexpected inefficiency in the FPGA implementations of SNNs compared to their equivalent ANNs.Building on these conclusions, this work then continues to explore power optimization methods for deep neural network inference on FPGAs, examining the potential of Partial Reconfiguration (PR) in this regard. The study investigates the use of a full PR methodology based on a cooperation of relevant system-level methodologies and synthesis tools to evaluate the energy efficiency of PR solutions and static solutions on several CNN benchmarks of different complexities. The results indicate that under the main condition of using an optimal reconfiguration control scheme, energy gains can reach a factor of two when PR is applied at the CNN layer level, and savings increase as the network size grows.This result stands as one of the pioneering demonstrations of the great potential of PR for Deep Learning applications on FPGAs. Research in this domain is still at an early stage, yet it already exhibits large promise for minimizing the size of programmable logic, particularly in terms of memory requirements.Additionally, this thesis contributes to an open neural network acceleration library with a compact 8-layer CNN for traffic sign recognition and a ResNet-18, with the relevant FPGA IPs to be made available online later
Rachdi, Adel. "Développement d'un réseau de neurones biologique." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2001. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/MQ65389.pdf.
Full textJouffroy, Guillaume. "Contrôle oscillatoire par réseau de neurones récurrents." Paris 8, 2008. http://www.theses.fr/2008PA082918.
Full textIn 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
Becker, Freddy. "Définition d'un réseau de référence métrologique pour le positionnement d'un grand accélérateur linéaire." Phd thesis, INSA de Strasbourg, 2003. http://tel.archives-ouvertes.fr/tel-00281959.
Full textCette thèse se situe dans le prolongement de travaux entrepris depuis 10 ans. Ceux-ci avaient notamment permis de sélectionner un certain nombre de capteurs métrologiques susceptibles de répondre aux besoins du CLIC. Or la plupart de ces capteurs effectuent leurs mesures par rapport à des références géométriques sensibles à la gravité. Le niveau élevé de précision requis nous a donc conduit à consacrer une partie importante de ce travail à l'effet des perturbations de la gravité sur l'utilisation de ces capteurs. Cela a permis de mettre en évidence les effets qui devront être pris en compte et de dégager les interrogations qui subsistent encore sur l'utilisation des niveaux hydrostatiques.
Cette recherche avait également pour but d'établir une proposition de configuration du système d'alignement, basée sur l'utilisation des capteurs sélectionnés. Il s'agissait donc d'effectuer des simulations des précisions obtenues avec les différentes configurations possibles. L'outil de calcul disponible étant inadapté, un effort majeur a été consacré au développement d'un nouveau logiciel. Les méthodologies orientées-objet se sont avérées être très bénéfiques dans ce contexte et ont permis la mise au point d'un outil évolutif adapté à des projets de recherche. Les simulations effectuées ont permis de définir une configuration optimale du réseau.
Enfin, en raison des problèmes peut-être insolubles que pose l'utilisation des capteurs hydrostatiques, nous avons mené une réflexion qui nous a permis d'ébaucher assez précisément une solution alternative basée sur l'utilisation d'un long faisceau laser.
Yonaba, Harouna. "Modélisation hydrologique hybride : réseau de neurones - modèle conceptuel." Thesis, Université Laval, 2009. http://www.theses.ulaval.ca/2009/26583/26583.pdf.
Full textCarpentier, Mathieu. "Classification fine par réseau de neurones à convolution." Master's thesis, Université Laval, 2019. http://hdl.handle.net/20.500.11794/35835.
Full textArtificial 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.
Charpentier, 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.
Full textCayouette, Philippe. "Aérocapture martienne par réseau de neurones entraîné par algorithme génétique." Mémoire, Université de Sherbrooke, 2006. http://savoirs.usherbrooke.ca/handle/11143/1372.
Full textTrinh, Franck Ky. "Simulation d'un réseau de neurones à l'aide de transistors SET." Mémoire, Université de Sherbrooke, 2010. http://hdl.handle.net/11143/5493.
Full textLiu, Xiaoqing. "Analyse d'images couleur en composantes indépendantes par réseau de neurones." Grenoble INPG, 1991. http://www.theses.fr/1991INPG0120.
Full textCaron, 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 textLecerf, Gwendal. "Développement d'un réseau de neurones impulsionnels sur silicium à synapses memristives." Thesis, Bordeaux, 2014. http://www.theses.fr/2014BORD0219/document.
Full textSupported financially by ANR MHANN project, this work proposes an architecture ofspiking neural network in order to recognize pictures, where traditional processing units are inefficient regarding this. In 2008, a new passive electrical component had been discovered : the memristor. Its resistance can be adjusted by applying a potential between its terminals. Behaving intrinsically as artificial synapses, memristives devices can be used inside artificial neural networks.We measure the variation in resistance of a ferroelectric memristor (obtained from UMjCNRS/Thalès) similar to the biological law STDP (Spike Timing Dependant Plasticity) used with spiking neurons. With our measurements on the memristor and our network simulation (aided by INRIASaclay) we designed successively two versions of the IC. The second IC design is driven by specifications of the first IC with additional functionalists. The second IC contains two layers of a spiking neural network dedicated to learn a picture of 81 pixels. A demonstrator of hybrid neural networks will be achieved by integrating a chip of memristive crossbar interfaced with thesecond IC
Goulet-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.
Full textGoncalves, Pedro. "Un Modèle du réseau neuronal de l'intégrateur oculomoteur : théorie pour la dissection." Paris 6, 2012. http://www.theses.fr/2012PA066200.
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
Ho, Tuong Vinh. "Un réseau de neurones à décharges pour la reconnaissance de processus spatio-temporels." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape8/PQDD_0002/NQ42823.pdf.
Full textNadal, Jean-Pierre. "Deux applications de la physique des systèmes désordonnés : croissance de structures et réseaux de neurones." Paris 11, 1987. http://www.theses.fr/1987PA112029.
Full textRangoni, Yves. "Réseau de neurones dynamique perceptif - Application à la reconnaissance de structures logiques de documents." Phd thesis, Université Nancy II, 2007. http://tel.archives-ouvertes.fr/tel-00584318.
Full textLaurent, 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.
Full textBergeron, 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.
Full textKhoyratee, 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.
Full textNeuroscience 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
Chen, Xiaoning. "Contrôle optimal d'un disjoncteur de puissance : visualisation, mise en oeuvre d'un réseau de neurones." Cergy-Pontoise, 2000. http://www.theses.fr/2000CERG0110.
Full textAsnaashari, Ahmad. "Modélisation de la défaillance des réseaux d'eau : approches statistique, réseau de neurones et survie." Lille 1, 2007. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/2007/50376-2007-Asnaashari.pdf.
Full textAit, Fares Salma. "Réseau de neurones adaline pour l'estimation des harmoniques pour la commande d'un filtre actif." Thèse, Université du Québec à Trois-Rivières, 2003. http://depot-e.uqtr.ca/3991/1/000103594.pdf.
Full textLamrani, Jamal. "Étude et tentative d'optimisation des paramètres d'un réseau de neurones de types auto-associatif." Thèse, Université du Québec à Trois-Rivières, 1994. http://depot-e.uqtr.ca/5026/1/000616425.pdf.
Full textMarissal, Thomas. "Une approche développementale de l' hétérogénéité fonctionnelle des neurones pyramidaux de CA3." Thesis, Aix-Marseille, 2012. http://www.theses.fr/2012AIXM4001/document.
Full textThere is increasing evidence that CA3 pyramidal cells are biochemically, electrophysiologically, morphologically and functionally diverse. As most of these properties are acquired during development, we hypothesized that the heterogeneity of the morphofunctionnal properties of pyramidal cells could be determined at the early stages of life. To test this hypothesis, we used a transgenic mouse line in which we glutamatergic cells are labelled with GFP according to their birth date. Using calcium imaging, we recorded multineuron activity in hippocampal slices and show that early generated pyramidal neurons fire during the build-up phase of epileptiform activities generated in the absence of fast GABAergic transmission. Moreover, we show that early generated pyramidal neurons display distinct morpho-physiological properties. Finally, we demonstrate that early generated neurons can generate epileptiform activities when stimulated as assemblies at immature stages, and when stimulated individually at juvenile stages. Thus we suggest a link between the date of birth and the morpho-functional properties of CA3 pyramidal neurons
Cabirol-Pol, Marie-Jeanne. "Caractérisation morphofonctionnelle d'un réseau neuronal simple : implications de la géométrie des neurones et de la ségrégation des synapses intra-réseau et modulatrices." Bordeaux 1, 1998. http://www.theses.fr/1998BOR10561.
Full textPearlstein, Edouard. "Organisation modulaire d'un réseau locomoteur : étude des motoneurones élévateurs et dépresseurs dans les appendices thoraciques de l'écrevisse." Aix-Marseille 3, 1996. http://www.theses.fr/1996AIX30011.
Full textAmbroise, Matthieu. "Hybridation des réseaux de neurones : de la conception du réseau à l’interopérabilité des systèmes neuromorphiques." Thesis, Bordeaux, 2015. http://www.theses.fr/2015BORD0394/document.
Full textHYBRID experiments allow to connect a biological neural network with an artificial one,used in neuroscience research and therapeutic purposes. During these three yearsof PhD, this thesis focused on hybridization in a close-up view (bi-diretionnal direct communication between the artificial and the living) and in a broader view (interoperability ofneuromorphic systems). In the early 2000s, an analog neuromorphic system has been connected to a biological neural network. This work is firstly, about the design of a digital neural network, for hybrid experimentsin two multi-disciplinary projects underway in AS2N team of IMS presented in this document : HYRENE (ANR 2010-Blan-031601), aiming the development of a hybrid system for therestoration of motor activity in the case of a spinal cord lesion,BRAINBOW (European project FP7-ICT-2011-C), aiming the development of innovativeneuro-prostheses that can restore communication around cortical lesions. Having a configurable architecture, a digital neural network was designed for these twoprojects. For the first project, the artificial neural network emulates the activity of CPGs (Central Pattern Generator), causing the locomotion in the animal kingdom. This activity will trigger aseries of stimuli in the injured spinal cord textit in vitro and recreating locomotion previously lost. In the second project, the neural network topology will be determined by the analysis anddecryption of biological signals from groups of neurons grown on electrodes, as well as modeling and simulations performed by our partners. The neural network will be able to repair the injuredneural network. This work show the two different networks design approach and preliminary results obtained in the two projects.Secondly, this work hybridization to extend the interoperability of neuromorphic systems. Through a communication protocol using Ethernet, it is possible to interconnect electronic neuralnetworks, computer and biological. In the near future, it will increase the complexity and size of networks
Kara, Reda. "Une Approche modulaire du réseau de neurones CMAC pour la commande d'un système robot-vision." Mulhouse, 2002. http://www.theses.fr/2002MULH0704.
Full textThe work of this thesis investigates artificial neural networks capabilities to estimate robotic functions, and their performances as controllers. We propose an adaptive visual servoing scheme based on the CMAC ("Cerebellar Model Articulation Controller") network. The CMAC network is thus well suited for robot control but in practice there are two drawbacks: its output is "discrete" and its precision depends on its size. Thus, we have developed two modular neural : the HCMAC ("Hierarchical CMAC") and the AL_CMAC ("Adaptive Linear CMAC"). These two networks are a combination of networks of small size. The efficiency of the HCMAC and AL_CMAC neuro-controller is validated through visual servoing experiments with a three degrees of freedom robot arm and with a two camera vision system. Visual servoing experiments consist in positioning tasks and in tracking mobile objects. The performances are compared to other neuro-controllers like CMAC and SSOM ("Supervised Self-Organizing Maps") networks
Chauvet, Pierre. "Sur la stabilité d'un réseau de neurones hiérarchique à propos de la coordination du mouvement." Angers, 1993. http://www.theses.fr/1993ANGE0011.
Full textPatry, Marco. "Modelisation de la défibration secondaire de la pâte cellulose à l'aide d'un réseau de neurones." Thèse, Université du Québec à Trois-Rivières, 2001. http://depot-e.uqtr.ca/2798/1/000680637.pdf.
Full textVuillet, Jacqueline. "Place des neurones contenant le neuropeptide Y dans le réseau striatal : apptoche ultrastructurale et immunocytochimique." Aix-Marseille 2, 1993. http://www.theses.fr/1993AIX22023.
Full textObjois, Philippe. "Réseau de cellules intégré : mécanisme de communication inter-cellulaire et application à la simulation logique." Phd thesis, Grenoble INPG, 1988. http://tel.archives-ouvertes.fr/tel-00328188.
Full textCornu-Emieux, Renaud. "Réseau de cellules intégré : étude d'architectures pour des applications de CAO de VLSI." Phd thesis, Grenoble INPG, 1988. http://tel.archives-ouvertes.fr/tel-00328650.
Full textKosmidis, Efstratios. "Effets du bruit dans le système nerveux central : du neurone au réseau de neurones : fiabilité des neurones, rythmogenèse respiratoire, information visuelle : étude par neurobiologie numérique." Paris 6, 2002. http://www.theses.fr/2002PA066199.
Full textBenaouda, Djamel. "Modélisation et simulation d'un réseau de neurones formels : implantation sur machine parallèle "hypercube FPS T-40." Phd thesis, Grenoble 1, 1992. http://tel.archives-ouvertes.fr/tel-00340978.
Full textSabeva, Silvia. "Application d'un réseau de neurones ARTMAP à la reconnaissance des commandes gestuelles d'édition de documents braille." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape7/PQDD_0002/MQ42925.pdf.
Full textLe, Masson Gwendal. "Stabilité fonctionnelle des réseaux de neurones : étude expérimentale et théorique dans le cas d'un réseau simple." Bordeaux 1, 1998. http://www.theses.fr/1998BOR10534.
Full textMusca, Serban. "Auto-rafraîchissement de la mémoire humaine : études comportementales et simulations en réseau de neurones dual réverbérant." Grenoble 2, 2004. http://www.theses.fr/2004GRE29008.
Full textTay, 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.
Full textKharroubi, 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.
Full textThe 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
Chervier, Frédéric. "Modélisation des variations basse fréquence des émissions de COVB à l'aide d'un réseau de neurones artificiels." Paris 7, 2005. http://www.theses.fr/2005PA077179.
Full textRoyer, Alex. "Amélioration des méthodes de calcul thermique par réseau de neurones dans les chambres de combustion aéronautiques." Electronic Thesis or Diss., Université de Lorraine, 2023. http://www.theses.fr/2023LORR0141.
Full textAeronautical combustion chambers are constrained environments operating at temperatures and pressures that have been steadily increasing over the last decades. Under these conditions, radiative heat transfer is significant and its influence on flame structure and wall temperatures is noticeable. It is therefore essential to be able to accurately model this transfer mode on very heterogeneous industrial cases and on mesh of several hundred million cells. Common resolution methods do not provide satisfactory accuracy in view of the growing needs. A fine resolution and the use of spectral gas models would be necessary but would imply a prohibitive consumption of computing resources.To overcome this problem, we propose in this work a new radiation modelling methodology based on Monte Carlo methods and Bayesian neural networks. The principle of the concept detailed in this manuscript starts with the sampling of reference points randomly drawn in the study domain. The radiative quantity of interest is computed at each of these points using a Monte Carlo method and a fine spectral model. The results of these calculations are then stored in a database on which a neural network is trained using a Levenberg-Marquardt algorithm. The Bayesian paradigm allows us to define the optimal topology of the network and to automatically adapt the set of parameters inherent to the network without user intervention. The trained network allows to reconstitute the flux or flux divergence fields within the domain. After a theoretical description of the notions used in this work, results on academic cases are presented in different configurations. We then demonstrate the ability of the developed method to model radiation in a participatory environment with very high accuracy and low computational costs
Sadeghsa, Shohre. "Prédiction, réseau de neurones et optimisation : applications aux domaines des agro-matériaux et de la télécommunication." Electronic Thesis or Diss., Amiens, 2021. http://www.theses.fr/2021AMIE0091.
Full textIn the context of global changes in the world, the use of vegetal resources in composite materials is an alternative solution to the exploitation of fossil resources. However, the development of the vegetal composite requires taking into account the time and space availability of bio-sourced raw materials, their interchangeability, and their consequences on resulting functional characteristics. Optimization of the vegetal composite faces a variety of available data, the complexity to establish cause and effect relationships, and the mandatory handling of unexpected events (such as disaster, crises, break down, etc, ...). Thus, a reliable and sustainable system is required in order to produce the vegetal composite with constant efficiency. Artificial intelligence methods should allow improving the understanding and control of the production related to the concerned materials. Considering the uncertainty and changeability of the data related to the vegetal materials, we applied machine learning and artificial intelligence methods to predict the parameters of the experiments dynamically. A model can adapt itself based on the training data. Predictions are dynamic, and the results are data-oriented.Herein, the vegetal composite is studied with three aspects: to predict the compressive strength of the composite, to predict the flexural strength of the composite, and a simulation model to predict the parameters of the compressive composite strength test. To overcome the mentioned problems, artificial intelligence and machine learning methods are suggested as a solution that learns from the old data in order to converge towards better local optima. The development of the vegetal composite requires taking into account the specific parameters of the bio-sourced raw materials such as temporal availability, interchangeability, and the consequences on the resulting functional properties. Optimization of the vegetal composites can be viewed as a complex problem related to different domains such as biology, physico-chemistry, and process engineering. The sustainable optimization and production of the vegetal materials also require the localization, centralization, and consolidation of the supply chain sites. The supply chain problems consist of localizing the production sites, routing, and scheduling, and storage of raw materials, and final distribution and marketing. Regrouping, consolidating or clustering are referred to the act of merging two or more sites. It is the act of reducing the number of existing centers. In order to keep the continuous efficiency in the supply and production chains, each site has to provide the whole services that used to be served by the replaced sites. The regrouping problem can be seen in any part of this chain. The k-clustering problem can be defined in any of the two parts of the supply chain that are in direct relations. This thesis aims to deal with the complexity encountered to optimize the vegetal composite and to ensure the sustainability of the supply, production, and marketing sites. The former is achieved, in the first part, by optimizing the characteristics of the composite material using artificial intelligence methods. The latter is presented in the second part of this study. The proposed method merges the supply chain site(s) using the K-clustering problem. Different optimization solution methods are proposed. The applied transversal approach allowing the coupling of skills is presented within the research unit EPROAD. The proposed methods are from the field of artificial intelligence, combinatorial optimization, discrete modeling resulting from applied mathematics, sensitivity analysis, and the field of process engineering for the development of intelligent cooperative methods
Desmaisons, David. "Oscillations de réseau et synchronisation dans le bulbe olfactif : une étude in vitro." Paris 6, 2001. http://www.theses.fr/2001PA066415.
Full textTertois, Sylvain. "Réduction des effets des non-linéarités dans une modulation multiporteuse à l'aire de réseaux de neurones." Phd thesis, Université Rennes 1, 2003. http://tel.archives-ouvertes.fr/tel-00004015.
Full textTout d'abord, le mémoire commence par une introduction aux communications numériques et en particulier à la modulation OFDM. Aujourd'hui, plusieurs standards reposent sur cette technique de transmission, en particulier en raison de la simplicité de l'égalisation du canal, et donc la possibilité de transmettre avec plus d'efficacité des données sur des canaux multitrajets. Cependant le signal OFDM temporel est particulièrement sensible aux non-linéarités présentes dans l'amplificateur d'émission et diverses techniques sont étudiées pour diminuer ces effets.
Ensuite, les réseaux de neurones sont présentés, ainsi que leur utilisation dans le domaine de l'approximation de fonctions. Après avoir décrit les deux modèles de réseaux de neurones les plus courants, les réseaux d'ordre supérieur, tels que le RPN, sont introduits. Les techniques d'apprentissage de ces différentes architectures de réseaux de neurones sont également décrites.
Dans les différents correcteurs étudiés dans cette thèse, le réseau de neurones est placé dans le récepteur, après l'égalisation de canal. Son objectif est de corriger le signal reçu afin de compenser les effets des non-linéarités. Dans un premier temps le réseau de neurones est placé dans le domaine fréquentiel. Dans un système OFDM à 4 porteuses avec une modulation MAQ16, un amplificateur de type SSPA, un recul de 0 dB et pour un taux d'erreur binaire de 10-2, le correcteur avec un réseau RPN apporte un gain de 1,5 dB de rapport signal sur bruit. Cependant des difficultés apparaissent durant la phase d'apprentissage du réseau de neurones avec un nombre de porteuses supérieur.
Pour palier ce défaut, les réseaux de neurones décrits précédemment sont simplifiés en étant placés dans le domaine temporel. Ce système est plus proche des solutions déjà proposées pour la compensation des non-linéarités dans une modulation monoporteuse, avec toutefois des différences au niveau de l'égalisation du canal et de la nature de la fonction que doit accomplir le réseau de neurones. Un correcteur basé sur un réseau RPN a montré de très bonnes performances, même en augmentant le nombre de porteuses. Un gain de 8 dB a été mesuré pour un taux d'erreur binaire de 10-2 dans un système OFDM à 48 porteuses, une modulation MAQ16 et un amplificateur de type SSPA avec un recul de 0 dB. Le système présenté permet donc dans ces conditions de diviser la puissance de l'amplificateur, et donc sa consommation d'énergie, par un facteur supérieur à 4 tout en conservant la même qualité de transmission.
Le correcteur à RPN dans le domaine temporel est ensuite simulé sur un canal multitrajet, afin de vérifier que la compensation reste efficace dans le cas d'un canal sévère. Enfin les deux approches proposées (fréquentielle et temporelle) sont comparées, au niveau des performances obtenues et de la puissance de calcul nécessaire dans le récepteur. Une comparaison avec une autre approche proposée dans la littérature est également présentée. Le correcteur temporel basé sur un RPN est bien moins complexe que le système cité, au détriment d'une légère dégradation des performances.
Ce mémoire se conclut par quelques perspectives de recherche pouvant prolonger les travaux accomplis durant cette thèse.
Zoungrana, Ouinlassida Robert. "Etude extracellulaire et intracellulaire du réseau neuronique programmant la déglutition : effets de la stimulation des afférences linguales, vagales et du cortex masticateur." Aix-Marseille 3, 1994. http://www.theses.fr/1994AIX30023.
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)
Soula, Hédi. "Dynamique et plasticité dans les réseaux de neurones à impulsions : étude du couplage temporel réseau / agent / environnement." Lyon, INSA, 2005. http://theses.insa-lyon.fr/publication/2005ISAL0056/these.pdf.
Full textAn «artificial life » approach is conducted in order to assess the neural basis of behaviours. Behaviour is the consequence of a good concordance between the controller, the agent’s sensori-motors capabilities and the environment. Within a dynamical system paradigm, behaviours are viewed as attractors in the perception/action space – derived from the composition of the internal and external dynamics. Since internal dynamics is originated by the neural dynamics, learning behaviours therefore consists on coupling external and internal dynamics by modifying network’s free parameters. We begin by introducing a detailed study of the dynamics of large networks of spiking neurons. In spontaneous mode (i. E. Without any input), these networks have a non trivial functioning. According to the parameters of the weight distribution and provided independence hypotheses, we are able to describe completely the spiking activity. Among other results, a bifurcation is predicted according to a coupling factor (the variance of the distribution). We also show the influence of this parameter on the chaotic dynamics of the network. To learn behaviours, we use a biologically plausible learning paradigm – the Spike-Timing Dependent Plasticity (STDP) that allows us to couple neural and external dynamics. Applying shrewdly this learning law enables the network to remain “at the edge of chaos” which corresponds to an interesting state of activity for learning. In order to validate our approach, we use these networks to control an agent whose task is to avoid obstacles using only the visual flow coming from its linear camera. We detail the results of the learning process for both simulated and real robotics platform