Dissertations / Theses on the topic 'Réseaux de Neuronne'
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 Neuronne.'
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.
Ben, Slimane Tarek. "Investigation of the Optical Emission of Hall Effect Thrusters using a Collisional Radiative Model, Particle-In-Cell Simulations, and Machine Learning." Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAX153.
This thesis provides an analysis of the optical emission of Hall Effect thrusters. The study is grounded in the context of the dynamic field of micro reusable launchers and ride-share satellite programs, which have substantially reduced space operation costs. This shift has intensified the demand for standardized and miniaturized satellite equipment, with a particular focus on Hall thrusters due to their advantageous thrust-to-power ratio, specific impulse, and efficiency.This thesis builds upon the development of the LPPic Particle-In-Cell code, and explores the plasma dynamics and interactions within the thruster by coupling the simulation results with virtual diagnostics. First is the collective Thomson scattering, which explores the electron density fluctuations in the thruster. Second is the optical emission spectroscopy coupled with a collisional radiative model, which characrerizes the electron energy distribution function. Both are instrumental in validating LPPic simulations, with the latter also serving as a promising tool for assessing the performance in orbit and characterizing ground facility effects.The methodology consists of a blend of simulations and experiments, relying on virtual diagnostics to assess simulations and guide experimental practices. The thesis is structured into eight chapters. These include the exploration of virtual collective Thomson scattering diagnostics, the development and validation of HET0D, a collisional-radiative model for neutral xenon, and the establishment of a framework for performing virtual optical emission spectroscopy from Particle-In-Cell simulations. This established the importance of considering spatial gradients in the plume of the thruster when extracting plasma parameters from optical emission. It also highlighted the validity of the transport and Maxwellian assumptions in the collisional radiative models of neutral species and highlighted line-specific bandwidth limitations for the implementation of optical emission spectroscopy to study high frequency instabilities (>MHz). These insights were confronted with experiments where actual spectra were used to extract plasma parameters using the collisional radiative model under various thruster conditions, thereby demonstrating the validity of the virtual diagnostic analysis and the adequacy of optical emission and collisional radiative models to monitor Hall Effect thrusters. Finally, an innovative enhancement to optical emission and collisional radiative model through the integration of artificial neural networks is also presented, which significantly improves the efficiency and scope of the diagnostic, by speeding up the processing, reducing the needed hardware in-orbit, and allowing the optical control of the operating parameters.This research makes an initial contribution to the field of electric propulsion by offering a unique perspective that combines numerical simulations, virtual diagnostics with experimental data, and neural networks, thereby enhancing the understanding of diagnostics, simulations, and the behavior of Hall Effect thrusters
Cohen, Floriane. "Architectures dynamiques des réseaux neuronaux in vitro." Thesis, Paris Sciences et Lettres (ComUE), 2018. https://tel.archives-ouvertes.fr/tel-02512337.
The function of the nervous system relies on the establishment of complex neuronal circuitry. During development, axon branching allows each neuron to establish synaptic contacts with multiple targets and is essential to the assembly of highly interconnected networks. Therefore, understanding the mechanisms underlying the control of neuronal branching is crucial in the study of neuronal circuit development.In this thesis, we investigated this phenomenon by imposing morphological constraints to neurons through the use of different chemical micropatterning techniques. Using static micropatterns, we explored branching behavior in a wide range of geometries with a focus on the influence of branching angle. In parallel, we have also worked on the development of a dynamic patterning technique based on spontaneous adsorption of comb-like derivatives of poly-L-lysine to form switchable patterns on highly cell-repellent surfaces, with the aim of creating a platform allowing for spatio-temporally controlled generation of neurite branches
Pfeuty, Benjamin. "Rôles des synapses électriques dans la synchronisation neuronale : Une étude théorique." Phd thesis, Université Pierre et Marie Curie - Paris VI, 2004. http://tel.archives-ouvertes.fr/tel-00007936.
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.
Asnaashari, 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.
Grehl, Stephanie. "Stimulation-specific effects of low intensity repetitive magnetic stimulation on cortical neurons and neural circuit repair in vitro (studying the impact of pulsed magnetic fields on neural tissue)." Thesis, Paris 6, 2014. http://www.theses.fr/2014PA066706/document.
Electromagnetic fields are widely used to non-invasively stimulate the human brain in clinical treatment and research. This thesis investigates the effects of different low intensity (mT) repetitive magnetic stimulation (LI-rMS) parameters on single neurons and neural networks and describes key aspects of custom tailored LI-rMS delivery in vitro. Our results show stimulation specific effects of LI-rMS on cell survival, neuronal morphology, neural circuit repair and gene expression. We show novel mechanisms underlying cellular responses to stimulation below neuronal firing threshold, extending our understanding of the fundamental effects of LI-rMS on biological tissue which is essential to better tailor therapeutic applications
Ambroise, 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.
HYBRID 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
Le, 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.
Wenzek, Didier. "Construction de réseaux de neurones." Phd thesis, Grenoble INPG, 1993. http://tel.archives-ouvertes.fr/tel-00343569.
Tsopze, 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.
The 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
Rouach-Holcman, Nathalie. "Contribution de la communication jonctionnelle astrocytaire dans les interactions entre réseaux neuronaux et gliaux." Paris 6, 2002. http://www.theses.fr/2002PA066322.
Maktoobi, Sheler. "Couplage diffractif pour réseaux de neurones optiques." Thesis, Bourgogne Franche-Comté, 2020. http://www.theses.fr/2020UBFCD019.
Photonic 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)
Bedecarrats, Alexis. "Etude cellulaire de la genèse et de l'apprentissage d'un comportement motivé chez l'aplysie." Thesis, Bordeaux, 2014. http://www.theses.fr/2014BORD0452/document.
Motivated behaviors such as feeding or sexual behavior are irregularly expressed by impulsive drives from the central nervous system. However, such goal-directed acts are regulated by sensory inputs and learning. In a form of associative learning, appetitive operant conditioning, an animal learns the consequences of its own actions by making the contingentassociation between an emitted act and delivery of a rewarding (highly appetitive) stimulus. It is now established that this learning procedure induces the transition from an initially infrequent and irregular motor activity to a frequent and regular behavior. However the cellular and central network mechanisms that mediate this behavioral plasticity remain poorlyunderstood. Our study on the marine sea slug Aplysia has allowed us to analyze these mechanisms in an identified neuronal network that is responsible for generating the motor patterns of the animal's feeding behavior. Using in vitro neuronal preparations, we selectively controlled the frequency and regularity of the motor activity induced by operant learning with experimental manipulations of the functional plasticity in identified pacemaker neurons. We found for the first time a causal relationship between the learning-induced plasticity and (1) changes in pacemaker neuron membrane properties and the increased frequency of feeding motor activity, and (2), in the strength of their interconnecting electrical synapses and the regularized phenotype of this motor activity. We then addressed the role of the transmitterdopamine in the induction of this functional plasticity and specifically the expression of a frequent and stereotyped rhythmic feeding motor pattern. Finally, we analyzed the intrinsic membrane properties of the essential pacemaker neuron for generating the irregular motor drive in naïve animals. In conclusion, the data from this thesis work have provided novelinsights into the cellular and synaptic mechanisms underlying the intrinsic variability of a motivated behavior and its regulation by learning
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.
An «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
Voegtlin, Thomas. "Réseaux de neurones et auto-référence." Lyon 2, 2002. http://theses.univ-lyon2.fr/documents/lyon2/2002/voegtlin_t.
The 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.
Côté, Marc-Alexandre. "Réseaux de neurones génératifs avec structure." Thèse, Université de Sherbrooke, 2017. http://hdl.handle.net/11143/10489.
Brette, 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.
Desmaisons, David. "Oscillations de réseau et synchronisation dans le bulbe olfactif : une étude in vitro." Paris 6, 2001. http://www.theses.fr/2001PA066415.
Bugnicourt, Ghislain. "Adhésion, croissance et polarisation de neurones sur substrats micro-et nano-structurés." Phd thesis, Université de Grenoble, 2011. http://tel.archives-ouvertes.fr/tel-00665074.
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.
Nadal, 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.
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.
Picardo, Michel. "Origine embryonnaire et propriétés morpho-physiologiques des neurones hubs de l'hippocampe en développement." Thesis, Aix-Marseille, 2012. http://www.theses.fr/2012AIXM4057.
We have recently demonstrated the existence of functional hubs driving network synchronizations in the developing hippocampus. Hubs are a subpopulation of GABAergic neurons displaying widespread axonal projections. During my PhD, using paired electrophysiological recordings, I have shown that hub cells are synaptically connected to a large number of neurons (Bonifazi et al. 2009). Next, using genetic fate mapping approaches, I have demonstrated that early born GABAergic neurons constitute a subpopulation of hub cells. These pioneer hub cells remain into adulthood and develop into GABAergic neurons with an extrahippocampal projection (Picardo et al. 2011). This suggests that hub function may to retained into adulthood, at least structurally
Duhr, Fanny. "Voies de signalisation associées au récepteur 5-HT6 et développement neuronal." Thesis, Montpellier, 2015. http://www.theses.fr/2015MONTT042/document.
Brain circuitry patterning is a complex, highly regulated process. Alteration of this process is affected gives rise to various neurodevelopmental disorders such as schizophrenia or Autism Spectrum Disorders (ASD), which are both characterized by a wide spectrum of deficits. Serotonin 6 receptor (5-HT6 receptor), which is known for its implication in neuronal migration process, has been identified as a key therapeutic target for the treatment of cognitive deficits observed in schizophrenia, but also in neurodegenerative pathologies such as Alzheimer's disease. However, the signalling mechanisms knowned to be activated by the 5-HT6 receptor do not explain its involvement in neurodevelopmental processes. My thesis project therefore aimed at characterizing the signalling pathways engaged by 5-HT6 receptor during neural development. A proteomic approach allowed me to show that the 5-HT6 receptor was interacting with several proteins playing crucial roles in neurodevelopmental processes such as Cdk5 or WAVE-1. I then demonstrated that, besides its role in neuronal migration, the 5-HT6 receptor was also involved in neurite growth through constitutive phosphorylation of 5-HT6 receptor at Ser350 by associated Cdk5, a process leading to an increase in Cdc42 activity. The second part of my work aimed at understanding the role of 5-HT6 receptor in dendritic spines morphogenesis, and the involvement of WAVE-1 and Cdk5 in this process. These results provide new insights into the control of neurodevelopemental processes by 5-HT6 receptor. Thus, 5-HT6 receptor appears to be a key therapeutic target for neurodevelopmental disorders by contributing to the development of cognitive circuitry related to the pathophysiology of ASD or schizophrenia
Bigot, Pascal. "Utilisation des réseaux de neurones pour la télégestion des réseaux techniques urbains." Lyon 1, 1995. http://www.theses.fr/1995LYO10036.
Tardif, Patrice. "Autostructuration des réseaux de neurones avec retards." Thesis, Université Laval, 2007. http://www.theses.ulaval.ca/2007/24240/24240.pdf.
Ouali, Jamel. "Architecture intégrée flexible pour réseaux de neurones." Grenoble INPG, 1991. http://www.theses.fr/1991INPG0035.
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.
Marissal, Thomas. "Une approche développementale de l' hétérogénéité fonctionnelle des neurones pyramidaux de CA3." Thesis, Aix-Marseille, 2012. http://www.theses.fr/2012AIXM4001/document.
There 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
Jarre, Guillaume. "Etude des réseaux neuronaux du cortex somatosensoriel au cours de l'épileptogenèse dans un modèle d'épilepsie génétique." Thesis, Université Grenoble Alpes (ComUE), 2017. http://www.theses.fr/2017GREAV064.
The brain is organized into several interconnected neuronal networks whose formation is highly regulated by cellular, molecular and functional processes. The dysfunction of these processes during brain development could disrupt neuronal circuit establishment and lead to neurological pathologies. Absence epilepsy is a genetically determined disease with a childhood onset. Absence seizures are characterized by an impairment of the consciousness associated on the electroencephalogram with spike and wave discharges (SWD). However, little is known about the mechanisms leading to the establishment of recurrent epileptic discharges (i.e. epileptogenesis). We hypothesized that SWD onset originates from an abnormal brain maturation.During my PhD, I examined this hypothesis in a recognized genetic model of absence epilepsy, the GAERS rat. First, I studied the epileptogenic process by recording in vivo the local field potential and the intracellular activities of pyramidal neurons in the initiating area of SWD, the somatosensory cortex (SoCx), at different post natal days in GAERS. We showed that SWD progressively developed after the end of a highly sensitive and plastic maturation period of the SoCx (i.e critical period). Afterward, epileptic discharges maturation consists in an increase of their duration, their number and in an evolution of the pattern reaching a relative stability at adulthood. Moreover, these changes are associated with a gradual abnormal alteration of the intrinsic properties of pyramidal neurons which is accompanied with a progressive increase in the strength of the local synaptic activity and a growing propensity of SoCx neurons to generate synchronized oscillations.Then, we explored the reasons for this abnormal susceptibility of SoCx neurons to be more synchronized in GAERS. We sought to bring to light anomalies of SoCx maturation at the structural and functional organization level prior to SWD onset in GAERS. Combining MRI, immunohistochemistry labeling and rabies-mediated retrograde monosynaptic tracing to reveal long-range connectivity, we showed that, prior to SWD onset, no brain and SoCx architecture abnormalities could be observed in GAERS. Then, using two photon calcium imaging we recorded in vivo the spontaneous activity of SoCx layers 2-3 neurons to evidence their functional organization. We found that these neurons were more active and unveiled a different functional organization in GAERS compared to control animals. Finally, to understand how is mediated this abnormal functional organization, we studied the dendritic and synaptic fine structure of SoCx neurons by combining electron microscopy and morphological neuron reconstruction. We highlighted an enlargement of the dendritic spines as well as an increase of the post-synaptic density length in the GAERS SoCx.Taken together, these findings showed the progressive nature of absence epilepsy development and the presence of abnormalities in the cortical maturation which affect the structure and the functional of the neuronal network the prior to SWD. These alterations constitute a breeding ground for the establishment and evolution of SWD. Future studies will aim at interfering with the epileptogenesis process should target these early alterations to stop seizure development
Abadi, Mehdi. "Réalisation d'un réseau de neurones "SOM" sur une architecture matérielle adaptable et extensible à base de réseaux sur puce "NoC"." Thesis, Université de Lorraine, 2018. http://www.theses.fr/2018LORR0068/document.
Since its introduction in 1982, Kohonen’s Self-Organizing Map (SOM) showed its ability to classify and visualize multidimensional data in various application fields. Hardware implementations of SOM, by exploiting the inherent parallelism of the Kohonen algorithm, allow to increase the overall performances of this neuronal network, often at the expense of the flexibility. On the other hand, the flexibility is offered by software implementations which on their side are not suited for real-time applications due to the limited time performances. In this thesis we proposed a distributed, adaptable, flexible and scalable hardware architecture of SOM based on Network-on-Chip (NoC) designed for FPGA implementation. Moreover, based on this approach we also proposed a novel hardware architecture of a growing SOM able to evolve its own structure during the learning phase
Abadi, Mehdi. "Réalisation d'un réseau de neurones "SOM" sur une architecture matérielle adaptable et extensible à base de réseaux sur puce "NoC"." Electronic Thesis or Diss., Université de Lorraine, 2018. http://www.theses.fr/2018LORR0068.
Since its introduction in 1982, Kohonen’s Self-Organizing Map (SOM) showed its ability to classify and visualize multidimensional data in various application fields. Hardware implementations of SOM, by exploiting the inherent parallelism of the Kohonen algorithm, allow to increase the overall performances of this neuronal network, often at the expense of the flexibility. On the other hand, the flexibility is offered by software implementations which on their side are not suited for real-time applications due to the limited time performances. In this thesis we proposed a distributed, adaptable, flexible and scalable hardware architecture of SOM based on Network-on-Chip (NoC) designed for FPGA implementation. Moreover, based on this approach we also proposed a novel hardware architecture of a growing SOM able to evolve its own structure during the learning phase
Kosmidis, Efstratios. "Effets du bruit dans le système nerveux central : du neurone au réseau de neurones : fiabilité des neurones, rythmogenèse respiratoire, information visuelle : étude par neurobiologie numérique." Paris 6, 2002. http://www.theses.fr/2002PA066199.
Meunier, David. "UNE MODÉLISATION ÉVOLUTIONNISTE DU LIAGE TEMPOREL." Phd thesis, Université Lumière - Lyon II, 2007. http://tel.archives-ouvertes.fr/tel-00198797.
Nous avons développé un modèle de réseau de neurones impulsionnels, dont la topologie est modifiée par un algorithme évolutionniste. Le critère de performance utilisé pour l'algorithme évolutionniste est évalué par l'intermédiaire du comportement d'un individu contrôlé par un réseau de neurones impulsionnels, et placé dans un environnement virtuel. L'utilisation du neurone impulsionnel, ayant la propriété de détection de synchronie, oblige l'évolution à construire un système utilisant cette propriété au niveau global, d'où l'émergence de la synchronisation neuronale à large-échelle. Les propriétés topologiques et dynamiques du réseau de neurones ne sont pas prises en compte dans le calcul de la performance, mais sont étudiées a posteriori, en comparant les individus avant et après évolution.
D'une part, grâce aux outils de la théorie des réseaux complexes, nous montrons l'émergence d'un certain nombre de propriétés topologiques, notamment la propriété de réseau ``petit-monde''. Ces propriétés topologiques sont similaires à celles observées au niveau de l'anatomie des systèmes nerveux en biologie. D'autre part, au niveau de la dynamique, nous établissons que la propriété de synchronisation neuronale à large-échelle, résultant de la présentation d'un stimulus, est présente chez les individus évolués. Pour ce faire, nous nous appuyons sur les outils classiquement utilisés en électrophysiologie, et nous les étendons pour pouvoir interpréter la grande quantité de données obtenue à partir du modèle.
Le modèle montre que l'on peut construire des réseaux de neurones basés sur l'hypothèse du liage temporel en ayant recours à l'évolution artificielle, en se basant sur un critère de performance écologique, c.à.d. le comportement de l'individu dans son environnement. D'autre part, les outils développés pour l'analyse des propriétés du modèle peuvent être utilisés dans d'autres domaines, en premier lieu en électrophysiologie. En effet, à cause des progrès techniques sur les enregistrements électrophysiologiques, la quantité de données se rapproche singulièrement de celle issue du modèle.
Koiran, Pascal. "Puissance de calcul des réseaux de neurones artificiels." Lyon 1, 1993. http://www.theses.fr/1993LYO19003.
Graïne, Slimane. "Inférence grammaticale régulière par les réseaux de neurones." Paris 13, 1994. http://www.theses.fr/1994PA132020.
Le, Fablec Yann. "Prévision de trajectoires d'avions par réseaux de neurones." Toulouse, INPT, 1999. http://www.theses.fr/1999INPT034H.
Corne, Christophe. "Parallélisation de réseaux de neurones sur architecture distribuée." Mulhouse, 1999. http://www.theses.fr/1999MULH0583.
Fernandez, Brillet Lucas. "Réseaux de neurones CNN pour la vision embarquée." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM043.
Recently, 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
He, 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.
Pompougnac, Hugo. "Spécification et compilation de réseaux de neurones embarqués." Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS436.
In 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
Pothier, Dominique. "Réseaux convolutifs à politiques." Master's thesis, Université Laval, 2021. http://hdl.handle.net/20.500.11794/69184.
Despite their excellent performances, artificial neural networks high demand of both data and computational power limit their adoption in many domains. Developing less demanding architecture thus remain an important endeavor. This thesis seeks to produce a more flexible and less resource-intensive architecture by using reinforcement learning theory. When considering a network as an agent instead of a function approximator, one realize that the implicit policy followed by popular feed forward networks is extremely simple. We hypothesize that an architecture able to learn a more flexible policy could reach similar performances while reducing its resource footprint. The architecture we propose is inspired by research done in weight prediction, particularly by the hypernetwork architecture, which we use as a baseline model.Our results show that learning a dynamic policy achieving similar results to the static policies of conventional networks is not a trivial task. Our proposed architecture succeeds in limiting its parameter space by 20%, but does so at the cost of a 24% computation increase and loss of5% accuracy. Despite those results, we believe that this architecture provides a baseline that can be improved in multiple ways that we describe in the conclusion.
Oussar, Yacine. "Réseaux d'ondelettes et réseaux de neurones pour la modélisation statique et dynamique de processus." Phd thesis, Université Pierre et Marie Curie - Paris VI, 1998. http://pastel.archives-ouvertes.fr/pastel-00000677.
Bissery, Christophe. "La détection centralisée des fuites sur les réseaux d'eau potable par réseaux de neurones." Lyon, INSA, 1994. http://www.theses.fr/1994ISAL0112.
For few years, under the influence of the urban environment, the perception of dysfunction risk in technical systems and in particular in water supply networks has changed. The lack of risk doesn't exist and it's necessary to learn how to manage it. It's in this way that appears the need of centralized leakage detection on water supply networks, leaks that represent an important part of the dysfunction risk of water supply. This study proposes a centralized leakage detection system using a computerized neural network approach. The building method of learning bases and the sensors localization method are pointed out and developed. This study has showed that on a realistic network model results obtained with the centralized leakage detection system using a computerized neural network approach allowed experimentations on real networks. The study ends on the presentation of the working priorities for these real experimentations (and in particular the need of hourly water consumption previsions)
Giraudin, Aurore. "Réseaux de neurones et fonction respiratoire : mécanismes sensorimoteurs à la base du coupage locomotion-respiration." Thesis, Bordeaux 1, 2008. http://www.theses.fr/2008BOR13746/document.
Respiration is an autonomous rhythmic motor activity that requires the coordinated contractions of diverse muscles to produce ventilatory movements adapted to organismal needs. This crucial physiological function must be reliable and adaptable on a short-term basis, and requires coordianted movements with various other motor activities. For instance, respiratory rhythmicity becomes coupled to locomotion during physical exercise. My doctoral work aimed to explore the neurogenic mechanisms underlying the interactions between these two motor functions in the neonatal rat. This work was mainly conducted on isolated in vitro brain stem-spinal cord preparations of newborn rats (0-3 days), an experimental model that allows the maintenance of the still functional respiratory and locomotor CPGs in vitro. Due to the easy access to the neuronal networks in these preparations, locomotor-respiratory coupling and respiratory entrainment mechanisms were investigated by combined electrophysiological, neuroanatomical, pharmacological and lesional approaches. A major finding was the crucial played by sensory information from fore- and hindlimb in respiratory entrainment induced by locomotor rythmicity. Spinal sensory afferents can reset and entrain the activity of the medullary respiratory centres via a pontine relay, as well as making direct connections with the various spinal respiratory motoneuron (phrenic, intercostal and abdominal) populations
Boitard, Constance. "Identification des réseaux neurobiologiques gouvernant les apprentissages ambigus chez l'abeille Apis mellifera." Thesis, Toulouse 3, 2015. http://www.theses.fr/2015TOU30125/document.
Associative learning spans different levels of complexity, from simple tasks involving simple causal relationships between events, to ambiguous tasks, in which animals have to solve complex discriminations based on non-linear associative links. We focused on two protocols presenting a temporal or configural ambiguity at the level of stimulus contingencies in honey bees (\textit{Apis mellifera}). We performed selective blockades of GABAergic signalisation from recurrent feedback neurons in the mushroom bodies (MBs), higher-order insect brain structures associated with memory storage and retrieval, and found that this blockade within the MB calyces impaired both ambiguous learning tasks, although if did not affect simple conditioning counterparts. We suggest that the A3v cluster of the GABA feedback neurons innervating the MBs calyces are thus dispensable for simple learning, but are required for counteracting stimulus ambiguity in complex discriminations in honey bees
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.
Cofré, Rodrigo. "Statistique de potentiels d'action et distributions de Gibbs dans les réseaux de neurones." Thesis, Nice, 2014. http://www.theses.fr/2014NICE4078/document.
Sensory neurons respond to external stimulus using sequences of action potentials (“spikes”). They convey collectively to the brain information about the stimulus using spatio-temporal patterns of spikes (spike trains), that constitute a “neural code”. Since spikes patterns occur irregularly (yet highly structured) both within and over repeated trials, it is reasonable to characterize them using statistical methods and probabilistic descriptions. However, the statistical characterization of experimental data presents several major constraints: apart from those inherent to empirical statistics like finite size sampling, ‘the’ underlying statistical model is unknown. In this thesis we adopt a complementary approach to experiments. We consider neuromimetic models allowing the study of collective spike trains statistics and how it depends on network architecture and history, as well as on the stimulus. First, we consider a conductance-based Integrate-and-Fire model with chemical and electric synapses. We show that the spike train statistics is characterized by non-stationary, infinite memory, distribution consistent with conditional probabilities (Left interval specifications), which is continuous and non null, thus a Gibbs distribution. Then, we present a novel method that allows us to unify spatio-temporal Maximum Entropy models (whose invariant measure are Gibbs distributions in the Bowen sense) and neuro-mimetic models, providing a solid ground towards biophysical explanation of spatio-temporal correlations observed in experimental data. Finally, using these tools, we discuss the stimulus response of retinal ganglion cells, and the possible generalization of the co
Chevalier, Stéphanie. "Plasticité post-lésionnelle des réseaux médullaires locomoteurs des urodèles : étude électrophysiologique et immunohistochimique." Bordeaux 2, 2004. http://www.theses.fr/2004BOR21178.
Urodeles can recover spontaneously their locomotor behaviour following a complete spinal cord transection. Using electrophysiological and neuroanatomical in vivo techniques, we have shown that locomotor recovery is related to a reinnervation of locomotor networks below the lesion by reticulospinal axons. Some of the regenerated reticulospinal axons come from glutamatergic and serotoninergic neurons. However, long term post-lesionnal modifications of the locomotor patterns were observed. Moreover, in vitro study of intrinsic properties of motoneurons, before and after spinal cord transection, showed that the muscarinic modulation of motoneuron excitability is increased after spinalisation. In conclusion, the post-lesionnal plasticity of Urodele locomotor networks depends both on their reinnervation by descending pathways and on modifications of motoneuron intrinsic properties