Teses / dissertações sobre o tema "Réseaux de neurones lipschitz"
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Veja os 50 melhores trabalhos (teses / dissertações) para estudos sobre o assunto "Réseaux de neurones lipschitz".
Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.
Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.
Veja as teses / dissertações das mais diversas áreas científicas e compile uma bibliografia correta.
Béthune, Louis. "Apprentissage profond avec contraintes Lipschitz". Electronic Thesis or Diss., Université de Toulouse (2023-....), 2024. http://www.theses.fr/2024TLSES014.
Texto completo da fonteThis thesis explores the characteristics and applications of Lipschitz networks in machine learning tasks. First, the framework of "optimization as a layer" is presented, showcasing various applications, including the parametrization of Lipschitz-constrained layers. Then, the expressiveness of these networks in classification tasks is investigated, revealing an accuracy/robustness tradeoff controlled by entropic regularization of the loss, accompanied by generalization guarantees. Subsequently, the research delves into the utilization of signed distance functions as a solution to a regularized optimal transport problem, showcasing their efficacy in robust one-class learning and the construction of neural implicit surfaces. After, the thesis demonstrates the adaptability of the back-propagation algorithm to propagate bounds instead of vectors, enabling differentially private training of Lipschitz networks without incurring runtime and memory overhead. Finally, it goes beyond Lipschitz constraints and explores the use of convexity constraint for multivariate quantiles
Neacșu, Ana-Antonia. "Robust Deep learning methods inspired by signal processing algorithms". Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPAST212.
Texto completo da fonteUnderstanding the importance of defense strategies against adversarial attacks has become paramount in ensuring the trustworthiness and resilience of neural networks. While traditional security measures focused on protecting data and software from external threats, the unique challenge posed by adversarial attacks lies in their ability to exploit the inherent vulnerabilities of the underlying machine learning algorithms themselves.The first part of the thesis proposes new constrained learning strategies that ensure robustness against adversarial perturbations by controlling the Lipschitz constant of a classifier. We focus on nonnegative neural networks for which accurate Lipschitz bounds can be derived, and we propose different spectral norm constraints offering robustness guarantees from a theoretical viewpoint. We validate our solution in the context of gesture recognition based on Surface Electromyographic (sEMG) signals.In the second part of the thesis, we propose a new class of neural networks (ACNN) which can be viewed as establishing a link between fully connected and convolutional networks, and we propose an iterative algorithm to control their robustness during training. Next, we extend our solution to the complex plane and address the problem of designing robust complex-valued neural networks by proposing a new architecture (RCFF-Net) for which we derive tight Lipschitz constant bounds. Both solutions are validated for audio denoising.In the last part, we introduce ABBA Networks, a novel class of (almost) non-negative neural networks, which we show to be universal approximators. We derive tight Lipschitz bounds for both linear and convolutional layers, and we propose an algorithm to train robust ABBA networks. We show the effectiveness of the proposed approach in the context of image classification
Gupta, Kavya. "Stability Quantification of Neural Networks". Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPAST004.
Texto completo da fonteArtificial neural networks are at the core of recent advances in Artificial Intelligence. One of the main challenges faced today, especially by companies likeThales designing advanced industrial systems is to ensure the safety of newgenerations of products using these technologies. In 2013 in a key observation, neural networks were shown to be sensitive to adversarial perturbations, raising serious concerns about their applicability in critically safe environments. In the last years, publications studying the various aspects of this robustness of neural networks, and rising questions such as "Why adversarial attacks occur?", "How can we make the neural network more robust to adversarial noise?", "How to generate stronger attacks?" etc., have grown exponentially. The contributions of this thesis aim to tackle such problems. The adversarial machine learning community concentrates majorly on classification scenarios, whereas studies on regression tasks are scarce. Our contributions bridge this significant gap between adversarial machine learning and regression applications.The first contribution in Chapter 3 proposes a white-box attackers designed to attack regression models. The presented adversarial attacker is derived from the algebraic properties of the Jacobian of the network. We show that our attacker successfully fools the neural network and measure its effectiveness in reducing the estimation performance. We present our results on various open-source and real industrial tabular datasets. Our analysis relies on the quantification of the fooling error as well as different error metrics. Another noteworthy feature of our attacker is that it allows us to optimally attack a subset of inputs, which may help to analyze the sensitivity of some specific inputs. We also, show the effect of this attacker on spectrally normalised trained models which are known to be more robust in handling attacks.The second contribution of this thesis (Chapter 4) presents a multivariate Lipschitz constant analysis of neural networks. The Lipschitz constant is widely used in the literature to study the internal properties of neural networks. But most works do a single parametric analysis, which do not allow to quantify the effect of individual inputs on the output. We propose a multivariate Lipschitz constant-based stability analysis of fully connected neural networks allowing us to capture the influence of each input or group of inputs on the neural network stability. Our approach relies on a suitable re-normalization of the input space, intending to perform a more precise analysis than the one provided by a global Lipschitz constant. We display the results of this analysis by a new representation designed for machine learning practitioners and safety engineers termed as a Lipschitz star. We perform experiments on various open-access tabular datasets and an actual Thales Air Mobility industrial application subject to certification requirements.The use of spectral normalization in designing a stability control loop is discussed in Chapter 5. A critical part of the optimal model is to behave according to specified performance and stability targets while in operation. But imposing tight Lipschitz constant constraints while training the models usually leads to a reduction of their accuracy. Hence, we design an algorithm to train "stable-by-design" neural network models using our spectral normalization approach, which optimizes the model by taking into account both performance and stability targets. We focus on Small Unmanned Aerial Vehicles (UAVs). More specifically, we present a novel application of neural networks to detect in real-time elevon positioning faults to allow the remote pilot to take necessary actions to ensure safety
Wenzek, Didier. "Construction de réseaux de neurones". Phd thesis, Grenoble INPG, 1993. http://tel.archives-ouvertes.fr/tel-00343569.
Texto completo da fonteTsopze, 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.
Texto completo da fonteThe 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
Voegtlin, Thomas. "Réseaux de neurones et auto-référence". Lyon 2, 2002. http://theses.univ-lyon2.fr/documents/lyon2/2002/voegtlin_t.
Texto completo da fonteThe 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.
Texto completo da fonteCôté, Marc-Alexandre. "Réseaux de neurones génératifs avec structure". Thèse, Université de Sherbrooke, 2017. http://hdl.handle.net/11143/10489.
Texto completo da fonteJodouin, 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.
Texto completo da fonteBrette, 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.
Texto completo da fonteTardif, Patrice. "Autostructuration des réseaux de neurones avec retards". Thesis, Université Laval, 2007. http://www.theses.ulaval.ca/2007/24240/24240.pdf.
Texto completo da fonteMaktoobi, Sheler. "Couplage diffractif pour réseaux de neurones optiques". Thesis, Bourgogne Franche-Comté, 2020. http://www.theses.fr/2020UBFCD019.
Texto completo da fontePhotonic 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.
Texto completo da fonteBigot, Pascal. "Utilisation des réseaux de neurones pour la télégestion des réseaux techniques urbains". Lyon 1, 1995. http://www.theses.fr/1995LYO10036.
Texto completo da fonteKoiran, Pascal. "Puissance de calcul des réseaux de neurones artificiels". Lyon 1, 1993. http://www.theses.fr/1993LYO19003.
Texto completo da fonteGraïne, Slimane. "Inférence grammaticale régulière par les réseaux de neurones". Paris 13, 1994. http://www.theses.fr/1994PA132020.
Texto completo da fonteLe, Fablec Yann. "Prévision de trajectoires d'avions par réseaux de neurones". Toulouse, INPT, 1999. http://www.theses.fr/1999INPT034H.
Texto completo da fonteCorne, Christophe. "Parallélisation de réseaux de neurones sur architecture distribuée". Mulhouse, 1999. http://www.theses.fr/1999MULH0583.
Texto completo da fonteFernandez, Brillet Lucas. "Réseaux de neurones CNN pour la vision embarquée". Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM043.
Texto completo da fonteRecently, 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.
Texto completo da fontePompougnac, Hugo. "Spécification et compilation de réseaux de neurones embarqués". Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS436.
Texto completo da fonteIn 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
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.
Texto completo da fonteGatet, Laurent. "Intégration de Réseaux de Neurones pour la Télémétrie Laser". Phd thesis, Toulouse, INPT, 2007. http://oatao.univ-toulouse.fr/7595/1/gatet.pdf.
Texto completo da fonteRobitaille, 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.
Texto completo da fonteDucom, Jean-Christophe. "Codage temporel et apprentissage dans les réseaux de neurones". Aix-Marseille 1, 1996. http://www.theses.fr/1996AIX11041.
Texto completo da fonteBenaïm, Michel. "Dynamiques d'activation et dynamiques d'apprentissage des réseaux de neurones". Toulouse, ENSAE, 1992. http://www.theses.fr/1992ESAE0001.
Texto completo da fonteAupetit, Michaël. "Approximation de variétés par réseaux de neurones auto-organisés". Grenoble INPG, 2001. http://www.theses.fr/2001INPG0128.
Texto completo da fonteJiang, Fei. "Optimisation de la topologie de grands réseaux de neurones". Paris 11, 2009. http://www.theses.fr/2009PA112211.
Texto completo da fonteIn this dissertation, we present our study regarding the influence of the topology on the learning performances of neural networks with complex topologies. Three different neural networks have been investigated: the classical Self-Organizing Maps (SOM) with complex graph topology, the Echo States Network (ESN) and the Standard Model Features(SMF). In each case, we begin by comparing the performances of different topologies for the same task. We then try to optimize the topology of some neural network in order to improve such performance. The first part deals with Self-Organizing Maps, and the task is the standard classification of handwritten digits from the MNIST database. We show that topology has a small impact on performance and robustness to neuron failures, at least at long learning times. Performance may however be increased by almost 10% by artificial evolution of the network topology. In our experimental conditions, the evolved networks are more random than their parents, but display a more heterogeneous degree distribution. In the second part, we propose to apply CMA-ES, the state-of-the-art method in evolutionary continuous parameter optimization, to the evolutionary learning of the parameters of an Echo State Network (the Readout weights, of course, but also, Spectral Radius, Slopes of the neurons active function). First, a standard supervised learning problem is used to validate the approach and compare it to the original one. But the flexibility of Evolutionary optimization allows us to optimize not only the outgoing weights but also, or alternatively, other ESN parameters, sometimes leading to improved results. The classical double pole balancing control problem is used to demonstrate the feasibility of evolutionary reinforcement learning of ESN. We show that the evolutionary ESN obtain results that are comparable with those of the best topology-learning neuro-evolution methods. Finally, the last part presents our initial research of the SMF - a visual object recognition model which is inspired by the visual cortex. Two version based on SMF are applied to the PASCAL Visual multi-Object recognition Challenge (VOC2008). The long terms goal is to find the optimal topology of the SMF model, but the computation cost is however too expensive to optimize the complete topology directly. So as a first step, we apply an Evolutionary Algorithm to auto-select the feature used by the systems. We show that, for the VOC2008 challenge, with only 20% selected feature, the system can perform as well as with all 1000 randomly selected feature
Alvado, Ludovic. "Neurones artificiels sur silicium : une évolution vers les réseaux". Bordeaux 1, 2003. http://www.theses.fr/2003BOR12674.
Texto completo da fonteThis thesis describes a new approach for modelling biological neuron networks. This approach uses analogue specific integrated circuit (ASIC) in which Hodgkin-Huxley formalism as been implemented to integrate medium density artificial neural network, modelled at a biological realistic level. This thesis also deals with the component mismatches problem and the pertinent choice of optimized structure dedicated to network applications
Biela, Philippe. "Classification automatique d'observations multidimensionnelles par réseaux de neurones compétitifs". Lille 1, 1999. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/1999/50376-1999-469.pdf.
Texto completo da fonteElhor, Noureddine. "Suivi de fonctionnement d'une éolienne par réseaux de neurones". Lille 1, 2000. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/2000/50376-2000-57.pdf.
Texto completo da fonteLa projection non lineaire offre une visualisation plane des donnees alors que les comparaisons entre les sorties estimees et reelles generent des residus permettant de verifier si le spectre courant a devie ou non du fonctionnement normal memorise par le reseau. Pour valider notre etude, nous avons teste les performances du reseau sur des donnees en fonctionnement normal acquis dans des situations differentes de celles de la base d'apprentissage et sur des situations correspondant a des defauts simules type balourd. Ce type de defauts se manifeste par l'apparition d'une frequence et ses harmoniques dans le spectre d'energie. Dans les deux situations, les resultats obtenus par le reseau ont ete quantifies et se sont reveles satisfaisants. Nous avons exploite, par ailleurs, un reseau modulaire a apprentissage supervise pour la discrimination entre deux situations : le fonctionnement normal et la presence d'un defaut type balourd d'une amplitude minimale fixee. Les performances du reseau ont ete testees sur des defauts d'amplitudes differentes. Souvent les methodes de diagnostic sont appliquees sur des bancs d'essais dans des conditions de laboratoire controlees. Notre demarche est d'autant plus importante que nous surveillons une machine reelle en pleine production
Chakik, Fadi El. "Maximum d'entropie et réseaux de neurones pour la classification". Grenoble INPG, 1998. http://www.theses.fr/1998INPG0091.
Texto completo da fonteDemartines, Pierre. "Analyse de données par réseaux de neurones auto-organisés". Grenoble INPG, 1994. http://www.theses.fr/1994INPG0129.
Texto completo da fonteOussar, 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.
Texto completo da fonteBissery, Christophe. "La détection centralisée des fuites sur les réseaux d'eau potable par réseaux de neurones". Lyon, INSA, 1994. http://www.theses.fr/1994ISAL0112.
Texto completo da fonteFor 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)
Basterrech, Sebastián. "Apprentissage avec les réseaux de neurones aléatoires et les machines de calcul avec réservoir de neurones". Rennes 1, 2012. http://www.theses.fr/2012REN1S178.
Texto completo da fonteSince the 1980s a new computational model merging concepts from neural networks and queuing theory was developed. The model was introduced under the name of Random Neural Networks (RNNs), inside the field of Neural Networks. In this thesis, a first contribution consists of an adaptation of quasi-Newton optimisation methods for training the RNN model. In the last decade, a new computational paradigm was introduced in the field of Machine Learning, under the name of Reservoir Computing (RC). One of the pioneers and most diffused RC methods is the Echo State Network (ESN) model. Here, we propose a method based on topographic maps to initialise the ESN procedure. Another contribution of the thesis is the introduction of a new RC model called the Echo State Queueing Network (ESQN), where we use ideas coming from RNNs for the design of the reservoir. An ESQN consists of an ESN where the reservoir has a new dynamics inspired by recurrent RNNs. In this thesis, we position the ESQN method in the global Machine Learning area, and provide examples of their use and performances. Finally, we propose a method for real–time estimation of Speech Quality using the learning tools above described. Audio quality in the Internet can be strongly affected by network conditions. As a consequence, many techniques to evaluate it have been developed. In particular, the ITU-T adopted in 2001 a technique called Perceptual Evaluation of Speech Quality (PESQ) to automatically measuring speech quality. PESQ is a well-known and widely used procedure, providing in general an accurate evaluation of perceptual quality by comparing the original and received voice sequences. The thesis provides a procedure for estimating PESQ output working only with measures taken on the network state and using some properties of the communication system, without any original signal. The experimental results obtained prove the capability of our approach to give good estimations of the speech quality in a real–time context
Krauth, Werner. "Physique statistique des réseaux de neurones et de l'optimisation combinatoire". Phd thesis, Université Paris Sud - Paris XI, 1989. http://tel.archives-ouvertes.fr/tel-00011866.
Texto completo da fontePersonnaz, Léon. "Etude des réseaux de neurones formels : conception, propriétés et applications". Paris 6, 1986. http://www.theses.fr/1986PA066569.
Texto completo da fonteMercier, David. "Hétéro-association de signaux audio-vidéo par réseaux de neurones". Rennes 1, 2003. http://www.theses.fr/2003REN10009.
Texto completo da fontePuechmorel, Stéphane. "Réseaux de neurones et optimisation globale en analyse temps-fréquence". Toulouse, INPT, 1994. http://www.theses.fr/1994INPT105H.
Texto completo da fonteBoné, Romuald. "Réseaux de neurones récurrents pour la prévision de séries temporelles". Tours, 2000. http://www.theses.fr/2000TOUR4003.
Texto completo da fonteStrock, Anthony. "Mémoire de travail dans les réseaux de neurones récurrents aléatoires". Thesis, Bordeaux, 2020. http://www.theses.fr/2020BORD0195.
Texto completo da fonteWorking memory can be defined as the ability to temporarily store and manipulate information of any kind.For example, imagine that you are asked to mentally add a series of numbers.In order to accomplish this task, you need to keep track of the partial sum that needs to be updated every time a new number is given.The working memory is precisely what would make it possible to maintain (i.e. temporarily store) the partial sum and to update it (i.e. manipulate).In this thesis, we propose to explore the neuronal implementations of this working memory using a limited number of hypotheses.To do this, we place ourselves in the general context of recurrent neural networks and we propose to use in particular the reservoir computing paradigm.This type of very simple model nevertheless makes it possible to produce dynamics that learning can take advantage of to solve a given task.In this job, the task to be performed is a gated working memory task.The model receives as input a signal which controls the update of the memory.When the door is closed, the model should maintain its current memory state, while when open, it should update it based on an input.In our approach, this additional input is present at all times, even when there is no update to do.In other words, we require our model to be an open system, i.e. a system which is always disturbed by its inputs but which must nevertheless learn to keep a stable memory.In the first part of this work, we present the architecture of the model and its properties, then we show its robustness through a parameter sensitivity study.This shows that the model is extremely robust for a wide range of parameters.More or less, any random population of neurons can be used to perform gating.Furthermore, after learning, we highlight an interesting property of the model, namely that information can be maintained in a fully distributed manner, i.e. without being correlated to any of the neurons but only to the dynamics of the group.More precisely, working memory is not correlated with the sustained activity of neurons, which has nevertheless been observed for a long time in the literature and recently questioned experimentally.This model confirms these results at the theoretical level.In the second part of this work, we show how these models obtained by learning can be extended in order to manipulate the information which is in the latent space.We therefore propose to consider conceptors which can be conceptualized as a set of synaptic weights which constrain the dynamics of the reservoir and direct it towards particular subspaces; for example subspaces corresponding to the maintenance of a particular value.More generally, we show that these conceptors can not only maintain information, they can also maintain functions.In the case of mental arithmetic mentioned previously, these conceptors then make it possible to remember and apply the operation to be carried out on the various inputs given to the system.These conceptors therefore make it possible to instantiate a procedural working memory in addition to the declarative working memory.We conclude this work by putting this theoretical model into perspective with respect to biology and neurosciences
Chevallier, Julien. "Modélisation de grands réseaux de neurones par processus de Hawkes". Thesis, Université Côte d'Azur (ComUE), 2016. http://www.theses.fr/2016AZUR4051/document.
Texto completo da fonteHow does the brain compute complex tasks? Is it possible to create en artificial brain? In order to answer these questions, a key step is to build mathematical models for information processing in the brain. Hence this manuscript focuses on biological neural networks and their modelling. This thesis lies in between three domains of mathematics - the study of partial differential equations (PDE), probabilities and statistics - and deals with their application to neuroscience. On the one hand, the bridges between two neural network models, involving two different scales, are highlighted. At a microscopic scale, the electrical activity of each neuron is described by a temporal point process. At a larger scale, an age structured system of PDE gives the global activity. There are two ways to derive the macroscopic model (PDE system) starting from the microscopic one: by studying the mean dynamics of one typical neuron or by investigating the dynamics of a mean-field network of $n$ neurons when $n$ goes to infinity. In the second case, we furthermore prove the convergence towards an explicit limit dynamics and inspect the fluctuations of the microscopic dynamics around its limit. On the other hand, a method to detect synchronisations between two or more neurons is proposed. To do so, tests of independence between temporal point processes are constructed. The level of the tests are theoretically controlled and the practical validity of the method is illustrated by a simulation study. Finally, the method is applied on real data
Oudjail, Veïs. "Réseaux de neurones impulsionnels appliqués à la vision par ordinateur". Electronic Thesis or Diss., Université de Lille (2022-....), 2022. http://www.theses.fr/2022ULILB048.
Texto completo da fonteArtificial neural networks (ANN) have become a must-have technique in computer vision, a trend that started during the 2012 ImageNet challenge. However, this success comes with a non-negligible human cost for manual data labeling, very important in model learning, and a high energy cost caused by the need for large computational resources. Spiking Neural Networks (SNN) provide solutions to these problems. It is a particular class of ANNs, close to the biological model, in which neurons communicate asynchronously by representing information through spikes. The learning of SNNs can rely on an unsupervised rule: the STDP. It modulates the synaptic weights according to the local temporal correlations observed between the incoming and outgoing spikes. Different hardware architectures have been designed to exploit the properties of SNNs (asynchrony, sparse and local operation, etc.) in order to design low-power solutions, some of them dividing the cost by several orders of magnitude. SNNs are gaining popularity and there is growing interest in applying them to vision. Recent work shows that SNNs are maturing by being competitive with the state of the art on "simple" image datasets such as MNIST (handwritten numbers) but not on more complex datasets. However, SNNs can potentially stand out from ANNs in video processing. The first reason is that these models incorporate an additional temporal dimension. The second reason is that they lend themselves well to the use of event-driven cameras. They are bio-inspired sensors that perceive temporal contrasts in a scene, in other words, they are sensitive to motion. Each pixel can detect a light variation (positive or negative), which triggers an event. Coupling these cameras to neuromorphic chips allows the creation of totally asynchronous and massively parallelized vision systems. The objective of this thesis is to exploit the capabilities offered by SNNs in video processing. In order to explore the potential offered by SNNs, we are interested in motion analysis and more particularly in motion direction estimation. The goal is to develop a model capable of learning incrementally, without supervision and with few examples, to extract spatiotemporal features. We have therefore performed several studies examining the different points mentioned using synthetic event datasets. We show that the tuning of the SNN parameters is essential for the model to be able to extract useful features. We also show that the model is able to learn incrementally by presenting it with new classes without deteriorating the performance on the mastered classes. Finally, we discuss some limitations, especially on the weight learning, suggesting the possibility of more delay learning, which are still not very well exploited and which could mark a break with ANNs
Carrillo, Hernan. "Colorisation d'images avec réseaux de neurones guidés par l'intéraction humaine". Electronic Thesis or Diss., Bordeaux, 2024. http://www.theses.fr/2024BORD0016.
Texto completo da fonteColorization is the process of adding colors to grayscale images. It is an important task in the image-editing and animation community. Although automatic colorization methods exist, they often produce unsatisfying results due to artifacts such as color bleeding, inconsistency, unnatural colors, and the ill-posed nature of the problem. Manual intervention is often necessary to achieve the desired outcome. Consequently, there is a growing interest in automating the colorization process while allowing artists to transfer their own style and vision to the process. In this thesis, we investigate various interaction formats by guiding colors of specific areas of an image or transferring them from a reference image or object. As part of this research, we introduce two semi-automatic colorization frameworks. First, we describe a deep learning architecture for exemplar-based image colorization that takes into account user’s reference images. Our second framework uses a diffusion model to colorize line art using user-provided color scribbles. This thesis first delves into a comprehensive overview of state-of-the-art image colorization methods, color spaces, evaluation metrics, and losses. While recent colorization methods based on deep-learning techniques are achieving the best results on this task, these methods are based on complex architectures and a high number of joint losses, which makes the reasoning behind each of these methods difficult. Here, we leverage a simple architecture in order to analyze the impact of different color spaces and several losses. Then, we propose a novel attention layer based on superpixel features to establish robust correspondences between high-resolution deep features from target and reference image pairs, called super-attention. This proposal deals with the quadratic complexity problem of the non-local calculation in the attention layer. Additionally, it helps to overcome color bleeding artifacts. We study its use in color transfer and exemplar-based colorization. We finally extend this model to specifically guide the colorization on segmented objects. Finally, we propose a diffusion probabilistic model based on implicit and explicit conditioning mechanism, to learn colorizing line art. Our approach enables the incorporation of user guidance through explicit color hints while leveraging on the prior knowledge from the trained diffusion model. We condition with an application-specific encoder that learns to extract meaningful information on user-provided scribbles. The method generates diverse and high-quality colorized images
Pothier, Dominique. "Réseaux convolutifs à politiques". Master's thesis, Université Laval, 2021. http://hdl.handle.net/20.500.11794/69184.
Texto completo da fonteDespite 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.
Koubi, Vassilada. "Reseaux de neurones et optimisation combinatoire". Paris 5, 1994. http://www.theses.fr/1994PA05S014.
Texto completo da fonteRichard, Vincent. "Outils de synthèse pour les réseaux réflecteurs exploitant la cellule Phoenix et les réseaux de neurones". Thesis, Rennes, INSA, 2018. http://www.theses.fr/2018ISAR0004/document.
Texto completo da fonteIn collaboration with Thales Alenia Space and the French Space Agency (CNES), this PHD takes part in a very active international context on a new antenna: the reflectarrays (RA).Combining the advantages of conventional reflectors and those of networks, RA could eventually replace the currently used shaped reflectors. They consist of a primary source placed in front of a network of cells controlling the properties of the reflected electromagnetic field. Although many studies already focus on the characterization of cells, one of the issues is to carefully select them to achieve the final antenna: this is the synthesis step.An overview of different synthesis methods revealed the complexity to quickly obtain good performance simultaneously on the co- and cross-polarizations, for a wide frequency band and for the realization of shaped radiation pattern. The Phoenix cell is selected in this work for its good properties since it provides the entire phase range following a continuous cycle of geometries.Because one of the constraints in the design of RA is to maintain continuous geometry variations between two juxtaposed cells on the layout, a spherical representation tool made it possible to classify all the studied cells. It judiciously lists all the cells on a continuous, closed and periodic surface.A new step is reached with the design of behavioral models using Artificial Neural Networks (ANN). These models enable to a fast electromagnetic characterization of cells in terms of phase and amplitude of the direct and cross coefficients of the reflection matrix.The originality of the synthesis algorithm proposed in this work is the combined use of the spherical representation and a rapid cell characterization by ANN. A min / max optimization tool is used to improve the overall performance of the RA panel. It is then applied to a concrete case as part of a telecommunication mission
Bernauer, Éric. "Les réseaux de neurones et l'aide au diagnostic : un modèle de neurones bouclés pour l'apprentissage de séquences temporelles". Toulouse 3, 1996. http://www.theses.fr/1996TOU30277.
Texto completo da fonteAziz, Mohammed, e Abdelaziz Bensrhair. "Apprentissage de réseaux de neurones impulsionnels. Application à des systèmes sensorimoteurs". INSA de Rouen, 2005. http://www.theses.fr/2005ISAM0005.
Texto completo da fonte