Dissertations / Theses on the topic 'Réseaux de neurones artificiels (ANNs)'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Réseaux de neurones artificiels (ANNs).'
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.
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.
Full textSince 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
Blagouchine, Iaroslav. "Modélisation et analyse de la parole : Contrôle d’un robot parlant via un modèle interne optimal basé sur les réseaux de neurones artificiels. Outils statistiques en analyse de la parole." Thesis, Aix-Marseille 2, 2010. http://www.theses.fr/2010AIX26666.
Full textThis Ph.D. dissertation deals with speech modeling and processing, which both share the speech quality aspect. An optimum internal model with constraints is proposed and discussed for the control of a biomechanical speech robot based on the equilibrium point hypothesis (EPH, lambda-model). It is supposed that the robot internal space is composed of the motor commands lambda of the equilibrium point hypothesis. The main idea of the work is that the robot movements, and in particular the robot speech production, are carried out in such a way that, the length of the path, traveled in the internal space, is minimized under acoustical and mechanical constraints. Mathematical aspect of the problem leads to one of the problems of variational calculus, the so-called geodesic problem, whose exact analytical solution is quite complicated. By using some empirical findings, an approximate solution for the proposed optimum internal model is then developed and implemented. It gives interesting and challenging results, and shows that the proposed internal model is quite realistic; namely, some similarities are found between the robot speech and the real one. Next, by aiming to analyze speech signals, several methods of statistical speech signal processing are developed. They are based on higher-order statistics (namely, on normalized central moments and on the fourth-order cumulant), as well as on the discrete normalized entropy. In this framework, we also designed an unbiased and efficient estimator of the fourth-order cumulant in both batch and adaptive versions
Koiran, Pascal. "Puissance de calcul des réseaux de neurones artificiels." Lyon 1, 1993. http://www.theses.fr/1993LYO19003.
Full textBazzi, Hussein. "Resistive memory co-design in CMOS technologies." Electronic Thesis or Diss., Aix-Marseille, 2020. http://www.theses.fr/2020AIXM0567.
Full textMany diversified applications (internet of things, embedded systems for automotive and medical applications, artificial intelligence) require an integrated circuit (SoC, System on Chip) with high-performance non-volatile memories to operate optimally. Although Flash memory is widely used today, this technology needs high voltage for programing operations and has reliability issues that are hard to handle beyond 18 nm technological node, increasing the cost of circuit design and fabrication. In this context, the semiconductor industry seeks an alternative non-volatile memory that can replace Flash memories. Among possible candidates (MRAM - Magnetic Random Access Memory, PCM - Phase Change Memory, FeRAM - Ferroelectric Random Access Memory), Resistive memories (RRAMs) offer superior performances on essential key points: compatibility with CMOS manufacturing processes, scalability, current consumption (standby and active), operational speed. Due to its relatively simple structure, RRAM technology can be easily integrated in any design flow opening the way for the development of new architectures that answer Von Neumann bottleneck. In this thesis, the main object is to show the integration abilities of RRAM devices with CMOS technology, using circuit design and electrical measurements, in order to develop different hybrid structures: non-volatile Static Random Access Memories (SRAM), True Random Number Generator (TRNG) and artificial neural networks
Bénédic, Yohann. "Approche analytique pour l'optimisation de réseaux de neurones artificiels." Phd thesis, Université de Haute Alsace - Mulhouse, 2007. http://tel.archives-ouvertes.fr/tel-00605216.
Full textAlvado, Ludovic. "Neurones artificiels sur silicium : une évolution vers les réseaux." Bordeaux 1, 2003. http://www.theses.fr/2003BOR12674.
Full textThis 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
Bier, Thomas. "Disaggregation of Electrical Appliances using Non-Intrusive Load Monitoring." Thesis, Mulhouse, 2014. http://www.theses.fr/2014MULH8860/document.
Full textThis thesis presents a method to disaggregate electrical appliances in the load profile of residential buildings. In recent years, energy monitoring has obtained significantly popularity in private and industrial environment. With algorithms of the disaggregation, the measured data from so-called smart meters can be used to provide more information of the energy usage. One method to receive these data is called non-intrusive appliance load monitoring.The main part of the thesis can be divided into three parts. At first, an own measurement system was developed and verified. With that system, real data sets can be generated for the development and verification of the disaggregation algorithms. The second part describes the development of an event detector. Different methods are presented and evaluated, with which the switching times of the appliances can be detected in the load profile. The last part describes a classification method. Different features are used for the classification. The classifier recognizes and labels the individual appliances in the load profile. For the classification different structures of artificial neural network (ANN) are compared
Wang, Shengrui. "Réseaux multicouches de neurones artificiels : algorithmes d'apprentissage, implantations sur hypercube : applications." Phd thesis, Grenoble INPG, 1989. http://tel.archives-ouvertes.fr/tel-00335818.
Full textLaflaquière, Arnaud. "Neurones artificiels sur silicium : conception analogique et construction de réseaux hybrides." Bordeaux 1, 1998. http://www.theses.fr/1998BOR10617.
Full textNedjari, Tayeb. "Réseaux de neurones artificiels et connaissances symboliques : insertion, raffinement et extraction." Paris 13, 1998. http://www.theses.fr/1998PA132024.
Full textWilson, Dennis G. "Évolution des principes de la conception des réseaux de neurones artificiels." Thesis, Toulouse 3, 2019. http://www.theses.fr/2019TOU30075.
Full textThe biological brain is an ensemble of individual components which have evolved over millions of years. Neurons and other cells interact in a complex network from which intelligence emerges. Many of the neural designs found in the biological brain have been used in computational models to power artificial intelligence, with modern deep neural networks spurring a revolution in computer vision, machine translation, natural language processing, and many more domains. However, artificial neural networks are based on only a small subset of biological functionality of the brain, and often focus on global, homogeneous changes to a system that is complex and locally heterogeneous. In this work, we examine the biological brain, from single neurons to networks capable of learning. We examine individually the neural cell, the formation of connections between cells, and how a network learns over time. For each component, we use artificial evolution to find the principles of neural design that are optimized for artificial neural networks. We then propose a functional model of the brain which can be used to further study select components of the brain, with all functions designed for automatic optimization such as evolution. Our goal, ultimately, is to improve the performance of artificial neural networks through inspiration from modern neuroscience. However, through evaluating the biological brain in the context of an artificial agent, we hope to also provide models of the brain which can serve biologists
Martin, Philippe. "Réseaux de neurones artificiels : application à la reconnaissance optique de partitions musicales." Phd thesis, Grenoble 1, 1992. http://tel.archives-ouvertes.fr/tel-00340938.
Full textAssoum, Ammar. "Etude de la tolérance aux aléas logiques des réseaux de neurones artificiels." Phd thesis, Grenoble INPG, 1997. http://tel.archives-ouvertes.fr/tel-00004913.
Full textBourgeois, Yoann. "Les réseaux de neurones artificiels pour mesurer les risques économiques et financiers." Paris, EHESS, 2003. http://www.theses.fr/2003EHES0118.
Full textThe objective of this thesis is to provide complete methodologies to solve prediction and classification problems in economy and finance by using Artificial Neural networks. The plan of work shows that the thesisplays a great part in establishing in several ways a statistic methodology for neural networks. We proceed in four chapters. The first chapter describes supervised and unsupervised neural network methodology to modelize quantitative or qualitative variables. In the second chapter, we are interested by the bayesian approach for supervised neural networks and the developpement of a set of misspecification statistic tests for binary choice models. In chapter three, we show that multivariate supervised neural networks enable to take into account structural changes and the neural networks methodology is able to estimate some probabilities of exchange crisis. In chapter four, we develope a complete based neural network-GARCH model to manage a stocks portfolio. We introduce some terms as conditional returns or conditional risk for a stock or a portfolio. Next, we apply bayesian Self-Organizing Map in order to estimate the univariate probability density function of the DM/USD exchange rate
Gautier, Eric. "Utilisation des réseaux de neurones artificiels pour la commande d'un véhicule autonome." Grenoble INPG, 1999. http://www.theses.fr/1999INPG0009.
Full textThe subject of this thesis covers both mobile robotic and artificial neural networks (ANN) fields. Our aim is to study solutions that connectionist techniques can bring to particular problems raised by the automatic control of a car-like vehicle. This report is composed of two main parts. The first of them processes fundamental aspects of mobile robot control and of the use of artificial neural networks for control of complex systems. This first study allows us to underline the different points where ANN can contribute in a control architecture providing a real autonomy to the vehicle while respecting the robustness and rapidity constraints induced by the utilisation of a robot of the size and the speed of a car. We propose in the second part of this report several controllers allowing gradual increase of the robot autonomy. First of all, we are interested in a simple task consisting only in enslaving the robot on a reference path given by a planner. Our approach enables a continuous adaptation of the system facing possible changes of the parameters of the robot or its environment. So as to allow the execution of manoeuvres without external orders, we also propose a methodology for the realisation of controllers based on external sensors of the vehicle. Our approach uses a model allying characteristics from both fuzzy logic and ANN. Finally we show how complex tasks can be realised using a sequence of several simple controllers. Our realisation of the selection system for these controllers, which uses a recurrent ANN, exhibits some characteristics of robustness and very fast reactions when faced to the external events that must be taken into account
Frydlender, Hervé. "Implantation de réseaux de neurones artificiels sur multi-processeurs à mémoire distribuée." Grenoble INPG, 1992. http://www.theses.fr/1992INPG0132.
Full textChamekh, Abdessalem. "Optimisation des procédés de mise en forme par les réseaux de neurones artificiels." Phd thesis, Université d'Angers, 2008. http://tel.archives-ouvertes.fr/tel-00445341.
Full textHudon, Guillaume. "Quantification d'odeurs à l'aide de nez électroniques et de réseaux de neurones artificiels." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape8/PQDD_0016/MQ53580.pdf.
Full textRichard, 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.
Full textIn 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
Osório, Fernando Santos. "Inss : un système hybride neuro-symbolique pour l'apprentissage automatique constructif." Grenoble INPG, 1998. https://tel.archives-ouvertes.fr/tel-00004899.
Full textVarious Artificial Intelligence methods have been developed to reproduce intelligent human behaviour. These methods allow to reproduce some human reasoning process using the available knowledge. Each method has its advantages, but also some drawbacks. Hybrid systems combine different approaches in order to take advantage of their respective strengths. These hybrid intelligent systems also present the ability to acquire new knowledge from different sources and so to improve their application performance. This thesis presents our research in the field of hybrid neuro-symbolic systems, and in particular the study of machine learning tools used for constructive knowledge acquisition. We are interested in the automatic acquisition of theoretical knowledge (rules) and empirical knowledge (examples). We present a new hybrid system we implemented: INSS - Incremental Neuro-Symbolic System. This system allows knowledge transfer from the symbolic module to the connectionist module (Artificial Neural Network - ANN), through symbolic rule compilation into an ANN. We can refine the initial ANN knowledge through neural learning using a set of examples. The incremental ANN learning method used, the Cascade-Correlation algorithm, allows us to change or to add new knowledge to the network. Then, the system can also extract modified (or new) symbolic rules from the ANN and validate them. INSS is a hybrid machine learning system that implements a constructive knowledge acquisition method. We conclude by showing the results we obtained with this system in different application domains: ANN artificial problems(The Monk's Problems), computer aided medical diagnosis (Toxic Comas), a cognitive modelling task (The Balance Scale Problem) and autonomous robot control. The results we obtained show the improved performance of INSS and its advantages over others hybrid neuro-symbolic systems
Dariouchy, Abdelilah. "Utilisation des réseaux de neurones artificiels en diffusion acoustique et en agriculture sous serres." Le Havre, 2008. http://www.theses.fr/2008LEHA0002.
Full textThis study is devoted to the models development able to predict the reduced cut-off frequencies and the forms functions for submerged tubes in water and to predict the acoustic spectrum retrodiffused by two welded plates on the one hand, and on the other hand, to predict the time series of the internal temperature and the internal moisture of the tomato greenhouse in a semi-arid area. To validate our results, the representation time-frequency of Wigner-Ville is used to compare the form function calculated by the traditional analytical method and that predicted by ANN. The control of the ANN models allows us now to consider other applications according to the requests
Dollfus, Denis. "Reconnaissance de formes naturelles par des réseaux de neurones artificiels : application au nannoplancton calcaire." Aix-Marseille 3, 1997. http://www.theses.fr/1997AIX30099.
Full textCarboni, Lucrezia. "Graphes pour l’exploration des réseaux de neurones artificiels et de la connectivité cérébrale humaine." Electronic Thesis or Diss., Université Grenoble Alpes, 2023. http://www.theses.fr/2023GRALM060.
Full textThe main objective of this thesis is to explore brain and artificial neural network connectivity from agraph-based perspective. While structural and functional connectivity analysis has been extensivelystudied in the context of the human brain, there is a lack of a similar analysis framework in artificialsystems.To address this gap, this research focuses on two main axes.In the first axis, the main objective is to determine a healthy signature characterization of the humanbrain resting state functional connectivity. To achieve this objective, a novel framework is proposed,integrating traditional graph statistics and network reduction tools, to determine healthy connectivitypatterns. Hence, we build a graph pair-wise comparison and a classifier to identify pathological statesand rank associated perturbed brain regions. Additionally, the generalization and robustness of theproposed framework were investigated across multiple datasets and variations in data quality.The second research axis explores the benefits of brain-inspired connectivity exploration of artificialneural networks (ANNs) in the future perspective of more robust artificial systems development. Amajor robustness issue in ANN models is represented by catastrophic forgetting when the networkdramatically forgets previously learned tasks when adapting to new ones. Our work demonstrates thatgraph modeling offers a simple and elegant framework for investigating ANNs, comparing differentlearning strategies, and detecting deleterious behaviors such as catastrophic forgetting.Moreover, we explore the potential of leveraging graph-based insights to effectively mitigatecatastrophic forgetting, laying a foundation for future research and explorations in this area
Chouakri, Nassim. "Identification des paramètres d'un modèle de type Monod a l'aide de réseaux de neurones artificiels." Vandoeuvre-les-Nancy, INPL, 1993. http://www.theses.fr/1993INPL101N.
Full textViriyametanont, Kriengkai. "Reconnaissance physique et géométrique d’éléments en béton armé par radar et réseaux de neurones artificiels." Toulouse, INSA, 2008. http://eprint.insa-toulouse.fr/archive/00000202/.
Full textPhysical and geometrical survey of reinforced-concrete elements is difficult due to many problems associated to limited knowledge and comprehension of the various NDT techniques. The radar technology is increasingly implemented on reinforced concrete structures for the geometrical survey (detection of steel reinforcement, 3D positioning of buried objects). Radar measurements are usually restricted to the rough assessment of the concrete cover. However, the electromagnetic response of the surveyed element contains more information (moisture content and porosity of concrete, diameter of the reinforcement). The purpose of this work is focused on the application of radar to the physical and geometrical characterization of reinforced concrete elements according to a statistical approach based on the concept of artificial neural networks (ANN). ANN belong to the class of statistical modelling methods. ANN are supposed to reproduce the learning and recognition capacities of the human brain and are sometime described as a concept of artificial intelligence. A laboratory statistical database was established and used to train ANN models able to recognize radar signatures and to extract information such as : moisture content of concrete ; concrete porosity ; reinforcement depth and diameter. The developed models were at last tested on real concrete structures
Paugam-Moisy, Hélène. "Optimisation des réseaux de neurones artificiels : analyse et mises en œuvre sur ordinateurs massivement parallèles." Lyon 1, 1992. http://www.theses.fr/1992LYO10018.
Full textDjouani, Karim. "Contribution à la commande dynamique des navires. Commande optimale non-linéaire et réseaux de neurones artificiels." Paris 12, 1994. http://www.theses.fr/1994PA120043.
Full textFessant, Françoise. "Prediction des series temporelles par reseaux de neurones artificiels : application aux series temporelles ionospheriques." Rennes 1, 1995. http://www.theses.fr/1995REN10103.
Full textChlyah, Badr. "La prédiction statique et dynamique des besoins énergétiques d'un bâtiment en utilisant les réseaux de neurones artificiels." Mémoire, École de technologie supérieure, 2008. http://espace.etsmtl.ca/133/1/CHLYAH_Badr.pdf.
Full textAttik, Mohammed. "Traitement intelligent de données par réseaux de neurones artificiels : application à la valorisation des systèmes d'information géographiques." Nancy 1, 2006. http://docnum.univ-lorraine.fr/public/SCD_T_2006_0211_ATTIK.pdf.
Full textThe purpose of this thesis is: (i) establish predictive maps on ore deposits, (ii) select a subset of descriptive features that effectively contribute to the building of these predictive maps, (iii) identify and interpret dependencies between the selected features, (iv) place the features into a hierarchy that indicates their importance. A real-life data of Geographical Information System provided by the French geological survey (BRGM) have been used in the accomplished experiments. In order to establish predictive maps, we have used neural network ensemble which is a very successful technique where outputs of a set of separately trained neural network are combined to form one unified prediction. This technique generates several predictive maps following the used aggregation function. In addition, to understand domain data, we have focused on selecting a subset of relevant features. We have proposed an improvement of existing features selection techniques that are based on the principle of Optimal Brain Damage (OBD) as well as those of Optimal Brain Surgeon (OBS) and Mutual Information (MI). We have also proposed novel solutions to understand data that combine ensemble feature selection approach with either concept lattices or statistic techniques. The latter solutions help discovering all relevant features and organizing them into hierarchy according to their concurrencies in the selected subsets of features. Moreover, we have addressed the problem of clustering-based analysis of data provided with multiple labels. The proposed approach uses new measures that extend the scope of the recall and precision measures in information retrieval (IR) to the processing of multi-label data. Experiments have been carried out on data pertaining to geographical information system and documentary system have highlighted the accuracy of our approach for knowledge extraction
Bordieu, Christophe. "Utilisation des réseaux de neurones artificiels pour la détection et la reconnaissance des gaz en temps réel." Bordeaux 1, 1998. http://www.theses.fr/1998BOR10562.
Full textBelley, Katia. "Détection de sites sécuritaires par réseaux de neurones pour un atterrissage autonome sur corps planétaire." Mémoire, Université de Sherbrooke, 2008. http://savoirs.usherbrooke.ca/handle/11143/1447.
Full textMoposita, Tatiana. "Artificial Neural Network (ANN) design using Compute-in-Memory." Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS682.
Full textNowadays, the era of ”More than Moore” has arisen as a significant influence in light of the limitations anticipated by Moore’s law. The computing systems are exploring alternative technologies to sustain and enhance performance improvements. The idea of alternative innovative technologies has emerged in solving challenges of electronic systems inspired by biological neural networks, commonly referred to as Artificial Neural Network (ANN). The use of emerging non-volatile memory (eNVM) technologies are being explored as promising alternatives. These technologies offer several advantages over traditional CMOS technology, such as increased speed, higher densities, and lower power consumption. As a result, Compute-in-memory employs eNVMs to perform computation within the memory itself, hence increasing memory capacity and processing speed. The objective of this thesis focuses on the research of Artificial Neural Networks design using Compute in Memory, by employing efficient hardware solutions for ANNs at both circuit- and architecture-level. Recent research work in this context has proposed very efficient circuit designs to optimize the enormous computational needs required by data processing by ANNs. Therefore, to explore the capabilities of an ANN at the output node, the design of activation functions were proposed. The selection of an activation function is significant as it determines the power and capabilities of the neural network, and the accuracy of predictions is primarily dependent on this choice. To assess the effectiveness of an activation function designed for analog implementation, the sigmoid and the softmax activation function are proposed. Besides, this thesis explores the integration of emerging memory devices like Spin-Transfer-Torque Magnetic Random Access Memory (STT-MRAM) with CMOS technology. This combined approach aims to leverage the intrinsic capability of in-memory computing offered by these devices. STT-MRAMs based on state-of-the-art perpendicular magnetic tunneling junction (MTJ) and FinFETs has been considered for this study. Single-barrier magnetic tunnel junction (SMTJ) and double-barrier magnetic tunnel junction (DMTJ) devices are considered to evaluate the impact of STT-MRAM cell based on DMTJ against the conventional SMTJ counterpart on the performance of a two-layer multilayer perceptron (MLP) neural network. The assessment was carried out through a customized simulation framework from device and bitcell levels to memory architecture and algorithm levels. Moreover, to improve the energy-efficiency of a Logic-in-Memory (LIM) architecture based on STT-MTJ devices, a new architecture (SIMPLY+) from the Smart Material Implication (SIMPLY) logic and perpendicular MTJ based STT-MRAM technologies was developed. The SIMPLY+ scheme is a promising solution for the development of energy-efficient and reliable in-memory computing architectures. All circuit solutions were evaluated using commercial circuit simulators (e.g. Cadence Virtuoso). Circuit design activity involving emerging memory devices also required the use and calibration of Verilog-A based compact models to integrate the behavior of such devices into the circuit design tool. The solutions presented in this thesis involve techniques that offer significant advancements for future applications. From a design perspective, the integration of logic modules with STT-MRAM memory is highly feasible due to the seamless compatibility between STT-MRAMs and CMOS circuits. This approach not only proves advantageous for standard CMOS technology but also leverages the potential of emerging technologies
Tay, Yong Haur. "Reconnaissance de l'écriture manuscrite hors-ligne par réseau de neurones artificiels et modèles de Markov cachés." Nantes, 2002. http://www.theses.fr/2002NANT2106.
Full textBoulnois, Philippe. "Contribution à l'étude de différentes architectures de réseaux de neurones artificiels réalisant une transcription graphèmes-phonèmes pour le français." Compiègne, 1994. http://www.theses.fr/1994COMPD675.
Full textLanglet-Caüet, Fabien. "Étude et implantation de la prédistorsion d'amplificateurs à bord de satellites à base de réseaux de neurones." Toulouse, INPT, 2004. http://www.theses.fr/2004INPT022H.
Full textVintenat, Lionel. "Apport des réseaux de neurones artificiels à la tolérance aux fautes en environnement spatial des fonctions de bord." Toulouse, ENSAE, 1999. http://www.theses.fr/1999ESAE0020.
Full textIbnkahla, Mohamed. "Réseaux de neurones : nouvelles structures et applications aux communications numériques par satellite." Toulouse, INPT, 1996. http://www.theses.fr/1996INPT123H.
Full textSauget, Marc. "Parallélisation de problèmes d'apprentissage par des réseaux neuronaux artificiels. Application en radiothérapie externe." Phd thesis, Université de Franche-Comté, 2007. http://tel.archives-ouvertes.fr/tel-00260013.
Full textLa première partie a donc porté sur la mise au point de l'algorithme d'apprentissage des réseaux de neurones. Un des problèmes majeurs lors de la préparation de l'apprentissage concerne la détermination de la structure optimale permettant l'apprentissage le plus efficace possible. Pour construire un réseau proche de l'optimal, nous nous sommes basés sur une construction incrémentale du réseau. Ensuite, pour permettre une prise en charge des nombreux paramètres liés à notre domaine d'application, et du volume des données nécessaires à un apprentissage rigoureux, nous nous sommes attachés à paralléliser notre algorithme. Nous avons obtenu, à la fin de cette première phase de nos travaux, un algorithme d'apprentissage incrémental et parallèle pouvant être déployé de manière efficace sur une grappe de calcul non-fiable. Ce déploiement est possible grâce à l'ajout d'un mécanisme de tolérance aux pannes. La deuxième partie, quant à elle, a consisté en la mise au point d'algorithmes permettant l'évaluation des doses déposées lors d'une irradiation. Ces algorithmes utilisent les réseaux de neurones comme référence pour la valeur des doses ainsi que le principe de continuité de la dose en tout point du milieu. Ils ont été construits à partir d'une fine observation du comportement de la courbe de dépôt de dose à chaque changement de milieu.
En aboutissement, nous présentons des expérimentations montrant les performances de notre algorithme d'apprentissage, ainsi que de nos algorithmes d'évaluation de doses dans différentes configurations.
Gevrey, Muriel. "Modélisation de la diversité et de la structure des communautés aquatiques par la technique des réseaux de neurones artificiels." Paris 6, 2003. http://www.theses.fr/2003PA066137.
Full textBouchired, Steven. "Égalisation de canaux non-linéaires variant dans le temps à l'aide des réseaux de neurones : application au canal satellite mobile." Toulouse, INPT, 1999. http://www.theses.fr/1999INPT044H.
Full textVoyant, Cyril. "Prédiction de séries temporelles de rayonnement solaire global et de production d'énergie photovoltaïque à partir de réseaux de neurones artificiels." Phd thesis, Université Pascal Paoli, 2011. http://tel.archives-ouvertes.fr/tel-00635298.
Full textHattab, Nour. "Ecodynamique des éléments traces et caractérisation de l'exposition des sols contaminés : expérimentation et modélisation par les réseaux de neurones artificiels." Phd thesis, Université d'Orléans, 2013. http://tel.archives-ouvertes.fr/tel-01069449.
Full textHattab, Nour. "Ecodynamique des éléments traces et caractérisation de l’exposition des sols contaminés : expérimentation et modélisation par les réseaux de neurones artificiels." Thesis, Orléans, 2013. http://www.theses.fr/2013ORLE2020/document.
Full textSoils contaminated with potentially toxic trace elements (PTTE) often have serious consequences for terrestrial ecosystems. Several phytoremediaction have been developped to reclaim contaminated soils; however the efficiency and capacity of these techniques to reduce excessive concentrations of trace elements or their (phyto) availability in contaminated soils have to be assessed. The present work is focused on studying the effectiveness of two phyoremediation options such as phytostabilisation and phytoextraction assisted by organic and inorganic amendments to remediatethe high concentrations of PTTE in contaminated natural soils and technosoils. Total PTTE concentrations were determined in soil pore water (SPW) sampled by Rhizon soil moisture samplers. The soil exposure intensity was assessed by DGT (diffusive gradient in thin films) probes. The PTTE phytoavailability was characterized by growing dwarf beans on potted soils and analyzing their foliar PTTE concentrations. Then a model of artificial neural network was applied to understand the factors most relevant for the variability on the phytoavailability of trace elements. Both options were found to be able to reduce the concentrations or phytoavailability of PTTE in the presence of amendments. The artificial neural network has been very effective to predict missing results and to determine the control parameters of the variability of the PTTE phytoavailoability from the soil parameters
Schoonjans, Nathan. "Établissement d'une boucle de communication bidirectionnelle entre des neurones vivants et des neurones artificiels analogiques pour la conception de neurobiohybrides de nouvelle génération." Electronic Thesis or Diss., Université de Lille (2022-....), 2023. https://pepite-depot.univ-lille.fr/ToutIDP/EDENGSYS/2023/2023ULILN056.pdf.
Full textNeurobiohybrids are systems composed of an artificial element, a living component and their interface. These powerful tools enable the functional connection of electronic elements and neuronal structures both in vitro and in vivo. Many neurobiohybrid systems, more commonly known as neuroprostheses, are used in medicine to improve the quality of life of patients with disabilities (deafness, visual impairment, paralysis) by enabling them to recover, at least partly, lost physiological functions. Current neuroprostheses are unidirectional (they stimulate OR record the activity of targeted neurons) and are particularly energy-intensive. Integrating a feedback loop into these systems so that they could communicate bidirectionally in real time with nerve tissues would improve their efficiency and effectiveness, while broadening the range of their therapeutic potential. The main difficulty to overcome for enabling such a loop is to find an autonomous and sufficiently miniaturized signal processing system. In 2017, the Circuits Systèmes Applications des Micro-ondes (CSAM) group at Lille's Institute of Electronics, Microelectronics and Nanotechnologies (IEMN) published an ultra-efficient artificial neuron in terms of energy consumption that could meet these needs. This neuron generates biomimetic action potentials of similar shape, amplitude and frequency compared to living neurons, and is entirely analog. In a previous PhD work, it was shown that such biomimetic action potentials can trigger electric activity in living neurons. Following this demonstration, the present work aims to establish the proof-of-concept of the complete bidirectional communication loop between living neurons and these artificial neurons. To reach this goal, three main objectives were set: 1- Optimize the design and technology of a neurobiohybrid interface; 2- Select living cells for in vitro use and characterize them both morphologically and functionally; 3- Establish a first bidirectional communication loop between these living neurons and artificial neurons through the neurobiohybrid interface. This manuscript presents the manufacturing and optimization steps of the interface, whose surface has been enhanced to optimize recording conditions in an electrolytic environment, notably by adding a passivation layer to isolate the access lines and by developing methods to optimize cell position on the electrodes. The electrically active cells chosen for this demonstration (murine pituitary endocrine GH4C1 cells, an established cell line, and human glutamatergic neurons derived from induced pluripotent stem cells) were characterized by patch-clamp, fluorescence imaging and calcium imaging. The first recordings of the electrical activity of GH4C1 cells grown in a neurobiohybrid interface were carried out on an electronic recording bench designed and optimized in-house for detecting very low amplitude signals. This work also led to the development of an electrical model implemented in LTSPICE software, integrating electrical signals emitted by GH4C1 cells as recorded through the neurobiohybrid interface. This enabled the establishment of a bidirectional communication loop between living and artificial neurons. To conclude, this work opens the way to a new generation of bidirectional neuroprostheses
Janod, Killian. "La représentation des documents par réseaux de neurones pour la compréhension de documents parlés." Thesis, Avignon, 2017. http://www.theses.fr/2017AVIG0222/document.
Full textApplication of spoken language understanding aim to extract relevant items of meaning from spoken signal. There is two distinct types of spoken language understanding : understanding of human/human dialogue and understanding in human/machine dialogue. Given a type of conversation, the structure of dialogues and the goal of the understanding process varies. However, in both cases, most of the time, automatic systems have a step of speech recognition to generate the textual transcript of the spoken signal. Speech recognition systems in adverse conditions, even the most advanced one, produce erroneous or partly erroneous transcript of speech. Those errors can be explained by the presence of information of various natures and functions such as speaker and ambience specificities. They can have an important adverse impact on the performance of the understanding process. The first part of the contribution in this thesis shows that using deep autoencoders produce a more abstract latent representation of the transcript. This latent representation allow spoken language understanding system to be more robust to automatic transcription mistakes. In the other part, we propose two different approaches to generate more robust representation by combining multiple views of a given dialogue in order to improve the results of the spoken language understanding system. The first approach combine multiple thematic spaces to produce a better representation. The second one introduce new autoencoders architectures that use supervision in the denoising autoencoders. These contributions show that these architectures reduce the difference in performance between a spoken language understanding using automatic transcript and one using manual transcript
Henniquau, Dimitri. "Conception d’une interface fonctionnelle permettant la communication de neurones artificiels et biologiques pour des applications dans le domaine des neurosciences." Thesis, Université de Lille (2018-2021), 2021. http://www.theses.fr/2021LILUN032.
Full textNeuromorphic engineering is an exciting emerging new field, which combines skills in electronics, mathematics, computer sciences and biomorphic engineering with the aim of developing artificial neuronal networks capable of reproducing the brain’s data processing. Thus, neuromorphic systems not only offer more effective and energy efficient solutions than current data processing technologies, but also set the bases for developing novel original therapeutic strategies in the context of pathological brain dysfunctions. The research group Circuits Systèmes Applications des Micro-ondes (CSAM) of the Institute for Electronics, Microelectronics and Nanotechnologies (IEMN) in Lille, in which this thesis work was carried out, has contributed to the generation of such neuromorphic systems by developing a toolbox constituted of artificial neurons and synapses. In order to implement neuromorphic engineering in the therapeutic arsenal for treating neurologic disorders, we need to interface living and artificial neurons to ensure real communication between these different components. In this context and using the original tools developed by the CSAM group, the main goal of this thesis work was to design and produce a functional interface allowing a bidirectional communication loop to be established between living and artificial neurons. These artificial neurons have been developed by the CSAM group using CMOS technology and are able to emit biomimetic electrical signals. Living neurons were obtained from differentiated PC-12 cells. A first step in this work consisted in modeling and simulating this interface between artificial and living neurons; a second part of the thesis was dedicated to the fabrication and characterization of neurobiohybrid interfaces, and to the growth and characterization of living neurons before studying their capacities to communicate with artificial neurons. First, a model of neuronal membrane representing a living neuron interfaced with a metallic planar electrode has been developed. We thus showed that it is possible to excite neurons using biomimetic signals produced by artificial neurons while maintaining a low excitation voltage. Low voltage excitation would improve energy efficiency of neurobiohybrid systems integrating artificial neurons and reduce the impact of harmful electrical signals on living neurons. Then, the neurobiohybrid interfacing living and artificial neurons has been designed and produced. The results obtained by experimental characterization of this interface validate the approach consisting in exciting living neurons through a metallic planar electrode. Finally, living neurons from PC-12 cells were grown and differentiated directly onto neurobiohybrids. Then, an experimental proof of the ability of biomimetic electrical signals to excite living neurons was obtained using calcium imaging. To conclude, the work presented in this manuscript clearly establishes a proof of concept for the excitation of living neurons using a biomimetic signal in our experimental conditions and thus substantiates the first part of the bidirectional communication loop between artificial neurons and living neurons
Kharroubi, Ouissem. "Prévision des crues par modèle de réseau de neurones artificiels : application au bassin versant de l’Eure." Thesis, Lille 1, 2013. http://www.theses.fr/2013LIL10034/document.
Full textThe growth of riparian populations generates an increase in vulnerability of our societies to flood. Therefore, a high social demand to prevent and predict these natural disasters must be tacking to protect the population against floods. To achieve this objective, the provision of flood forecasting tools, operational and reliable, is primordial. But the flood forecasting still an exercise far from being evident. Firstly, because the forecast requirements (precision and time anticipation) are becoming more and more higher. And secondly, because the physical flood forecasting tools is limited by the relative knowledge of floods hydro-systems. In this context, this thesis presents the work done to produce rainfall-runoff flood forecasting models based on artificial neural networks (ANN) in the Eure watershed (and two sub-basins) up to a 48 hours horizon forecasting. Firstly, an analysis of the geographical complexity of studied basins will be conducted in order to determine the different factors that influencing the hydrological Eure watershed regime. Then, a methodological process to data statistical analysis, has allowed a synthesis on the hydrological nature of the watersheds studied and brings the elements needed to the definition of the non-linear relations rainfall-runoff. This contribution has allowed the creation of a rainfall-runoff nonlinear model for flood forecasting. ANN model able to perform a reliable forecasting of flood up to a 48 hours horizon forecasting. This process has been tested on three watersheds and the test results show a reliable forecasts as well as an ability of generalization to other hydro-systems
Guiraud, David. "Système de contrôle du mouvement du membre inférieur à base de réseaux de neurones artificiels : restauration de la marche chez le paraplégique." Châtenay-Malabry, Ecole centrale de Paris, 1993. http://www.theses.fr/1993ECAP0318.
Full textEl, Haddad Josette. "Chimiométrie appliquée à la spectroscopie de plasma induit par laser (LIBS) et à la spectroscopie terahertz." Phd thesis, Université Sciences et Technologies - Bordeaux I, 2013. http://tel.archives-ouvertes.fr/tel-00959288.
Full text