Dissertationen zum Thema „Réseaux neuronaux bio-inspirés“
Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an
Machen Sie sich mit Top-22 Dissertationen für die Forschung zum Thema "Réseaux neuronaux bio-inspirés" bekannt.
Neben jedem Werk im Literaturverzeichnis ist die Option "Zur Bibliographie hinzufügen" verfügbar. Nutzen Sie sie, wird Ihre bibliographische Angabe des gewählten Werkes nach der nötigen Zitierweise (APA, MLA, Harvard, Chicago, Vancouver usw.) automatisch gestaltet.
Sie können auch den vollen Text der wissenschaftlichen Publikation im PDF-Format herunterladen und eine Online-Annotation der Arbeit lesen, wenn die relevanten Parameter in den Metadaten verfügbar sind.
Sehen Sie die Dissertationen für verschiedene Spezialgebieten durch und erstellen Sie Ihre Bibliographie auf korrekte Weise.
Tlapale, Olivier Émilien. „Modelling the dynamics of contextual motion integration in the primate“. Nice, 2011. https://tel.archives-ouvertes.fr/tel-00850265.
Der volle Inhalt der QuelleThis thesis addresses the study of motion integration in the primate. Based on anatomical and functional knowledge of two cortical areas involved in motion perception, namely VI and MT, we explain various perceptual and oculo-motor responses found in the literature. First, we build a recurrent model of motion integration where a minimal number of cortical interactions are assumed. Proposing a simple readout mechanism, we are able to reproduce not only motion perception but also the dynamics of smooth pursuit eye movements on various line figures and gratings viewed through different apertures. Second, following perceptual studies concerning motion integration and physiological studies of receptive fields, we construct another dynamical model where motion information is gated by form cues. To this end, we postulate that the visual cortex takes advantage of luminance smoothness in order to gate motion diffusion. Such an elementary diffusion mechanism allows to solve various contextual problems where extrinsic junctions should be eliminated, without relying on complex junction detectors or depth computation. Finally, we rewrite the initial dynamical model into the neural field formalism in order to mathematically analyse its properties. We incorporate the multiplicative feedback term into the formalism, and prove the existence and uniqueness of the solution. To generalise the comparison against visual performance, we propose a new evaluation methodology based on human visual performance and design a database of image sequences taken from biology and psychophysics literature. Offering proper evaluation methodology is essential to continue progress in modelling the neural mechanisms involved in motion processing. To conclude, we investigate the performances of our neural field model by comparison against state of the art computer vision approaches and sequences. We find that, despite its original objective, this model gives results comparable to recent computer vision approaches of motion estimation
Djennas, Meriem. „Les apports des outils de l'intelligence artificielle à l'amélioration du processus de prévision des taux de change : le cas de la couronne norvégienne“. Amiens, 2013. http://www.theses.fr/2013AMIE0052.
Der volle Inhalt der QuelleThe main objective of our research covers the quantitative modeling of foreign exchange rate using an artifïcial intelligence approach, notably the genetic algorithms and neural networks, applied to the Norwegian foreign exchange market. In the context of modeling to explain the movement of exchange rates, the thesis proposes a reflection on the artifïcial intelligence means applied to the chartist-fundamentalist approach of the exchange rate. The results of optimization and simulation show that despite their complexity, the series of exchange rates can be modeled so that the estimated values of the exchange rate approach, wherever possible, the real values of foreign exchange rate. The artifïcial simulation by a neuro-genetic model gives the best result compared with a STAR model and a standard neural model. The second part of the thesis has shown that using a genetic algorithm as a means of optimization has allowed measuring the impact of explanatory variables on the movement of the Norwegian exchange rate
Mesquida, Thomas. „Méthode de calcul et implémentation d’un processeur neuromorphique appliqué à des capteurs évènementiels“. Thesis, Université Grenoble Alpes (ComUE), 2018. http://www.theses.fr/2018GREAT117/document.
Der volle Inhalt der QuelleStudying how our nervous system and sensory mechanisms work lead to the creation of event-driven sensors. These sensors follow the same principles as our eyes or ears for example. This Ph.D. focuses on the search for bio-inspired low power methods enabling processing data from this new kind of sensor. Contrary to legacy sensors, our retina and cochlea only react to the perceived activity in the sensory environment. The artificial “retina” and “cochlea” implementations we call dynamic sensors provide streams of events comparable to neural spikes. The quantity of data transmitted is closely linked to the presented activity, which decreases the redundancy in the output data. Moreover, not being forced to follow a frame-rate, the created events provide increased timing resolution. This bio-inspired support to convey data lead to the development of algorithms enabling visual tracking or speaker recognition or localization at the auditory level, and neuromorphic computing environment implementation. The work we present rely on these new ideas to create new processing solutions. More precisely, the applications and hardware developed rely on temporal coding of the data in the spike stream provided by the sensors
Louis, Thomas. „Conventionnel ou bio-inspiré ? Stratégies d'optimisation de l'efficacité énergétique des réseaux de neurones pour environnements à ressources limitées“. Electronic Thesis or Diss., Université Côte d'Azur, 2025. http://www.theses.fr/2025COAZ4001.
Der volle Inhalt der QuelleIntegrating artificial intelligence (AI) algorithms directly into satellites presents numerous challenges. These embedded systems, which are heavily limited in energy consumption and memory footprint, must also withstand interference. This systematically requires the use of system-on-chip (SoC) solutions to combine two so-called “heterogeneous” systems: a versatile microcontroller and an energy-efficient computing accelerator (such as an FPGA or ASIC). To address the challenges related to deploying such architectures, this thesis focuses on optimizing and deploying neural networks on heterogeneous embedded architectures, aiming to balance energy consumption and AI performance.In Chapter 2 of this thesis, an in-depth study of recent compression techniques for feedforward neural networks (FNN) like MLPs or CNNs was conducted. These techniques, which reduce the computational complexity and memory footprint of these models, are essential for deployment in resource-constrained environments. Spiking neural networks (SNN) were also explored. These bio-inspired networks can indeed offer greater energy efficiency compared to FNNs.In Chapter 3, we adapted and developed innovative quantization methods to reduce the number of bits used to represent the values in a spiking network. This allowed us to compare the quantization of SNNs and FNNs, to understand and assess their respective trade-offs in terms of losses and gains. Reducing the activity of an SNN (e.g., the number of spikes generated during inference) directly improves the energy efficiency of SNNs. To this end, in Chapter 4, we leveraged knowledge distillation and regularization techniques. These methods reduce the spiking activity of the network while preserving its accuracy, ensuring effective operation of SNNs on resource-limited hardware.In the final part of this thesis, we explored the hybridization of SNNs and FNNs. These hybrid networks (HNN) aim to further optimize energy efficiency while enhancing performance. We also proposed innovative multi-timestep networks, which process information with different latencies across layers within the same SNN. Experimental results show that this approach enables a reduction in overall energy consumption while maintaining performance across a range of tasks.This thesis serves as a foundation for deploying future neural network applications in space. To validate our methods, we provide a comparative analysis on various public datasets (CIFAR-10, CIFAR-100, MNIST, Google Speech Commands) as well as on a private dataset for cloud segmentation. Our approaches are evaluated based on metrics such as accuracy, energy consumption, or SNN activity. This research extends beyond aerospace applications. We have demonstrated the potential of quantized SNNs, hybrid neural networks, and multi-timestep networks for a variety of real-world scenarios where energy efficiency is critical. This work offers promising prospects for fields such as IoT devices, autonomous vehicles, and other systems requiring efficient AI deployment
Shahsavari, Mahyar. „Unconventional computing using memristive nanodevices : from digital computing to brain-like neuromorphic accelerator“. Thesis, Lille 1, 2016. http://www.theses.fr/2016LIL10203/document.
Der volle Inhalt der QuelleBy 2020, there will be 50 to 100 billion devices connected to the Internet. Two domains of hot research to address these high demands of data processing are the Internet of Things (IoT) and Big Data. The demands of these new applications are increasing faster than the development of new hardware particularly because of the slowdown of Moore's law. The main reason of the ineffectiveness of the processing speed is the memory wall or Von Neumann bottleneck which is coming from speed differences between the processor and the memory. Therefore, a new fast and power-efficient hardware architecture is needed to respond to those huge demands of data processing. In this thesis, we introduce novel high performance architectures for next generation computing using emerging nanotechnologies such as memristors. We have studied unconventional computing methods both in the digital and the analog domains. However, the main focus and contribution is in Spiking Neural Network (SNN) or neuromorphic analog computing. In the first part of this dissertation, we review the memristive devices proposed in the literature and study their applicability in a hardware crossbar digital architecture. At the end of part~I, we review the Neuromorphic and SNN architecture. The second part of the thesis contains the main contribution which is the development of a Neural Network Scalable Spiking Simulator (N2S3) suitable for the hardware implementation of neuromorphic computation, the introduction of a novel synapse box which aims at better learning in SNN platforms, a parameter exploration to improve performance of memristor-based SNN, and finally a study of the application of deep learning in SNN
Fois, Adrien. „Plasticité et codage temporel dans les réseaux impulsionnels appliqués à l'apprentissage de représentations“. Electronic Thesis or Diss., Université de Lorraine, 2022. http://www.theses.fr/2022LORR0299.
Der volle Inhalt der QuelleNeuromorphic computing is a rapidly growing field of computer science. It seeks to define models of computation inspired by the properties of the brain. Neuromorphic computing redefines the nature of the three key components of learning: 1) data, 2) computing substrate, and 3) algorithms, based on how the brain works. First, the data are represented with all-or-nothing events distributed in space and time: spikes. Second, the computational substrate erases the separation between computation and memory introduced by Von Neumann architectures by co-locating them, as in the brain. Furthermore, the computation is massively parallel and asynchronous allowing the computational units to be activated on the fly, independently. Third, the learning algorithms are adapted to the computing substrate by exploiting the information available locally, at the neuron level. This vast overhaul in the way information transfer, information representation, computation and learning are approached, allows neuromorphic processors to promise in particular an energy saving of a considerable factor of 100 to 1000 compared to CPUs. In this thesis, we explore the algorithmic side of neuromorphic computing by proposing event-driven learning rules that satisfy locality constraints and are capable of extracting representations of event-based, sparse and asynchronous data streams. Moreover, while most related studies are based on rate codes where information is exclusively represented in the number of spikes, our learning rules exploit much more efficient temporal codes, where information is contained in the spike times. We first propose an in-depth analysis of a temporal coding method using a population of neurons. We propose a decoding method and we analyze the delivered information and the code structure. Then we introduce a new event-driven and local rule capable of extracting representations from temporal codes by storing centroids in a distributed way within the synaptic weights of a neural population. We then propose to learn representations not in synaptic weights, but rather in transmission delays operating intrinsically in the temporal dimension. This led to two new event-driven and local rules. One rule adapts delays so as to store representations, the other rule adapts weights so as to filter features according to their temporal variability. The two rules operate complementarily. In a last model, these rules adapting weights and delays are augmented by a new spatio-temporal neuromodulator. This neuromodulator makes it possible for the model to reproduce the behavior of self-organizing maps with spiking neurons, thus leading to the generation of ordered maps during the learning of representations. Finally, we propose a new generic labeling and voting method designed for spiking neural networks dealing with temporal codes. This method is used so as to evaluate our last model in the context of categorization tasks
Santos, Francisco C. „Topological evolution: from biological to social networks“. Doctoral thesis, Universite Libre de Bruxelles, 2007. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/210702.
Der volle Inhalt der QuelleAbou, Rjeily Yves. „Management and sustainability of urban drainage systems within smart cities“. Thesis, Lille 1, 2016. http://www.theses.fr/2016LIL10085/document.
Der volle Inhalt der QuelleThis work presents the Real Time Control (RTC) of Urban Drainage Systems (UDS) within smart cities. RTC requires to understand the UDS operation and to perform simulations on measured, forecasted and synthetic events. Therefore, a Real Time Monitoring system (RTM) was implemented on the experimental site, and combined to a simulation model. A model auto-calibration process and hydraulic boundary conditions forecast system were developed, in order to simulate the hydrologic-hydraulic response. Aiming to protect the citizens and mitigate flooding consequences, the RTC was composed of a flooding forecast system followed by a dynamic management strategy. The proposed concept and methodologies were applied and evaluated on the Lille 1 University Campus, within the SunRise project. RTM was found very helpful in understanding the system operation and calibrating the simulation model. Genetic Algorithm followed by Pattern Search formed an effective auto-calibration procedure for the simulation model. NARX Neural Network was developed and validated for forecasting hydraulic boundary conditions. Once understanding the UDS operations, the RTC was developed. NARX Neural Network was found capable to forecast flooding events. A dynamic management for increasing a tank retention capacity, was studied based on calculating a Valve State Schedule, and results were satisfying by using Genetic Algorithm and a modified form of Artificial Bee Colony, as optimization methods. A qualitative management was also proposed and tested for verifying its potential in reducing flooding volumes
Falez, Pierre. „Improving spiking neural networks trained with spike timing dependent plasticity for image recognition“. Thesis, Lille 1, 2019. http://www.theses.fr/2019LIL1I101.
Der volle Inhalt der QuelleComputer vision is a strategic field, in consequence of its great number of potential applications which could have a high impact on society. This area has quickly improved over the last decades, especially thanks to the advances of artificial intelligence and more particularly thanks to the accession of deep learning. Nevertheless, these methods present two main drawbacks in contrast with biological brains: they are extremely energy intensive and they need large labeled training sets. Spiking neural networks are alternative models offering an answer to the energy consumption issue. One attribute of these models is that they can be implemented very efficiently on hardware, in order to build ultra low-power architectures. In return, these models impose certain limitations, such as the use of only local memory and computations. It prevents the use of traditional learning methods, for example the gradient back-propagation. STDP is a learning rule, observed in biology, which can be used in spiking neural networks. This rule reinforces the synapses in which local correlations of spike timing are detected. It also weakens the other synapses. The fact that it is local and unsupervised makes it possible to abide by the constraints of neuromorphic architectures, which means it can be implemented efficiently, but it also provides a solution to the data set labeling issue. However, spiking neural networks trained with the STDP rule are affected by lower performances in comparison to those following a deep learning process. The literature about STDP still uses simple data but the behavior of this rule has seldom been used with more complex data, such as sets made of a large variety of real-world images.The aim of this manuscript is to study the behavior of these spiking models, trained through the STDP rule, on image classification tasks. The main goal is to improve the performances of these models, while respecting as much as possible the constraints of neuromorphic architectures. The first contribution focuses on the software simulations of spiking neural networks. Hardware implementation being a long and costly process, using simulation is a good alternative in order to study more quickly the behavior of different models. Then, the contributions focus on the establishment of multi-layered spiking networks; networks made of several layers, such as those in deep learning methods, allow to process more complex data. One of the chapters revolves around the matter of frequency loss seen in several spiking neural networks. This issue prevents the stacking of multiple spiking layers. The center point then switches to a study of STDP behavior on more complex data, especially colored real-world image. Multiple measurements are used, such as the coherence of filters or the sparsity of activations, to better understand the reasons for the performance gap between STDP and the more traditional methods. Lastly, the manuscript describes the making of multi-layered networks. To this end, a new threshold adaptation mechanism is introduced, along with a multi-layer training protocol. It is proven that such networks can improve the state-of-the-art for STDP
Marcireau, Alexandre. „Vision par ordinateur évènementielle couleur : cadriciel, prototype et applications“. Thesis, Sorbonne université, 2019. http://www.theses.fr/2019SORUS248.
Der volle Inhalt der QuelleNeuromorphic engineering is a bio-inspired approach to sensors and computers design. It aims to mimic biological systems down to the transistor level, to match their unparalleled robustness and power efficiency. In this context, event-based vision sensors have been developed. Unlike conventional cameras, they feature independent pixels which asynchronously generate an output upon detecting changes in their field of view, with high temporal precision. These properties are not leveraged by conventional computer vision algorithms, thus a new paradigm has been devised. It advocates short calculations performed on each event to mimic the brain, and shows promise both for computer vision and as a model of biological vision. This thesis explores event-based computer vision to improve our understanding of visual perception and identify potential applications. We approach the issue through color, a mostly unexplored aspect of event-based sensors. We introduce a framework supporting color events, as well as two experimental devices leveraging it: a three-chip event-based camera performing absolute color measurements, and a visual psychophysics setup to study the role of precise-timing in the brain. We explore the possibility to apply the color sensor to the genetic engineering Brainbow method, and present a new mathematical model for the latter
Hirtzlin, Tifenn. „Digital Implementation of Neuromorphic systems using Emerging Memory devices“. Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPAST071.
Der volle Inhalt der QuelleWhile electronics has prospered inexorably for several decades, its leading source of progress will stop in the next coming years, due to the fundamental technological limits of transistors. Nevertheless, microelectronics is currently offering a major breakthrough: in recent years, memory technologies have undergone incredible progress, opening the way for multiple research venues in embedded systems. Additionally, a major feature for future years will be the ability to integrate different technologies on the same chip. new emerging memory devices that can be embedded in the core of the CMOS, such as Resistive Random Access Memory (RRAM) or Spin Torque Magnetic Tunnel Junction (STMRAM) based on naturally intelligent inmemory-computing architecture. Three braininspired algorithms are carefully examined: Bayesian reasoning binarized neural networks, and an approach that further exploits the intrinsic behavior of components, population coding of neurons. Each of these approaches explores different aspects of in-memory computing
La, Barbera Selina. „Development of filamentary Memristive devices for synaptic plasticity implementation“. Thesis, Lille 1, 2015. http://www.theses.fr/2015LIL10163/document.
Der volle Inhalt der QuelleReplicating the computational functionalities of the brain remains one of the biggest challenges for the future of information and communication technologies. In this context, neuromorphic engineering appears a very promising direction. In this context memristive devices have been recently proposed for the implementation of synaptic functions, offering the required features and integration potentiality in a single component. In this dissertation, we present how advanced synaptic features can be implemented in memristive nanodevices. By exploiting the physical properties of filamentary switching, we successfully implemented a non-Hebbian plasticity form corresponding to the synaptic adaptation. We demonstrate that complex filament shape, such as dendritic paths of variable density and width, can reproduce short- and long- term processes observed in biological synapses and can be conveniently controlled by achieving a flexible way to program the device memory state and the relative state volatility. Then, we show that filamentary switching can be additionally controlled to reproduce a Hebbian plasticity form that corresponds to an increase of the synaptic weight when time correlation between pre- and post-neuron firing is experienced at the synaptic connection. We interpreted our results in the framework of a phenomenological model developed for biological synapses. Finally, we exploit this model to investigate how spike-based systems can be realized for memory and computing applications. These results pave the way for future engineering of neuromorphic computing systems, where complex behaviors of memristive physics can be exploited
Ali, Elsayed Sarah. „Fault Tolerance in Hardware Spiking Neural Networks“. Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS310.
Der volle Inhalt der QuelleArtificial Intelligence (AI) and machine learning algorithms are taking up the lion's share of the technology market nowadays, and hardware AI accelerators are foreseen to play an increasing role in numerous applications, many of which are mission-critical and safety-critical. This requires assessing their reliability and developing cost-effective fault tolerance techniques; an issue that remains largely unexplored for neuromorphic chips and Spiking Neural Networks (SNNs). A tacit assumption is often made that reliability and error-resiliency in Artificial Neural Networks (ANNs) are inherently achieved thanks to the high parallelism, structural redundancy, and the resemblance to their biological counterparts. However, prior work in the literature unraveled the falsity of this assumption and exposed the vulnerability of ANNs to faults. This requires assessing their reliability and developing cost-effective fault tolerance techniques; an issue that remains largely unexplored for neuromorphic chips and Spiking Neural Networks (SNNs). In this thesis, we tackle the subject of testing and fault tolerance in hardware SNNs. We start by addressing the issue of post-manufacturing test and behavior-oriented self-test of hardware neurons. Then we move on towards a global solution for the acceleration of testing and resiliency analysis of SNNs against hardware-level faults. We also propose a neuron fault tolerance strategy for SNNs, optimized for low area and power overhead. Finally, we present a hardware case-study which would be used as a platform for demonstrating fault-injection experiments and fault-tolerance capabilities
Spyrou, Theofilos. „Functional safety and reliability of neuromorphic computing systems“. Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS118.
Der volle Inhalt der QuelleThe recent rise of Artificial Intelligence (AI) has found a wide range of applications essentially integrating it gaining more and more ground in almost every field of our lives. With this steep integration of AI, it is reasonable for concerns to arise, which need to be eliminated before the employment of AI in the field, especially in mission- and safety-critical applications like autonomous vehicles. Spiking Neural Networks (SNNs), although biologically inspired, inherit only partially the remarkable fault resilience capabilities of their biological counterparts, being vulnerable to electronic defects and faults occurring at hardware level. Hence, a methodological exploration of the dependability characteristics of AI hardware accelerators and neuromorphic platforms is of utmost importance. This thesis tackles the subjects of testing and fault tolerance in SNNs and their neuromorphic implementations on hardware
Boisard, Olivier. „Optimization and implementation of bio-inspired feature extraction frameworks for visual object recognition“. Thesis, Dijon, 2016. http://www.theses.fr/2016DIJOS016/document.
Der volle Inhalt der QuelleIndustry has growing needs for so-called “intelligent systems”, capable of not only ac-quire data, but also to analyse it and to make decisions accordingly. Such systems areparticularly useful for video-surveillance, in which case alarms must be raised in case ofan intrusion. For cost saving and power consumption reasons, it is better to perform thatprocess as close to the sensor as possible. To address that issue, a promising approach isto use bio-inspired frameworks, which consist in applying computational biology modelsto industrial applications. The work carried out during that thesis consisted in select-ing bio-inspired feature extraction frameworks, and to optimize them with the aim toimplement them on a dedicated hardware platform, for computer vision applications.First, we propose a generic algorithm, which may be used in several use case scenarios,having an acceptable complexity and a low memory print. Then, we proposed opti-mizations for a more global framework, based on precision degradation in computations,hence easing up its implementation on embedded systems. Results suggest that whilethe framework we developed may not be as accurate as the state of the art, it is moregeneric. Furthermore, the optimizations we proposed for the more complex frameworkare fully compatible with other optimizations from the literature, and provide encourag-ing perspective for future developments. Finally, both contributions have a scope thatgoes beyond the sole frameworks that we studied, and may be used in other, more widelyused frameworks as well
Thiele, Johannes C. „Deep learning in event-based neuromorphic systems“. Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLS403/document.
Der volle Inhalt der QuelleInference and training in deep neural networks require large amounts of computation, which in many cases prevents the integration of deep networks in resource constrained environments. Event-based spiking neural networks represent an alternative to standard artificial neural networks that holds the promise of being capable of more energy efficient processing. However, training spiking neural networks to achieve high inference performance is still challenging, in particular when learning is also required to be compatible with neuromorphic constraints. This thesis studies training algorithms and information encoding in such deep networks of spiking neurons. Starting from a biologically inspired learning rule, we analyze which properties of learning rules are necessary in deep spiking neural networks to enable embedded learning in a continuous learning scenario. We show that a time scale invariant learning rule based on spike-timing dependent plasticity is able to perform hierarchical feature extraction and classification of simple objects of the MNIST and N-MNIST dataset. To overcome certain limitations of this approach we design a novel framework for spike-based learning, SpikeGrad, which represents a fully event-based implementation of the gradient backpropagation algorithm. We show how this algorithm can be used to train a spiking network that performs inference of relations between numbers and MNIST images. Additionally, we demonstrate that the framework is able to train large-scale convolutional spiking networks to competitive recognition rates on the MNIST and CIFAR10 datasets. In addition to being an effective and precise learning mechanism, SpikeGrad allows the description of the response of the spiking neural network in terms of a standard artificial neural network, which allows a faster simulation of spiking neural network training. Our work therefore introduces several powerful training concepts for on-chip learning in neuromorphic devices, that could help to scale spiking neural networks to real-world problems
Alecu, Lucian. „Une approche neuro-dynamique de conception des processus d'auto-organisation“. Electronic Thesis or Diss., Nancy 1, 2011. http://www.theses.fr/2011NAN10031.
Der volle Inhalt der QuelleIn this work we propose a cortically inspired neural architecture capable of developping an emergent process of self-organization. In order to implement this neural architecture in a distributed manner, we use the dynamic neural fields paradigm, a generic mathematical formalism aimed at modeling the competition between the neural activities at a mesoscopic level of the cortical structure. In order to examine in detail the dynamic properties of classical models, we design a formal criterion and an evaluation instrument, capable of analysing and quantifying the dynamic behavior of the any neural field, in specific contexts of stimulation. While this instrument highlights the practical advantages of the usage of such models, it also reveals the inability of these models to help implementing the self-organization process (implemented by the described architecture) with satisfactory results. These results lead us to suggest an alternative to the classical neural field models, based on a back-inhibition model which implements a local process of neural activity regulation. Thanks to this mechanism, the new neural field model is capable of achieving successful results in the implementation of the self-organization process described by our cortically inspired neural architecture. Moreover, a detailed analysis confirms that this new neural field maintains the features of the classical field models. The results described in this thesis open the perspectives for developping neuro-computational architectures for the design of software solutions or biologically-inspired robot applications
Massé, Pierre-Yves. „Autour De L'Usage des gradients en apprentissage statistique“. Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLS568/document.
Der volle Inhalt der QuelleWe prove a local convergence theorem for the classical dynamical system optimization algorithm called RTRL, in a nonlinear setting. The rtrl works on line, but maintains a huge amount of information, which makes it unfit to train even moderately big learning models. The NBT algorithm turns it by replacing these informations by a non-biased, low dimension, random approximation. We also prove the convergence with arbitrarily close to one probability, of this algorithm to the local optimum reached by the RTRL algorithm. We also formalize the LLR algorithm and conduct experiments on it, on synthetic data. This algorithm updates in an adaptive fashion the step size of a gradient descent, by conducting a gradient descent on this very step size. It therefore partially solves the issue of the numerical choice of a step size in a gradient descent. This choice influences strongly the descent and must otherwise be hand-picked by the user, following a potentially long research
Luhandjula, Thierry. „Algorithme de reconnaissance visuelle d’intentions : application au pilotage automatique d’un fauteuil roulant“. Thesis, Paris Est, 2012. http://www.theses.fr/2012PEST1092/document.
Der volle Inhalt der QuelleIn this thesis, a methodological and algorithmic approach is proposed, for visual intention recognition based on the rotation and the vertical motion of the head and the hand. The context for which this solution is intended is that of people with disabilities whose mobility is made possible by a wheelchair. The proposed system is an interesting alternative to classical interfaces such as joysticks and pneumatic switches. The video sequence comprising 10 frames is processed using different methods leading to the construction of what is referred to in this thesis as an “intention curve”. A decision rule is proposed to subsequently classify each intention curve. For recognition based on head motions, a symmetry-based approach is proposed to estimate the direction intent indicated by a rotation and a Principal Component Analysis (PCA) is used to classify speed variation intents of the wheelchair indicated by a vertical motion. For recognition of the desired direction based on the rotation of the hand, an approach utilizing both a vertical symmetry-based approach and a machine learning algorithm (a neural network, a support vector machine or k-means clustering) results in a set of two intention curves subsequently used to detect the direction intent. Another approach based on the template matching of the finger region is also proposed. For recognition of the desired speed variation based on the vertical motion of the hand, two approaches are proposed. The first is also based on the template matching of the finger region, and the second is based on a mask in the shape of an ellipse used to estimate the vertical position of the hand. The results obtained display good performance in terms of classification both for single pose in each frame and for intention curves. The proposed visual intention recognition approach yields in the majority of cases a better recognition rate than most of the methods proposed in the literature. Moreover, this study shows that the head and the hand in rotation and in vertical motion are viable intent indicators
Alecu, Lucian. „Une approche neuro-dynamique de conception des processus d'auto-organisation“. Phd thesis, Université Henri Poincaré - Nancy I, 2011. http://tel.archives-ouvertes.fr/tel-00606926.
Der volle Inhalt der QuellePeng, Zhaoxia. „Contribution à la Commande d’un Groupe de Robots Mobiles Non-holonomes à Roues“. Thesis, Ecole centrale de Lille, 2013. http://www.theses.fr/2013ECLI0006.
Der volle Inhalt der QuelleThis work is based on the multi-agent system / multi-vehicles. This thesis especially focuses on formation control of multiple nonholonomic mobile robots. The objective is to design suitable controllers for each robot according to different control tasks and different constraint conditions, such that a group of mobile robots can form and maintain a desired geomantic pattern and follow a desired trajectory. The leader-follower formation control for multiple nonholonomic mobile robots is investigated under the backstepping technology, and we incorporate a bioinspired neurodynamics scheme in the robot controllers, which can solve the impractical velocity jumps problem. The distributed formation control problem using consensus-based approach is also investigated. Distributed kinematic controllers are developed, which guarantee that the multi-robots can at least exponentially converge to the desired geometric pattern under the assumption of "perfect velocity tracking". However, in practice, "perfect velocity tracking" doesn’t hold and the dynamics of robots should not be ignored. Next, in consideration of the dynamics of robot with unknown parameters, adaptive torque controllers are developed such that the multi-robots can asymptotically converge to the desired geometric pattern under the proposed distributed kinematic controllers. Furthermore, When the partial knowledge of dynamics is available, an asymptotically stable torque controller has been proposed by using robust adaptive control techniques. When the dynamics of robot is unknown, the neural network controllers with the robust adaptive term are proposed to guarantee robust velocity tracking
Bichler, Olivier. „Contribution à la conception d'architecture de calcul auto-adaptative intégrant des nanocomposants neuromorphiques et applications potentielles“. Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00781811.
Der volle Inhalt der Quelle