Inférence et apprentissage dans les réseaux de neurones profonds nécessitent une grande quantité de calculs qui, dans beaucoup de cas, limite leur intégration dans les environnements limités en ressources. Les réseaux de neurones évènementiels de type « spike » présentent une alternative aux réseaux de neurones artificiels classiques, et promettent une meilleure efficacité énergétique. Cependant, entraîner les réseaux spike demeure un défi important, particulièrement dans le cas où l’apprentissage doit être exécuté sur du matériel de calcul bio-inspiré, dit matériel neuromorphique. Cette thèse constitue une étude sur les algorithmes d’apprentissage et le codage de l’information dans les réseaux de neurones spike.A partir d’une règle d’apprentissage bio-inspirée, nous analysons quelles propriétés sont nécessaires dans les réseaux spike pour rendre possible un apprentissage embarqué dans un scénario d’apprentissage continu. Nous montrons qu’une règle basée sur le temps de déclenchement des neurones (type « spike-timing dependent plasticity ») est capable d’extraire des caractéristiques pertinentes pour permettre une classification d’objets simples comme ceux des bases de données MNIST et N-MNIST.Pour dépasser certaines limites de cette approche, nous élaborons un nouvel outil pour l’apprentissage dans les réseaux spike, SpikeGrad, qui représente une implémentation entièrement évènementielle de la rétro-propagation du gradient. Nous montrons comment cette approche peut être utilisée pour l’entrainement d’un réseau spike qui est capable d’inférer des relations entre valeurs numériques et des images MNIST. Nous démontrons que cet outil est capable d’entrainer un réseau convolutif profond, qui donne des taux de reconnaissance d’image compétitifs avec l’état de l’art sur les bases de données MNIST et CIFAR10. De plus, SpikeGrad permet de formaliser la réponse d’un réseau spike comme celle d’un réseau de neurones artificiels classique, permettant un entraînement plus rapide.Nos travaux introduisent ainsi plusieurs mécanismes d’apprentissage puissants pour les réseaux évènementiels, contribuant à rendre l’apprentissage des réseaux spike plus adaptés à des problèmes réels. / Inference 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.

<p>With the Moore’s Law era coming to an end, much attention has been given to novel nanoelectronic devices as a key driving force behind technological innovation. Utilizing the inherent device physics of nanoelectronic components, for sensory and computational tasks have proven to be useful in reducing the area and energy requirements of the underlying hardware fabrics. In this work we demonstrate how the intrinsic noise present in nano magnetic devices can pave the pathway for energy efficient neuromorphic hardware. Furthermore, we illustrate how the unique magnetic properties of such devices can be leveraged for accurate estimation of environmental magnetic fields. We focus on spintronic technologies in particular, due to the low current and energy requirements in contrast to traditional CMOS technologies.</p><p>Image segmentation is a crucial pre-processing stage used in many object identification tasks that involves simplifying the representation of an image so it can be conveniently analyzed in the later stages of a problem. This is achieved through partitioning a complicated image into specific groups based on color, intensity or texture of the pixels of that image. Locally Excitatory Globally Inhibitory Oscillator Network or LEGION is one such segmentation algorithm, where synchronization and desynchronization between coupled oscillators are used for segmenting an image. In this work we present an energy efficient and scalable hardware implementation of LEGION using stochastic Magnetic Tunnel Junctions that leverage the fast parallel</p><p> nature of the algorithm. We demonstrate that the proposed hardware is capable of segmenting binary and gray-scale images with multiple objects more efficiently than<br> existing hardware implementations. </p><p>It is understood that the underlying device physics of spin devices can be used for emulating the functionality of a spiking neuron. Stochastic spiking neural networks based on nanoelectronic spin devices can be a possible pathway of achieving brain-like compact and energy-efficient cognitive intelligence. Current computational models attempt to exploit the intrinsic device stochasticity of nanoelectronic synaptic or neural components to perform learning and inference. However, there has been limited analysis on the scaling effect of stochastic spin devices and its impact on the operation of such stochastic networks at the system level. Our work attempts to explore the design space and analyze the performance of nanomagnet based stochastic neuromorphic computing architectures, for magnets with different barrier heights. We illustrate how the underlying network architecture must be modified to account for the random telegraphic switching behavior displayed by magnets as they are scaled into the superparamagnetic regime.<br></p><p>Next we investigate how the magnetic properties of spin devices can be utilized for real world sensory applications. Magnetic Tunnel Junctions can efficiently translate variations in external magnetic fields into variations in electrical resistance. We couple this property of Magnetic Tunnel Junctions with Amperes law to design a non-invasive sensor to measure the current flowing through a wire. We demonstrate how undesirable effects of thermal noise and process variations can be suppressed through novel analog and digital signal conditioning techniques to obtain reliable and accurate current measurements. Our results substantiate that the proposed noninvasive current sensor surpass other state-of-the-art technologies in terms of noise and accuracy.<br></p><br>

Novel devices are being investigated as artificial synapse candidates for neuromorphic computing. These memory devices share the characteristics of an electronic element called memristor. The memristor can be regarded as a resistor with a history dependent resistance, which mimics the plasticity of a biological synapse. The present work presents various types of candidate devices that have been proposed in neuromorphic research, describes how they mimic a biological synapse and how they can be employed in artificial neuron network architectures.

No description available.

The growing availability of UAVs has created a demand for drone detection systems. Several studies have used neuromorphic cameras to detect UAVs; however, a fully neuromorphic system remains to be explored. We present a fully neuromorphic system consisting of an event camera and a spiking neural network running on neuromorphic hardware. Two spiking neural network architectures have been evaluated and compared to a non-spiking artificial neural network. The spiking networks show promise and perform on par with the non-spiking network in a few scenarios. Spiking networks were deployed on the Synsense Speck, a neuromorphic system on a chip, and demonstrated increased performance compared to simulations. The deployed network is capable of detecting drones up to a distance of 20 meters with high probability while consuming less than 7.13 milliwatts. The system can operate for over a year powered by a small power bank. In contrast, the equivalent non-spiking network running on the NVIDIA Jetson would operate for a few hours. The use of neuromorphic hardware enables sustained UAV detection in remote and challenging environments previously deemed inaccessible due to power constraints.

Due to the voltage driven switching at low voltages combined with nonvolatility of the achieved polarization state, ferroelectric materials have a unique potential for low power nonvolatile electronic devices. The competitivity of such devices is hindered by compatibility issues of well-known ferroelectrics with established semiconductor technology. The discovery of ferroelectricity in hafnium oxide changed this situation. The natural application of nonvolatile devices is as a memory cell. Nonvolatile memory devices also built the basis for other applications like in-memory or neuromorphic computing. Three different basic ferroelectric devices can be constructed: ferroelectric capacitors, ferroelectric field effect transistors and ferroelectric tunneling junctions. In this article first the material science of the ferroelectricity in hafnium oxide will be summarized with a special focus on tailoring the switching characteristics towards different applications.The current status of nonvolatile ferroelectric memories then lays the ground for looking into applications like in-memory computing. Finally, a special focus will be given to showcase how the basic building blocks of spiking neural networks, the neuron and the synapse, can be realized and how they can be combined to realize neuromorphic computing systems. A summary, comparison with other technologies like resistive switching devices and an outlook completes the paper.

<div>Event-Based cameras, also known as neuromophic cameras or dynamic vision sensors, are an imaging modality that attempt to mimic human eyes by asynchronously measuring contrast over time. If the contrast changes sufficiently then a 1-bit event is output, indicating whether the contrast has gone up or down. This stream of events is sparse, and its asynchronous nature allows the pixels to have a high dynamic range and high temporal resolution. However, these events do not encode the intensity of the scene, resulting in an inverse problem to estimate intensity images from the event stream. Hybrid event-based cameras, such as the DAVIS camera, provide a reference intensity image that can be leveraged when estimating the intensity at each pixel during an event. Normally, inverse problems are solved by formulating a forward and prior model and minimizing the associated cost, however, for this problem, the Plug and Play (P&P) algorithm is used to solve the inverse problem. In this case, P&P replaces the prior model subproblem with a denoiser, making the algorithm modular, easier to implement. We propose an idealized forward model that assumes the contrast steps measured by the DAVIS camera are uniform in size to simplify the problem. We show that the algorithm can swiftly reconstruct the scene intensity at a user-specified frame rate, depending on the chosen denoiser’s computational complexity and the selected frame rate.</div>

This work has been supported by the European FACETS-ITN project. Within the frameworkof this project, we contribute to the simulation of cortical cell types (employingexperimental electrophysiological data of these cells as references), using a specific VLSIneural circuit to simulate, at the single cell level, the models studied as references in theFACETS project. The real-time intrinsic properties of the neuromorphic circuits, whichprecisely compute neuron conductance-based models, will allow a systematic and detailedexploration of the models, while the physical and analog aspect of the simulations, as opposedthe software simulation aspect, will provide inputs for the development of the neuralhardware at the network level. The second goal of this thesis is to contribute to the designof a mixed hardware-software platform (PAX), specifically designed to simulate spikingneural networks. The tasks performed during this thesis project included: 1) the methodsused to obtain the appropriate parameter sets of the cortical neuron models that can beimplemented in our analog neuromimetic chip (the parameter extraction steps was validatedusing a bifurcation analysis that shows that the simplified HH model implementedin our silicon neuron shares the dynamics of the HH model); 2) the fully customizablefitting method, in voltage-clamp mode, to tune our neuromimetic integrated circuits usinga metaheuristic algorithm; 3) the contribution to the development of the PAX systemin terms of software tools and a VHDL driver interface for neuron configuration in theplatform. Finally, it also addresses the issue of synaptic tuning for future SNN simulation.

La recherche dans le domaine de l’informatique neuro-inspirée suscite beaucoup d'intérêt depuis quelques années. Avec des applications potentielles dans des domaines tels que le traitement de données à grande échelle, la robotique ou encore les systèmes autonomes intelligents pour ne citer qu'eux, des paradigmes de calcul bio-inspirés sont étudies pour la prochaine génération solutions informatiques (post-Moore, non-Von Neumann) ultra-basse consommation. Dans ce travail, nous discutons les rôles que les différentes technologies de mémoire résistive non-volatiles émergentes (RRAM), notamment (i) Phase Change Memory (PCM), (ii) Conductive-Bridge Memory (CBRAM) et de la mémoire basée sur une structure Metal-Oxide (OXRAM) peuvent jouer dans des dispositifs neuromorphiques dédies. Nous nous concentrons sur l'émulation des effets de plasticité synaptique comme la potentialisation à long terme (Long Term Potentiation, LTP), la dépression à long terme (Long Term Depression, LTD) et la théorie STDP (Spike-Timing Dependent Plasticity) avec des synapses RRAM. Nous avons développé à la fois de nouvelles architectures de faiblement énergivore, des méthodologies de programmation ainsi que des règles d’apprentissages simplifiées inspirées de la théorie STDP spécifiquement optimisées pour certaines technologies RRAM. Nous montrons l’implémentation de systèmes neuromorphiques a grande échelle et efficace énergétiquement selon deux approches différentes: (i) des synapses multi-niveaux déterministes et (ii) des synapses stochastiques binaires. Des prototypes d'applications telles que l’extraction de schéma visuel et auditif complexe sont également montres en utilisant des réseaux de neurones impulsionnels (Feed-forward Spiking Neural Network, SNN). Nous introduisons également une nouvelle méthodologie pour concevoir des neurones stochastiques très compacts qui exploitent les caractéristiques physiques intrinsèques des appareils CBRAM. / Research in the field of neuromorphic- and cognitive- computing has generated a lot of interest in recent years. With potential application in fields such as large-scale data driven computing, robotics, intelligent autonomous systems to name a few, bio-inspired computing paradigms are being investigated as the next generation (post-Moore, non-Von Neumann) ultra-low power computing solutions. In this work we discuss the role that different emerging non-volatile resistive memory technologies (RRAM), specifically (i) Phase Change Memory (PCM), (ii) Conductive-Bridge Memory (CBRAM) and Metal-Oxide based Memory (OXRAM) can play in dedicated neuromorphic hardware. We focus on the emulation of synaptic plasticity effects such as long-term potentiation (LTP), long term depression (LTD) and spike-timing dependent plasticity (STDP) with RRAM synapses. We developed novel low-power architectures, programming methodologies, and simplified STDP-like learning rules, optimized specifically for some RRAM technologies. We show the implementation of large-scale energy efficient neuromorphic systems with two different approaches (i) deterministic multi-level synapses and (ii) stochastic-binary synapses. Prototype applications such as complex visual- and auditory- pattern extraction are also shown using feed-forward spiking neural networks (SNN). We also introduce a novel methodology to design low-area efficient stochastic neurons that exploit intrinsic physical effects of CBRAM devices.

Nous présentons dans ce manuscrit un neurone électronique expérimental basé sur le modèle complet de Morris-Lecar sans simplifications, afin d’obtenir une cellule de base pour étudier l’association collective de neurones couplés. La conception du circuit est donnée en détail selon les différents courants ioniques du modèle. Les résultats expérimentaux sont comparés aux prédictions théoriques, conduisant à un bon accord, ce qui valide donc notre circuit. Nous présentons les différents domaines de bifurcation selon les paramètres de contrôle, la capacité membranaire et le courant d’excitation. Nous avons mis en évidence le comportement du neurone pour chaque zone de paramétrage. Un couplage de ces neurones est introduit en utilisant des simulations Pspice (Multisim) où les neurones ont été conçus pour être les mêmes qu’expérimentalement. Premièrement, nous avons simulé une chaîne fermée de 26 neurones faiblement couplés le long de laquelle les ondes se propagent avec des phases en opposition 2 à 2. Pour cette première étude, on travaille dans une zone présentant uniquement un cycle limite stable. Deuxièmement, une dizaine de neurones sont couplés, avec un choix de paramètres correspondant à une deuxième zone où il y a deux attracteurs, un cycle limite stable et un point fixe stable, tandis qu’entre eux se trouve un cycle instable. Selon le nombre de neurones qui oscillent initialement et les conditions aux bords, nos études montrent que le système évolue vers un état où seuls 1, 2 ou 3 neurones restent à l’état oscillatoire, tandis que les autres sont retournés à un état de repos, ce qui met en évidence un phénomène de clusterisation. Il est à noter que certaines parties de notre circuit de base peuvent ainsi être utilisées dans d’autres modèles de neurones, car ces parties correspondent à la production des divers courants ioniques qu’on retrouve dans d’autres modèles. / We present in this manuscript an experimental electronic neuron based on complete Morris-Lecar model without simplifications, able to become an experimental unit tool to study collective association of robust coupled neurons. The circuit design is given in details according to the ionic currents of this model. The experimental results are compared with the theoretical prediction, leading to a good agreement between them, which therefore validates the circuit. We present the different areas according to the bifurcation control parameters, the membrane capacitance and the excitation current. We have highlighted the behavior of the neuron for each parameters zone. A coupling of such neurons is introduced by using Pspice simulations (Multisim) where neurons have been designed to be the same as the experimental one. First, we simulate a chain of up to 26 neurons weakly coupled along which anti-phase wave patterns propagate with phases in opposition 2 to 2. Second, about ten neurons are coupled, and we succeed to generate clusters based on the boundary conditions of theneurons and their initial conditions. For this study, we work in the region close to the fold bifurcation of limit cycles, where two limit cycles exist, one being stable and another one unstable. Our studies show that the system evolves to a state where only 1, 2 or 3 neurons remain in the oscillatory state, while others returned to a state of rest, which highlights a phenomenon of clustering. The use of some parts of the circuit is also possible for other neuron models, namely for those based on ionic currents.