• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 21
  • 3
  • Tagged with
  • 35
  • 35
  • 35
  • 17
  • 9
  • 9
  • 8
  • 8
  • 7
  • 7
  • 6
  • 5
  • 5
  • 5
  • 5
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
31

Training of Object Detection Spiking Neural Networks for Event-Based Vision

Johansson, Olof January 2021 (has links)
Event-based vision offers high dynamic range, time resolution and lower latency than conventional frame-based vision sensors. These attributes are useful in varying light condition and fast motion. However, there are no neural network models and training protocols optimized for object detection with event data, and conventional artificial neural networks for frame-based data are not directly suitable for that task. Spiking neural networks are natural candidates but further work is required to develop an efficient object detection architecture and end-to-end training protocol. For example, object detection in varying light conditions is identified as a challenging problem for the automation of construction equipment such as earth-moving machines, aiming to increase the safety of operators and make repetitive processes less tedious. This work focuses on the development and evaluation of a neural network for object detection with data from an event-based sensor. Furthermore, the strengths and weaknesses of an event-based vision solution are discussed in relation to the known challenges described in former works on automation of earth-moving machines. A solution for object detection with event data is implemented as a modified YOLOv3 network with spiking convolutional layers trained with a backpropagation algorithm adapted for spiking neural networks. The performance is evaluated on the N-Caltech101 dataset with classes for airplanes and motorbikes, resulting in a mAP of 95.8% for the combined network and 98.8% for the original YOLOv3 network with the same architecture. The solution is investigated as a proof of concept and suggestions for further work is described based on a recurrent spiking neural network.
32

Deep learning in event-based neuromorphic systems / L'apprentissage profond dans les systèmes évènementiels, bio-inspirés

Thiele, Johannes C. 22 November 2019 (has links)
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.
33

Encoding and Information Transmission in Synaptically Coupled Neuronal Populations

Knoll, Gregory 24 February 2023 (has links)
In dieser Arbeit versuche ich, den neuronalen Code, d. h. die Art und Weise, wie die Nervenzellen des Gehirns Informationen in ihrer Aktivität übertragen und verarbeiten, besser zu verstehen, indem ich die Kodierung von Stimuli in neuronalen Systemen untersuche. Zu diesem Zweck analysiere ich die Veränderungen in der Dynamik von neuronalen Standardmodellen, die im Rahmen der statistischen Physik entwickelt wurden, in Bezug auf Veränder- ungen der Parameter und der Konnektivität bei Vorhandensein bzw. Fehlen eines Reizes. Ich verwende informationstheoretische Maße, um die Fähigkeit neuronaler Populationen, empfangene Informationen durch ihren Output zu übertragen, zu quantifizieren. Die vorgestellten Ergebnisse bauen auf einer Vielzahl früherer Studien über unverbundene und rekurrente neuronale Pop- ulationen auf. Einige dieser Studien heben zwei neuronale Code-Kandidaten hervor, die unterschiedliche Profile der Informationsfilterung aufweisen: einen Integrationscode, der als Tiefpass-Informationsfilter fungiert, und einen Synchroniecode, der als Bandpassfilter fungiert. Das Ziel der vorliegenden Arbeit ist es, die Ergebnisse dieser Studien auf Netzwerke mit einem höheren Konnektivitätsgrad, wie er im Kortex beobachtet wird, auszuweiten. / In this thesis I attempt to better understand the neural code, or the way in which the nerve cells of the brain transmit and process information in their activity, through the investigation of stimulus encoding in neural systems. To this end, I analyze changes in the dynamics of standard neuronal models, de- veloped in the framework of statistical physics, to variations in parameters and connectivity in the presence versus the absence of a stimulus. In conjunction, information theoretical measures are utilized to quantify the ability of neu- ronal populations to transmit received information through their output. The presented results build upon a multitude of previous studies of both uncon- nected and recurrent neural populations. Some of these studies highlight two neural code candidates that have distinct information filtering profiles: an in- tegration code that acts as a low-pass information filter and a synchrony code that acts as a bandpass filter. In the following, synaptic connectivity is added in diverse ways in order to extend results of these studies to networks with a higher level of connectivity, as observed in the cortex.
34

Exploring the column elimination optimization in LIF-STDP networks

Sun, Mingda January 2022 (has links)
Spiking neural networks using Leaky-Integrate-and-Fire (LIF) neurons and Spike-timing-depend Plasticity (STDP) learning, are commonly used as more biological possible networks. Compare to DNNs and RNNs, the LIF-STDP networks are models which are closer to the biological cortex. LIF-STDP neurons use spikes to communicate with each other, and they learn through the correlation among these pre- and post-synaptic spikes. Simulation of such networks usually requires high-performance supercomputers which are almost all based on von Neumann architecture that separates storage and computation. In von Neumann architecture solutions, memory access is the bottleneck even for highly optimized Application-Specific Integrated Circuits (ASICs). In this thesis, we propose an optimization method that can reduce the memory access cost by avoiding a dual-access pattern. In LIF-STDP networks, the weights usually are stored in the form of a two-dimensional matrix. Pre- and post-synaptic spikes trigger row and column access correspondingly. But this dual-access pattern is very costly for DRAM. We eliminate the column access by introducing a post-synaptic buffer and an approximation function. The post-synaptic spikes are recorded in the buffer and are processed at pre-synaptic spikes together with the row updates. This column update elimination method will introduce errors due to the limited buffer size. In our error analysis, the experiments show that the probability of introducing intolerable errors can be bounded to a very small number with proper buffer size and approximation function. We also present a performance analysis of the Column Update Elimination (CUE) optimization. The error analysis of the column updates elimination method is the main contribution of our work. / Spikande neurala nätverk som använder LIF-neuroner och STDP-inlärning, används vanligtvis som ett mer biologiskt möjligt nätverk. Jämfört med DNN och RNN är LIF-STDP-nätverken modeller närmare den biologiska cortex. LIFSTDP-neuroner använder spikar för att kommunicera med varandra, och de lär sig genom korrelationen mellan dessa pre- och postsynaptiska spikar. Simulering av sådana nätverk kräver vanligtvis högpresterande superdatorer som nästan alla är baserade på von Neumann-arkitektur som separerar lagring och beräkning. I von Neumanns arkitekturlösningar är minnesåtkomst flaskhalsen även för högt optimerade Application-Specific Integrated Circuits (ASIC). I denna avhandling föreslår vi en optimeringsmetod som kan minska kostnaden för minnesåtkomst genom att undvika ett dubbelåtkomstmönster. I LIF-STDPnätverk lagras vikterna vanligtvis i form av en tvådimensionell matris. Preoch postsynaptiska toppar kommer att utlösa rad- och kolumnåtkomst på motsvarande sätt. Men detta mönster med dubbel åtkomst är mycket dyrt i DRAM. Vi eliminerar kolumnåtkomsten genom att införa en postsynaptisk buffert och en approximationsfunktion. De postsynaptiska topparna registreras i bufferten och bearbetas vid presynaptiska toppar tillsammans med raduppdateringarna. Denna metod för eliminering av kolumnuppdatering kommer att introducera fel på grund av den begränsade buffertstorleken. I vår felanalys visar experimenten att sannolikheten för att införa oacceptabla fel kan begränsas till ett mycket litet antal med korrekt buffertstorlek och approximationsfunktion. Vi presenterar också en prestandaanalys av CUE-optimeringen. Felanalysen av elimineringsmetoden för kolumnuppdateringar är det huvudsakliga bidraget från vårt arbete
35

Development and Evaluation of a Road Marking Recognition Algorithm implemented on Neuromorphic Hardware / Utveckling och utvärdering av en algoritm för att läsa av vägbanan, som implementeras på neuromorfisk hårdvara

Bou Betran, Santiago January 2022 (has links)
Driving is one of the most common and preferred forms of transport used in our actual society. However, according to studies, it is also one of the most dangerous. One solution to increase safety on the road is applying technology to automate and prevent avoidable human errors. Nevertheless, despite the efforts to obtain reliable systems, we have yet to find a reliable and safe enough solution for solving autonomous driving. One of the reasons is that many drives are done in conditions far from the ideal, with variable lighting conditions and fast-paced, unpredictable environments. This project develops and evaluates an algorithm that takes the input of dynamic vision sensors (DVS) and runs on neuromorphic spiking neural networks (SNN) to obtain a robust road lane tracking system. We present quantitative and qualitative metrics that evaluate the performance of lane recognition in low light conditions against conventional algorithms. This project is motivated by the main advantages of neuromorphic vision sensors: recognizing a high dynamic range and allowing a high-speed image capture. Another improvement of this system is the computational speed and power efficiency that characterize neuromorphic hardware based on spiking neural networks. The results obtained show a similar accuracy of this new algorithm compared to previous implementations on conventional hardware platforms. Most importantly, it accomplishes the proposed task with lower latency and computing power requirements than previous algorithms. / Att köra bil är ett av de vanligaste och mest populära transportsätten i vårt samhälle. Enligt forskningen är det också ett av de farligaste. En lösning för att öka säkerheten på vägarna är att med teknikens hjälp automatisera bilkörningen och på så sätt förebygga misstag som beror på den mänskliga faktorn. Trots ansträngningarna för att få fram tillförlitliga system har man dock ännu inte hittat en tillräckligt tillförlitlig och säker lösning för självkörande bilar. En av orsakerna till det är att många körningar sker under förhållanden som är långt ifrån idealiska, med varierande ljusförhållanden och oförutsägbara miljöer i höga hastigheter. I det här projektet utvecklar och utvärderar vi en algoritm som tar emot indata från dynamiska synsensorer (Dynamic Vision Sensors, DVS) och kör datan på neuromorfiska pulserande neuronnät (Spiking Neural Networks, SNN) för att skapa ett robust system för att läsa av vägbanan. Vi presenterar en kvantitativ och kvalitativ utvärdering av hur väl systemet läser av körbanans linjer i svagt ljus, och jämför därefter resultaten med dem för tidigare algoritmer. Detta projekt motiveras av de viktigaste fördelarna med neuromorfiska synsensorer: brett dynamiskt omfång och hög bildtagningshastighet. En annan fördel hos detta system är den korta beräkningstiden och den energieffektivitet som kännetecknar neuromorfisk hårdvara baserad på pulserande neuronnät. De resultat som erhållits visar att den nya algoritmen har en liknande noggrannhet som tidigare algoritmer på traditionella hårdvaruplattformar. I jämförelse med den traditionella tekniken, utför algoritmen i den föreliggande studien sin uppgift med kortare latenstid och lägre krav på processorkraft. / La conducción es una de las formas de transporte más comunes y preferidas en la actualidad. Sin embargo, diferentes estudios muestran que también es una de las más peligrosas. Una solución para aumentar la seguridad en la carretera es aplicar la tecnología para automatizar y prevenir los evitables errores humanos. No obstante, a pesar de los esfuerzos por conseguir sistemas fiables, todavía no hemos encontrado una solución suficientemente fiable y segura para resolver este reto. Una de las razones es el entorno de la conducción, en situaciones que distan mucho de las ideales, con condiciones de iluminación variables y entornos rápidos e imprevisibles. Este proyecto desarrolla y evalúa un algoritmo que toma la entrada de sensores de visión dinámicos (DVS) y ejecuta su computación en redes neuronales neuromórficas (SNN) para obtener un sistema robusto de seguimiento de carriles en carretera. Presentamos métricas cuantitativas y cualitativas que evalúan el rendimiento del reconocimiento de carriles en condiciones de poca luz, frente a algoritmos convencionales. Este proyecto está motivado por la validación de las ventajas de los sensores de visión neuromórficos: el reconocimiento de un alto rango dinámico y la captura de imágenes de alta velocidad. Otra de las mejoras que se espera de este sistema es la velocidad de procesamiento y la eficiencia energética que caracterizan al hardware neuromórfico basado en redes neuronales de impulsos. Los resultados obtenidos muestran una precisión similar entre el nuevo algoritmo en comparación con implementaciones anteriores en plataformas convencionales. Y lo que es más importante, realiza la tarea propuesta con menor latencia y requisitos de potencia de cálculo.

Page generated in 0.1018 seconds