Dissertations / Theses on the topic 'Neuro inspired'

Les Big Data mettent en évidence tous les défauts du paradigme de l'informatique classique. Au contraire, le Neuro-Inspiré traite les Big Data comme ressources pour progresser. Dans cette thèse, nous adoptons les principes de Hierarchical Temporal Memory (HTM) comme références neuroscientifiques et nous élaborons sur la façon dont le Bayesian Machine Learning (BML) mène les approches dans le Neuro-Inspiré à s’unifier et à atteindre nos objectives: (i) la simplification et l'amélioration des algorithmes de BML et (ii) l'approche au Neuro-Inspiré avec une prospective Ultra-Low-Power. Donc, nous nous efforçons d'apporter le traitement intelligent proche aux sources de données et de populariser le BML sur l'électronique strictement limitées tels que les appareils portables, mettable et implantables. Cependant, les algorithmes de BML ont besoin d’être optimisés. En fait, leur mise en œuvre en HW est ni efficaces, ni réalisables en raison de la mémoire, la puissance de calcul requises. Nous proposons un algorithme moins complexe, en ligne, distribué et non paramétrique et montrons de meilleurs résultats par rapport aux solutions de l’état de l’art. En fait, nous gagnons deux ordres de grandeur de réduction en complexité au niveau algorithmique et un autre ordre de grandeur grâce à des techniques traditionnelles d'optimisation HW. En particulier, nous concevons une preuve de concept sur une plateforme FPGA pour l'analyse en temps réel d’un flux de données. Enfin, nous démontrons d’être en mesure de résumer les ultimes découvertes du domaine du BML sur un algorithme généralement valide qui peut être mis en œuvre en HW et optimisé pour des applications avec des ressources limitées
Big Data highlights all the flaws of the conventional computing paradigm. Neuro-Inspired computing and other data-centric paradigms rather address Big Data to as resources to progress. In this dissertation, we adopt Hierarchical Temporal Memory (HTM) principles and theory as neuroscientific references and we elaborate on how Bayesian Machine Learning (BML) leads apparently totally different Neuro-Inspired approaches to unify and meet our main objectives: (i) simplifying and enhancing BML algorithms and (ii) approaching Neuro-Inspired computing with an Ultra-Low-Power prospective. In this way, we aim to bring intelligence close to data sources and to popularize BML over strictly constrained electronics such as portable, wearable and implantable devices. Nevertheless, BML algorithms demand for optimizations. In fact, their naïve HW implementation results neither effective nor feasible because of the required memory, computing power and overall complexity. We propose a less complex on-line, distributed nonparametric algorithm and show better results with respect to the state-of-the-art solutions. In fact, we gain two orders of magnitude in complexity reduction with only algorithm level considerations and manipulations. A further order of magnitude in complexity reduction results through traditional HW optimization techniques. In particular, we conceive a proof-of-concept on a FPGA platform for real-time stream analytics. Finally, we demonstrate we are able to summarize the ultimate findings in Machine Learning into a generally valid algorithm that can be implemented in HW and optimized for strictly constrained applications

One method in achieving artificial intelligence is by emulating biological concepts onto an electronic device, specifically how a biological organism governs its behaviour. This research project investigates how the hippocampus works; and attempts to model this region of the brain onto an electronic device. The hippocampus is chosen because this is one of the regions in the brain responsible for learning and memory. This study uses models of the pyramidal neurons in the hippocampus as well as its spatial representation as the design components for a hardware neuro-controller module. The method chosen to model the individual neurons is the two-dimensional bio-inspired Izhikevich algorithm that has the ability to describe a variety of neuron dynamic behaviours observed in the brain. The hippocampus-inspired spiking neural network architecture also includes place cells/place field representation, a rate-based representation that provides spatial representation of the environment to the hippocampus. A biological nervous system is a dynamical system; it is governed by the learning rules that adjust the strength of connectivity between the neurons in the neural network. These learning rules are implemented to the hippocampus-inspired spiking neural network to allow the neural network to perform its task of path navigation. Following successful simulations of the software prototype of the neural network architecture in performing its desired task, this architecture is then synthesized onto a Field Programmable Gate Array (FPGA) device. This is to allow the neural network architecture to be utilized as a neuro-controller device for the purpose of path navigation, creates memories, and thus achieving autonomy.

ABSTRACT. In this work, a type of developmental brain-inspired computational network is presented and evaluated. It is based on the idea of evolving programs that build a computational neural structure. This thesis describes an artificial model of the brain based on evolutionary computation and neurodevelopmental techniques. This model is more biologically plausible than earlier techniques and demonstrates that adding more biological plausibility can enhance the computational power of the neural systems. The thesis demonstrates the capabilities of this brain inspired system on two different learning problems.

L'apprentissage automatique et la vision par ordinateur sont deux sujets de recherche d'actualité. Des contributions clés à ces domaines ont été les fruits de longues années d'études du cortex visuel et de la fonction des réseaux cérébraux. Dans cette thèse, nous nous intéressons à la conception des architectures neuro-inspirées pour le traitement de l'information sur trois niveaux différents du cortex visuel. Au niveau le plus bas, nous proposons un réseau de neurones pour l'acquisition des signaux visuels. Ce modèle est étroitement inspiré par le fonctionnement et l'architecture de la retine et les premières couches du cortex visuel chez l'humain. Il est également adapté à l'émulation des mouvements oculaires qui jouent un rôle important dans notre vision. Au niveau le plus haut, nous nous intéressons à la mémoire. Nous traitons un modèle de mémoire associative basée sur une architecture neuro-inspirée dite `Sparse Clustered Network (SCN)'. Notre contribution principale à ce niveau est de proposer une amélioration d'un algorithme utilisé pour la récupération des messages partiellement effacés du SCN. Nous suggérons également une formulation générique pour faciliter l'évaluation des algorithmes de récupération, et pour aider au développement des nouveaux algorithmes. Au niveau intermédiaire, nous étendons l'architecture du SCN pour l'adapter au problème de la mise en correspondance des caractéristiques d'images, un problème fondamental en vision par ordinateur. Nous démontrons que la performance de notre réseau atteint l'état de l'art, et offre de nombreuses perspectives sur la façon dont les architectures neuro-inspirées peuvent servir de substrat pour la mise en oeuvre de diverses tâches de vision
Computer vision and machine learning are two hot research topics that have witnessed major breakthroughs in recent years. Much of the advances in these domains have been the fruits of many years of research on the visual cortex and brain function. In this thesis, we focus on designing neuro-inspired architectures for processing information along three different stages of the visual cortex. At the lowest stage, we propose a neural model for the acquisition of visual signals. This model is adapted to emulating eye movements and is closely inspired by the function and the architecture of the retina and early layers of the ventral stream. On the highest stage, we address the memory problem. We focus on an existing neuro-inspired associative memory model called the Sparse Clustered Network. We propose a new information retrieval algorithm that offers more flexibility and a better performance over existing ones. Furthermore, we suggest a generic formulation within which all existing retrieval algorithms can fit. It can also be used to guide the design of new retrieval approaches in a modular fashion. On the intermediate stage, we propose a new way for dealing with the image feature correspondence problem using a neural network model. This model deploys the structure of Sparse Clustered Networks, and offers a gain in matching performance over state-of-the-art, and provides a useful insight on how neuro-inspired architectures can serve as a substrate for implementing various vision tasks

PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO
Esta dissertação objetivará a unificação de duas metodologias de algoritmos evolutivos consagradas para tratamento de problemas ou do tipo combinatórios, ou do tipo numéricos, num único algoritmo com representação mista. Trata-se de um algoritmo evolutivo inspirado na física quântica com representação mista binário-real do espaço de soluções, o AEIQ-BR. Este algoritmo trata-se de uma extensão do modelo com representação binária de Jang, Han e Kin, o AEIQ-B para otimizações combinatoriais, e o de representação real de Abs da Cruz, o AEIQ-R para otimizações numéricas. Com fins de exemplificação do novo algoritmo proposto, o discutiremos no contexto de neuroevolução, com o propósito de configurar completamente uma rede neural com alimentação adiante em termos: seleção de variáveis de entrada; números de neurônios na camada escondida; todos os pesos existentes; e tipos de funções de ativação de cada neurônio. Esta finalidade em se aplicar o algoritmo AEIQ-BR à neuroevolução – e também, numa analogia ao modelo NEIQ-R de Abs da Cruz – receberá a denominação NEIQ-BR. N de neuroevolução, E de evolutivo, IQ de inspiração quântica, e BR de binário-real. Para avaliar o desempenho do NEIQ-BR, utilizarse- á um total de seis casos benchmark de classificação, e outros dois casos reais, em campos da ciência como: finanças, biologia e química. Resultados serão comparados com algoritmos de outros pesquisadores e a modelagem manual de redes neurais, através de medidas de desempenho. Através de testes estatísticos concluiremos que o algoritmo NEIQ-BR apresentará um desempenho significativo na obtenção de previsões de classificação por neuroevolução.
This work aimed to unify two methodologies of evolutionary algorithms to treat problems with or combinatorial characteristics, or numeric, on a unique algorithm with mix representation. It is an evolutionary algorithm inspired in quantum physics with mixed representation of the solutions space, called QIEABR. This algorithm is an extension of the model with binary representation of the chromosome from Jang, Han e Kin, the QIEA-B for combinatorial optimization, and numeric representation from Abs da Cruz, the QIEA-R for numerical optimizations. For purposes of exemplification of the new algorithm, we will introduce the algorithm in the context of neuro-evolution, in order to completely configure a feed forward neural network in terms of: selection of input variables; numbers of neurons in the hidden layer; all existing synaptic weights; and types of activation functions of each neuron. This purpose when applying the algorithm QIEA-BR to neuro-evolution receive the designation of QIEN-BR. QI for quantum-inspired, E for evolutive, N for neuro-evolution, and BR for binary-real representation. To evaluate the performance of QIEN-BR, we will use a total of six benchmark cases of classification, and two real cases in fields of science such as finance, biology and chemistry. Results will be compared with algorithms of other researchers and manual modeling of neural networks through performance measures. Statistical tests will be provided to elucidate the significance of results, and what we can conclude is that the algorithm QIEN-BR better performance others researchers in terms of classification prediction.

Les réseaux de neurones artificiels, dont le concept s'inspire du fonctionnement des cerveaux biologiques et de leurs capacités d'apprentissage, sont une approche prometteuse pour répondre aux nouveaux usages informatiques dits « cognitifs », tels que la reconnaissance d'images ou l'interaction en langage naturel. Néanmoins, leur mise en œuvre par des ordinateurs conventionnels est peu efficace. Une solution à ce problème est le développement de puces d'accélération matérielle spécialisées qui comportent :- des neurones, unités de traitement de l'information, pour lesquelles des circuits électroniques efficaces existent ;- des synapses, reliant les neurones mais aussi support matériel de l'apprentissage, par le biais de la modulation de leur conductance électrique (qualifiée de « plasticité synaptique »). Réaliser des synapses artificielles intégrables densément et capables d'apprendre in situ reste aujourd'hui un défi majeur.Ces travaux de thèse portent sur l'utilisation synaptique de nanocomposants mémoires innovants, dont certains comportements plastiques riches et intrinsèques sont analogues aux fonctionnalités que nous recherchons.Nous nous intéressons tout d'abord aux jonctions tunnel magnétiques à transfert de spin, développées dans l'industrie pour concevoir de nouvelles mémoires informatiques non volatiles. Nous montrons qu'il est aussi possible d'en faire des synapses artificielles binaires. Après la modélisation analytique de leur comportement naturellement stochastique, nous présentons comment exploiter ce dernier pour faciliter la mise en œuvre in situ d'une règle d'apprentissage probabiliste. À l'aide d'outils de simulation développés au laboratoire, nous étudions l'influence du régime de programmation sur la robustesse d'un système à la variabilité de telles synapses et sur leur consommation énergétique.Nous nous tournons ensuite vers des cellules électrochimiques métalliques Ag2S, d'autres nanocomposants mémoires innovants fabriqués et étudiés par des collaborateurs de l'Université de Lille I, qui y ont déjà observé plusieurs comportements plastiques. Nous avons découvert une plasticité supplémentaire, proche d'un comportement observé en neurosciences. Grâce à un modèle analytique simple permettant de comprendre les relations entre les différentes plasticités, nous montrons en simulation une preuve de concept d'apprentissage non supervisé qui repose sur l'interaction de ces multiples comportements.Pour finir, nous soulevons des pistes de réflexion sur les défis posés par les circuits nécessaires au bon fonctionnement d'un système utilisant comme synapses artificielles les nanocomposants étudiés, notamment lors de la lecture ou de l'écriture de ces derniers.Les résultats de cette thèse ouvrent la voie à la conception de systèmes neuro-inspirés capables d'apprendre en s'appuyant sur la richesse de comportements plastiques offerte par les nanocomposants mémoires innovants
Artificial neural networks, which take some inspiration from the behavior of biological brains and their learning capabilities, are promising tools to address emerging computing uses known as “cognitive” tasks like classifying images or natural language interaction. However, implementing them on conventional computers is poorly efficient. A solution to this problem is to develop specialized acceleration chips which feature:• neurons, the information processing units, which can be implemented efficienctly with current electronic technologies;• synapses, the connections between the neurons which also support the learning process by adjusting their electrical conductance (“synaptic plasticity”). Implementing artificial synapses with high integration and on-line learning capabilities is still a challenge.This thesis explores the use of innovative memory nanodevices as artificial synapses: some of their rich plastic behaviors naturally implement features that are difficult to access with other devices.First, we investigate spin-transfer torque magnetic tunnel junctions, that are currently develop in industry as a new non volatile memory technology. We show that they can also be used as binary artificial synapses. After modeling their intrinsic stochastic behavior analytically, we describe how to harness this behavior to facilitate the implementation of an on-line probabilistic learning rule. With simulations tools developped in the laboratory, we detail the impact of the programming regime on the resilience of a system that uses such synapses, as well as on the system's power consumptionWe then investigate Ag2S electrochemical metalization cells, another type of innovative memory nanodevices fabricated and characterized by collaborators from Université de Lille I, who had already observed the existence of several plastic behaviors. We discovered an additional plasticity, close to a behavior known in neurosciences. With a simple analytical model that allows a better understanding of the relationships between theses plasticities, we show by simulations means a proof of concept of an unsupervised learning that relies on the interaction of the plastic behaviors theses nanodevices feature.Finally, we consider the challenges arising from the circuits that are required to read and write such artificial synapses in a neuro-inspired system.The results of this Ph.D. work pave the way for the design of neuro-inspired systems that can learn by harnessing the rich plastic behaviors that are featured by innovative memory nanodevices

Cette thèse s'inscrit dans le contexte de l'étude des circuits neuromorphiques utilisant des dispositifs memristifs comme synapses. Son objectif principal est d'évaluer les mérites d'une nouvelle classe de mémoires organiques développées au LICSEN (CEA Saclay/IRAMIS) et, plus particulièrement, leur adéquation avec les propositions d'implémentation et les règles d'apprentissage proposées par l'équipe NanoArchi de l'IEF (Univ. Paris-Sud, Orsay). Les memristors étudiés sont basés sur l'electro-greffage en films minces de complexes organiques redox pour la formation de jonctions métal/molécules/métal robustes et scalables. Outre la fabrication de memristors, le travail inclut d'importants efforts de caractérisation électrique (vitesse, non-volatilité, scalabilité, robustesse, etc.) visant d'une part à étudier les mécanismes de commutation dans ces nouveaux matériaux memristifs organiques, et d'autres part, à évaluer leur potentiel en tant que synapses. Cette thèse présente également une étude préparatoire à la réalisation d'un démonstrateur de circuit mixte de type réseaux de neurones combinant nano-memristors et électronique conventionnelle (programmabilité des dispositifs en mode impulsionnel, réalisation d'assemblées de dispositifs, variabilité). De plus, la démonstration de la compatibilité de ces memristors avec la propriété STDP (Spike Timing Dependent Plasticity) ainsi que de l’apprentissage d’un « réflexe conditionné » ouvrent la voie aux apprentissages non-supervisés
This PhD project takes place in the context of the study of neuromorphic circuits using memristor devices as synapses. The main objective is to evaluate a new class of organic memories developed at LICSEN (CEA Saclay/IRAMIS) and particularly their compatibility with the learning rules and the implementation strategy proposed by the Nanoarchi group at IEF (Univ. Paris-Sud, Orsay). These new memristors are based on the electro-grafting of organic redox complexes thin films to form robust and scalable metal/molecules/metal junctions. In addition to memristor fabrication, this work includes detailed electrical characterization studies (speed, retention property, scalability, robustness, etc.) aiming at, on the one hand, establishing the commutation mechanism in these new memristors and, on the other hand, evaluating their potential as synapses. This work also proposes a preparatory study of a neural-network type mixed-circuit demonstrator combining nano-memristors and conventional electronic (programmability of devices by spikes, fabrication of assemblies of memristors, variability). Moreover the demonstration of the compatibility of such memristors with the STDP (Spike Timing Dependent Plasticity) property and of the learning of a “conditioned reflex” opens the way to future unsupervised learning studies

Depuis les années soixante-dix l'évolution des performances des circuits électroniques repose exclusivement sur l'amélioration des performances des transistors. Ce composant a des propriétés extraordinaires puisque lorsque ses dimensions sont réduites, toutes ses caractéristiques sont améliorées. Mais, dû à certaines limites physiques fondamentales, la diminution des dimensions des transistors n’est plus possible. Néanmoins, de nouveaux nano-composants mémoire innovants qui peuvent être intégré conjointement avec les transistors voient le jour tant au niveau académique qu'industriel, ce qui constitue une opportunité pour repenser complètement l'architecture des circuits électroniques actuels. L'une des voies de recherche possible est l’inspiration du fonctionnement du cerveau biologique. Ce dernier peut accomplir des tâches complexes et variées en consommant très peu d’énergie. Ces travaux de thèse explorent trois paradigmes neuro-inspirés pour l'utilisation de ces composants mémoire. Chacune de ces approches explore différentes problématiques du calcul en mémoire
While 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

Le traitement actuel de l'information dans les grands clusters de calcul, est responsable d'un fort impact énergétique au niveau mondial. Le paradigme actuel est à repenser, et une architecture de calcul basée sur des composants photoniques (laser à semi-conducteur notamment) est étudiée dans cette thèse. La structure envisagée est un réseau de neurones artificiels pour du traitement de données de télécommunications. Nous étudions une diode laser et ses états dynamiques lorsque soumise à une injection optique et à un feedback optiques simultanés et les liens avec sa capacité de calcul neuroinspirée par de la simulation et de l'expérimentation
The current processing of information in large computing clusters is responsible for a strong energetic impact at a global level. The current paradigm needs to be rethought, and a computing architecture based on photonic components (semiconductor laser in particular) is studied in this thesis. The considered structure is a network of artificial neurons for telecommunications data processing. This involves using a laser diode to study the relationship between the dynamics with optical injection and optical feedback and neuroinspired computing capacity with simulations and experimental work

Les nouvelles techniques de fabrication nanométriques comme l'auto-assemblage ou la nanoimpression permettent de réaliser des matrices régulières (crossbars) atteignant des densités extrêmes (jusqu'à 1012 nanocomposants/cm2) tout en limitant leur coût de fabrication. Cependant, il est attendu que ces technologies s'accompagnent d'une augmentation significative du nombre de défauts et de dispersions de caractéristiques. La capacité à exploiter ces crossbars est alors conditionnée par le développement de nouvelles techniques de calcul capables de les spécialiser et de tolérer une grande densité de défauts. Dans ce contexte, l'approche neuromimétique qui permet tout à la fois de configurer les nanodispositifs et de tolérer leurs défauts et dispersions de caractéristiques apparaît spécialement pertinente. L'objectif de cette thèse est de démontrer l'efficacité d'une telle approche et de quantifier la fiabilité obtenue avec une architecture neuromimétique à base de crossbar de memristors, ou neurocrossbar (NC). Tout d'abord la thèse introduit des algorithmes permettant l'apprentissage de fonctions logiques sur un NC. Par la suite, la thèse caractérise la tolérance du modèle NC aux défauts et aux variations de caractéristiques des memristors. Des modèles analytiques probabilistes de prédiction de la convergence de NC ont été proposés et confrontés à des simulations Monte-Carlo. Ils prennent en compte l'impact de chaque type de défaut et de dispersion. Grâce à ces modèles analytiques il devient possible d'extrapoler cette étude à des circuits NC de très grande taille. Finalement, l'efficacité des méthodes proposées est expérimentalement démontrée à travers l'apprentissage de fonctions logiques par un NC composé de transistors à nanotube de carbone à commande optique (OG-CNTFET).

Nous produisons chaque jour de grandes quantités de données, que nous échangeons sur le réseau Internet. Ces données sont traitées grâce à des clusters de calcul, responsables de la consommation énergétique d’internet. Dans cette thèse, nous étudions une architecture faite de composants photoniques, pour se débarrasser des composants électroniques consommant de l'énergie. Grâce aux composants actuellement utilisés dans le réseau Internet (laser et fibre optique), nous réalisons un réseau neuronal artificiel capable de traiter les données de télécommunication. Le réseau de neurones artificiel est constitué d'un laser et d'une fibre optique qui renvoie la lumière dans ce laser. Le comportement complexe de ce système est utilisé pour alimenter les neurones artificiels qui sont répartis le long de la fibre. Nous sommes en mesure de prouver que ce système est capable de traiter soit un signal avec une grande efficacité, soit deux signaux au prix d'une petite perte de précision
We are producing everyday thousands of gigabits of data, exchanged over the internet network. These data are processed thanks to computation clusters, which are responsible of the large amount of energy consumed by the internet network. In this work, we study an architecture made of photonic components, to get rid of electronic components that are power consuming. Thanks to components that are currently used in the internet network (laser and optical fiber), we aim at building an artificial neural network that is able to process telecommunication data. The artificial neural network is made of a laser, and an optical fiber that send back the light into the laser. The complex behavior of this system is used to feed the artificial neurons that are distributed along the fiber. We are able to prove that this system is able either to process one signal with a high efficiency, or two signals at the expense of a small loss of accuracy

Dans cette thèse, nous proposons d'intégrer la notion d'habitude comportementale au sein d'une architecture de contrôle robotique, et d'étudier son interaction avec les mécanismes générant le comportement planifié. Les architectures de contrôle robotiques permettent à ce dernier d'être utilisé efficacement dans le monde réel et au robot de rester réactif aux changements dans son environnement, tout en étant capable de prendre des décisions pour accomplir des buts à long terme (Kortenkamp et Simmons, 2008). Or, ces architectures sont rarement dotées de capacités d'apprentissage leur permettant d'intégrer les expériences précédentes du robot. En neurosciences et en psychologie, l'étude des différents types d'apprentissage montre pour que ces derniers sont une capacité essentielle pour adapter le comportement des mammifères à des contextes changeants, mais également pour exploiter au mieux les contextes stables (Dickinson, 1985). Ces apprentissages sont modélisés par des algorithmes d'apprentissage par renforcement direct et indirect (Sutton et Barto, 1998), combinés pour exploiter leurs propriétés au mieux en fonction du contexte (Daw et al., 2005). Nous montrons que l'architecture proposée, qui s'inspire de ces modèles du comportement, améliore la robustesse de la performance lors d'un changement de contexte dans une tâche simulée. Si aucune des méthodes de combinaison évaluées ne se démarque des autres, elles permettent d'identifier les contraintes sur le processus de planification. Enfin, l'extension de l'étude de notre architecture à deux tâches (dont l'une sur robot réel) confirme que la combinaison permet l'amélioration de l'apprentissage du robot
In this work, we study how the notion of behavioral habit, inspired from the study of biology, can benefit to robots. Robot control architectures allow the robot to be able to plan to reach long term goals while staying reactive to events happening in the environment (Kortenkamp et Simmons, 2008). However, these architectures are rarely provided with learning capabilities that would allow them to acquire knowledge from experience. On the other hand, learning has been shown as an essential abiilty for behavioral adaptation in mammals. It permits flexible adaptation to new contexts but also efficient behavior in known contexts (Dickinson, 1985). The learning mechanisms are modeled as model-based (planning) and model-free (habitual) reinforcement learning algorithms (Sutton et Barto, 1998) which are combined into a global model of behavior (Daw et al., 2005). We proposed a robotic control architecture that take inspiration from this model of behavior and embed the two kinds of algorithms, and studied its performance in a robotic simulated task. None of the several methods for combining the algorithm we studied gave satisfying results, however, it allowed to identify some properties required for the planning process in a robotic task. We extended our study to two other tasks (one being on a real robot) and confirmed that combining the algorithms improves learning of the robot's behavior

Dans cette thèse, nous proposons d'intégrer la notion d'habitude comportementale au sein d'une architecture de contrôle robotique, et d'étudier son interaction avec les mécanismes générant le comportement planifié. Les architectures de contrôle robotiques permettent à ce dernier d'être utilisé efficacement dans le monde réel et au robot de rester réactif aux changements dans son environnement, tout en étant capable de prendre des décisions pour accomplir des buts à long terme (Kortenkamp et Simmons, 2008). Or, ces architectures sont rarement dotées de capacités d'apprentissage leur permettant d'intégrer les expériences précédentes du robot. En neurosciences et en psychologie, l'étude des différents types d'apprentissage montre pour que ces derniers sont une capacité essentielle pour adapter le comportement des mammifères à des contextes changeants, mais également pour exploiter au mieux les contextes stables (Dickinson, 1985). Ces apprentissages sont modélisés par des algorithmes d'apprentissage par renforcement direct et indirect (Sutton et Barto, 1998), combinés pour exploiter leurs propriétés au mieux en fonction du contexte (Daw et al., 2005). Nous montrons que l'architecture proposée, qui s'inspire de ces modèles du comportement, améliore la robustesse de la performance lors d'un changement de contexte dans une tâche simulée. Si aucune des méthodes de combinaison évaluées ne se démarque des autres, elles permettent d'identifier les contraintes sur le processus de planification. Enfin, l'extension de l'étude de notre architecture à deux tâches (dont l'une sur robot réel) confirme que la combinaison permet l'amélioration de l'apprentissage du robot
In this work, we study how the notion of behavioral habit, inspired from the study of biology, can benefit to robots. Robot control architectures allow the robot to be able to plan to reach long term goals while staying reactive to events happening in the environment (Kortenkamp et Simmons, 2008). However, these architectures are rarely provided with learning capabilities that would allow them to acquire knowledge from experience. On the other hand, learning has been shown as an essential abiilty for behavioral adaptation in mammals. It permits flexible adaptation to new contexts but also efficient behavior in known contexts (Dickinson, 1985). The learning mechanisms are modeled as model-based (planning) and model-free (habitual) reinforcement learning algorithms (Sutton et Barto, 1998) which are combined into a global model of behavior (Daw et al., 2005). We proposed a robotic control architecture that take inspiration from this model of behavior and embed the two kinds of algorithms, and studied its performance in a robotic simulated task. None of the several methods for combining the algorithm we studied gave satisfying results, however, it allowed to identify some properties required for the planning process in a robotic task. We extended our study to two other tasks (one being on a real robot) and confirmed that combining the algorithms improves learning of the robot's behavior

Computational intelligence techniques, such as artificial neural networks (ANNs), have been widely used to improve the performance of power system monitoring and control. Although inspired by the neurons in the brain, ANNs are largely different from living neuron networks (LNNs) in many aspects. Due to the oversimplification, the huge computational potential of LNNs cannot be realized by ANNs. Therefore, a more brain-like artificial neural network is highly desired to bridge the gap between ANNs and LNNs. The focus of this research is to develop a biologically inspired artificial neural network (BIANN), which is not only biologically meaningful, but also computationally powerful. The BIANN can serve as a novel computational intelligence tool in monitoring, modeling and control of the power systems. A comprehensive survey of ANNs applications in power system is presented. It is shown that novel types of reservoir-computing-based ANNs, such as echo state networks (ESNs) and liquid state machines (LSMs), have stronger modeling capability than conventional ANNs. The feasibility of using ESNs as modeling and control tools is further investigated in two specific power system applications, namely, power system nonlinear load modeling for true load harmonic prediction and the closed-loop control of active filters for power quality assessment and enhancement. It is shown that in both applications, ESNs are capable of providing satisfactory performances with low computational requirements. A novel, more brain-like artificial neural network, i.e. biologically inspired artificial neural network (BIANN), is proposed in this dissertation to bridge the gap between ANNs and LNNs and provide a novel tool for monitoring and control in power systems. A comprehensive survey of the spiking models of living neurons as well as the coding approaches is presented to review the state-of-the-art in BIANN research. The proposed BIANNs are based on spiking models of living neurons with adoption of reservoir-computing approaches. It is shown that the proposed BIANNs have strong modeling capability and low computational requirements, which makes it a perfect candidate for online monitoring and control applications in power systems. BIANN-based modeling and control techniques are also proposed for power system applications. The proposed modeling and control schemes are validated for the modeling and control of a generator in a single-machine infinite-bus system under various operating conditions and disturbances. It is shown that the proposed BIANN-based technique can provide better control of the power system to enhance its reliability and tolerance to disturbances. To sum up, a novel, more brain-like artificial neural network, i.e. biologically inspired artificial neural network (BIANN), is proposed in this dissertation to bridge the gap between ANNs and LNNs and provide a novel tool for monitoring and control in power systems. It is clearly shown that the proposed BIANN-based modeling and control schemes can provide faster and more accurate control for power system applications. The conclusions, the recommendations for future research, as well as the major contributions of this research are presented at the end.

Dans ce manuscrit nous proposons une architecture neuronale d'inspiration corticale, capable de développer un traitement émergent de type auto-organisation. Afin d'implémenter cette architecture neuronale de manière distribuée, nous utilisons le modèle de champs neuronaux dynamiques, un formalisme mathématique générique conçu pour modéliser la compétition des activités neuronales au niveau cortical mésoscopique. Pour analyser en détail les propriétés dynamiques des modèles de référence de ce formalisme, nous proposons un critère formel et un instrument d'évaluation, capable d'examiner et de quantifier le comportement dynamique d'un champ neuronal quelconque dans différents contextes de stimulation. Si cet instrument nous permet de mettre en évidence les avantages pratiques de ces modèles, il nous révèle aussi l'incapacité de ces modèles à conduire l'implantation des processus d'auto-organisation (implémenté par l'architecture décrite) vers des résultats satisfaisants. Ces résultats nous amènent à proposer une alternative aux modèles classiques de champs, basée sur un mécanisme de rétro-inhibition, qui implémente un processus local de régulation neuronale. Grâce à ce mécanisme, le nouveau modèle de champ réussit à implémenter avec succès le processus d'auto-organisation décrit par l'architecture proposée d'inspiration corticale. De plus, une analyse détaillée confirme que ce formalisme garde les caractéristiques dynamiques exhibées par les modèles classiques de champs neuronaux. Ces résultats ouvrent la perspective de développement des architectures de calcul neuronal de traitement d'information pour la conception des solutions logicielles ou robotiques bio-inspirées
In 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

O sistema olfatório é notável por sua capacidade de discriminar odores muito similares, mesmo que estejam misturados. Essa capacidade de discriminação é, em parte, devida a padrões de atividade espaço-temporais gerados nas células mitrais, as células principais do bulbo olfatório, durante a apresentação de um odor. Tais padrões dinâmicos decorrem de interações sinápticas recíprocas entre as células mitrais e interneurônios inibitórios do bulbo olfatório, por exemplo, as células granulares. Nesta tese, apresenta-se um modelo do bulbo olfatório baseado em modelos pulsados das células mitrais e granulares e avalia-se o seu desempenho como sistema reconhecedor de padrões usando-se bases de dados de padrões artificiais e reais. Os resultados dos testes mostram que o modelo possui a capacidade de separar padrões em diferentes classes. Essa capacidade pode ser explorada na construção de sistemas reconhecedores de padrões. Apresenta-se também a ferramenta denominada Nemos, desenvolvida para a implementação do modelo, que é uma plataforma para simulação de neurônios e redes de neurônios pulsados com interface gráfica amigável com o usuário.
The olfactory system is a remarkable system capable of discriminating very similar odorant mixtures. This is in part achieved via spatio-temporal activity patterns generated in mitral cells, the principal cells of the olfactory bulb, during odor presentation. Here, we present a spiking neural network model of the olfactory bulb and evaluate its performance as a pattern recognition system with datasets taken from both artificial and real pattern databases. Our results show that the dynamic activity patterns produced in the mitral cells of the olfactory bulb model by pattern attributes presented to it have a pattern separation capability. This capability can be explored in the construction of high-performance pattern recognition systems. Besides, we proposed Nemos a framework for simulation spiking neural networks through graphical user interface and has extensible models for neurons, synapses and networks.

Dans ce manuscrit nous proposons une architecture neuronale d'inspiration corticale, capable de développer un traitement émergent de type auto-organisation. Afin d'implémenter cette architecture neuronale de manière distribuée, nous utilisons le modèle de champs neuronaux dynamiques, un formalisme mathématique générique conçu pour modéliser la compétition des activités neuronales au niveau cortical mésoscopique. Pour analyser en détail les propriétés dynamiques des modèles de référence de ce formalisme, nous proposons un critère formel et un instrument d'évaluation, capable d'examiner et de quantifier le comportement dynamique d'un champ neuronal quelconque dans différents contextes de stimulation. Si cet instrument nous permet de mettre en évidence les avantages pratiques de ces modèles, il nous révèle aussi l'incapacité de ces modèles à conduire l'implantation des processus d'auto-organisation (implémenté par l'architecture décrite) vers des résultats satisfaisants. Ces résultats nous amènent à proposer une alternative aux modèles classiques de champs, basée sur un mécanisme de rétro-inhibition, qui implémente un processus local de régulation neuronale. Grâce à ce mécanisme, le nouveau modèle de champ réussit à implémenter avec succès le processus d'auto-organisation décrit par l'architecture proposée d'inspiration corticale. De plus, une analyse détaillée confirme que ce formalisme garde les caractéristiques dynamiques exhibées par les modèles classiques de champs neuronaux. Ces résultats ouvrent la perspective de développement des architectures de calcul neuronal de traitement d'information pour la conception des solutions logicielles ou robotiques bio-inspirées.

Made available in DSpace on 2014-12-17T15:38:38Z (GMT). No. of bitstreams: 1 AnaABM_TESE.pdf: 1144544 bytes, checksum: 6d221c02bdb372ff108e024fd2df6e45 (MD5) Previous issue date: 2014-03-20
Culturally, childbearing is understood as a situation that subjects will experience at some point in their lives, especially people who are married or have a similar affectionate relationship. Thus, to realize the inability to meet such a fate seems to be a natural cultural trigger of suffering, frustration and feelings of inadequacy and helplessness. Specifically for men, infertility is closely related to loss of masculinity, virility. He fails in his role as a male. This study sought to understand the impact that infertility have on the existence of a man who receives such a diagnosis, both in self-image as in their marital, sexual and professional roles. This study sets up as a hermeneutic phenomenological research based on the ideas of the philosopher Martin Heidegger. Participants were seven heterosexual, married and infertile men. Two interviews were conducted. The analysis of the material included both the material of the narratives, as the affectation of the researcher when interacting with the participants and their narratives, through phenomenological-hermeneutic interpretation. The results corroborate the literature that states the difficulty of the men, immersed in a context that defines them as virile, powerful and invulnerable to worry about issues related to health and disease. The possibility of any condition that impairs the reproductive capacity exceeds the acceptable limits of daily life for these men, not being recognized as a model of masculinity present in the condition in which they recognize. This leads to questions about their masculinity, role in the marital relationship and their existence. Thus, to recognize themselves as infertile surpass a medical diagnosis and is associated with the construction of meaning for their existence from the approximation with the infertility condition, which helps in redirecting their choices, restoring the project to be self and allowing further recognition as men. In the marital relationship, doing what they can to ensure, theirs happiness. Through these actions, they remain playing the role of family provider, showing that they are able to protect their wives and taking in assisted reproduction or adoption of children viable alternatives to fulfill the desire to leave a legacy and give a child to their wives and to society. Another result observed, refers to the ontological condition of care that characterizes the human being. The ways in which men are treated socially demonstrates a type of care that focuses on the development of characteristics such as strength, virility and determination but does not allow them to cope with the suffering of emotionally difficult situations, such as the diagnosis of infertility. At the end, the study gives rise to reflections on the need to provide a 12 space for men and their expressions of suffering, as well as to recognize their ability to overcome the painful and difficult situations
Culturalmente, procriar ? compreendido como uma situa??o que o sujeito deve vivenciar em algum momento de sua vida. Descobrir-se incapaz de cumprir tal destino naturalizado parece ser desencadeador de sofrimento, frustra??o e sentimentos de incapacidade e impot?ncia. Especificamente para o homem, a infertilidade est? estreitamente relacionada ? perda de masculinidade, de virilidade. Ele fracassa em seu papel de macho . O presente estudo buscou compreender os impactos que a infertilidade produz na exist?ncia do homem que recebe tal diagn?stico, tanto nos modos de perceber a si mesmo quanto no papel conjugal, sexual e profissional. Configura-se como uma pesquisa de inspira??o fenomenol?gico-hermen?utica, baseada em ideias do fil?sofo Martin Heidegger. Participaram do estudo sete homens heterossexuais, casados e com diagn?stico de infertilidade, sendo realizadas duas entrevistas individuais. A an?lise do material compreendeu tanto o material das narrativas quanto as afeta??es da pesquisadora por ocasi?o do contato com os colaboradores e suas narrativas, por meio da interpreta??o fenomenol?gico-hermen?utica. Os resultados corroboram dados da literatura, os quais afirmam a dificuldade dos homens, imersos em um contexto que exige que eles sejam viris, potentes e invulner?veis, de se preocuparem com as quest?es relacionadas ? sa?de e ? doen?a. Assim, a possibilidade de alguma condi??o que dificulte a sua capacidade reprodutiva, ultrapassa os limites aceit?veis no horizonte cotidiano de sentido que comp?e as vidas destes homens, n?o sendo reconhecida como uma condi??o presente no modelo de masculinidade no qual eles se reconhecem. Isto leva a um questionamento a respeito de sua masculinidade, de seu papel na rela??o conjugal e na pr?pria exist?ncia. Reconhecerem-se na condi??o de homens inf?rteis vai al?m de um diagn?stico m?dico e est? relacionado ? constru??o de novos sentidos existenciais. A partir da aproxima??o com tal condi??o, redirecionam suas escolhas, resgatando o projeto de ser si-mesmos e possibilitando continuarem se reconhecendo homens. Na rela??o conjugal, fazem o que estiver ao seu alcance para garantir, de alguma forma, que as esposas se sintam satisfeitas e, atrav?s destas a??es, eles permanecem exercendo o papel de provedores da fam?lia, demonstrando serem capazes de ampar?-las e proteg?-las, tendo, na reprodu??o assistida ou da ado??o de uma crian?a, alternativas vi?veis para concretizar o desejo de deixar um legado e de prover ? fam?lia e a sociedade. Outro resultado observado diz respeito ? condi??o ontol?gica de solicitude que caracteriza o ser humano. V?rias formas como os homens s?o 10 tratados pelas pessoas que est?o mais pr?ximas demonstram um tipo de solicitude no qual, ao mesmo tempo em que s?o valorizadas caracter?sticas como for?a, virilidade e determina??o, n?o ? permitido que os homens se aproximem de sofrimento, poupando-os de situa??es emocionalmente dif?ceis, como ? o caso do diagn?stico de infertilidade. Ao final, o estudo enseja reflex?es sobre a necessidade de proporcionar espa?os de acolhimento e de escuta aos homens e ?s suas express?es de sofrimento, bem como o reconhecimento de sua capacidade de supera??o das situa??es dolorosas e dif?ceis

Une boucle de rétroaction à retard a lieu lorsque la sortie d’un système est utilisée pour modifier le signal d’entrée de ce dernier. Ce phénomène apparaît dans des domaines aussi variés que la physique des amplificateurs, la biologie de la régulation de l’insuline ou encore les sciences sociales. Les effets d’une boucle de rétroaction à retard sur un système électronique sont bien connus et ont donné lieu à de nombreuses applications : boucle à verrouillage de phase pour améliorer les propriétés stochastiques, boucle d’amplification ou de régulation, etc. Cependant ces effets ont étés relativement peu étudiés dans le cadre des systèmes nanomagnétiques. Dans ces travaux de thèse j'ai étudié théoriquement les conséquences d'une boucle de rétroaction à retard sur la dynamique de l'aimantation de trois différents systèmes nanométriques avec un objectif distinct pour chaque système. Le premier concerne un oscillateur à transfert de spin dont j’ai étudié les propriétés stochastiques. La rétroaction engendre de fortes variations de la largeur spectrale et fait apparaitre de bandes secondaires à larges retards. Le deuxième système étudié est l'oscillateur macrospin dans lequel des transitions chaotiques entre deux modes de précession (dans le plan de la couche et hors du plan) sont induites par la rétroaction. Je montre qu'il est possible d'exploiter de telle dynamique pour la génération de nombres aléatoires. Enfin le troisième système représente une implémentation d'un oscillateur du type « Mackey-Glass » avec une paroi de domaine piégée dans un ruban. En déformant cette paroi par courant polarisé de spin, et avec un choix judicieux du signal de sortie, je démontre que ce système peut servir comme élément de base pour une architecture temporelle d'un calculateur avec réservoir (« reservoir computer »), qui permet d'effectuer des tâches comme la prédiction des séries temporelles non linéaires
A delay feedback loop occurs when the output of a system is used to modify the input signal of the system. This phenomenon appears in fields as varied as the physics of amplifiers, the biology of insulin regulation or in social interactions. The effects of a delay feedback loop on an electronic system are well known and have given rise to many applications: phase-locked loops to improve stochastic properties, amplification or regulation loops, and so on. However, these feedback effects remain relatively unexplored in the context of nanomagnetic systems. In this thesis I have studied theoretically the consequences of delayed feedback on the magnetization dynamics of three different nanoscale systems with a separate focus for each system. The first involves spin-torque nano-oscillators whose stochastic properties and the impact of a feedback loop on them have been studied. It is found that significant changes can occur to the spectral linewidth, along with the appearance of secondary frequencies at large delays. The second system involves the macrospin oscillator, where I investigated how delayed feedback can induce chaotic transitions between the in-plane and out-ofplane precession states. These complex dynamics can be used to generate random numbers. The third system represents a proposal for implementing a Mackey-Glass oscillator using a domain wall racetrack-like geometry. By deforming this domain wall with spin polarized currents and with a suitable readout function, I show that this oscillator can be used for a time-delay architecture for reservoir computing. Tests of nonlinear time series prediction are conducted to evaluate the performance of this system

Deep ‘Analog Artificial Neural Networks’ (AANNs) perform complex classification problems with high accuracy. However, they rely on humongous amount of power to perform the calculations, veiling the accuracy benefits. The biological brain on the other hand is significantly more powerful than such networks and consumes orders of magnitude less power, indicating some conceptual mismatch. Given that the biological neurons are locally connected, communicate using energy efficient trains of spikes, and the behavior is non-deterministic, incorporating these effects in Artificial Neural Networks (ANNs) may drive us few steps towards a more realistic neural networks.

Emerging devices can offer a plethora of benefits including power efficiency, faster operation, low area in a vast array of applications. For example, memristors and Magnetic Tunnel Junctions (MTJs) are suitable for high density, non-volatile Random Access Memories when compared with CMOS implementations. In this work, we analyze the possibility of harnessing the characteristics of such emerging devices, to achieve neuro-inspired solutions to intricate problems.

We propose how the inherent stochasticity of nano-scale resistive devices can be utilized to realize the functionality of spiking neurons and synapses that can be incorporated in deep stochastic Spiking Neural Networks (SNN) for image classification problems. While ANNs mainly dwell in the aforementioned classification problem solving domain, they can be adapted for a variety of other applications. One such neuro-inspired solution is the Cellular Neural Network (CNN) based Boolean satisfiability solver. Boolean satisfiability (k-SAT) is an NP-complete (k≥3) problem that constitute one of the hardest classes of constraint satisfaction problems. We provide a proof of concept hardware based analog k-SAT solver that is built using MTJs. The inherent physics of MTJs, enhanced by device level modifications, is harnessed here to emulate the intricate dynamics of an analog, CNN based, satisfiability (SAT) solver.

Furthermore, in the effort of reaching human level performance in terms of accuracy, increasing the complexity and size of ANNs is crucial. Efficient algorithms for evaluating neural network performance is of significant importance to improve the scalability of networks, in addition to designing hardware accelerators. We propose a scalable approach for evaluating Liquid State Machines: a bio-inspired computing model where the inputs are sparsely connected to a randomly interlinked reservoir (or liquid). It has been shown that biological neurons are more likely to be connected to other neurons in the close proximity, and tend to be disconnected as the neurons are spatially far apart. Inspired by this, we propose a group of locally connected neuron reservoirs, or an ensemble of liquids approach, for LSMs. We analyze how the segmentation of a single large liquid to create an ensemble of multiple smaller liquids affects the latency and accuracy of an LSM. In our analysis, we quantify the ability of the proposed ensemble approach to provide an improved representation of the input using the Separation Property (SP) and Approximation Property (AP). Our results illustrate that the ensemble approach enhances class discrimination (quantified as the ratio between the SP and AP), leading to improved accuracy in speech and image recognition tasks, when compared to a single large liquid. Furthermore, we obtain performance benefits in terms of improved inference time and reduced memory requirements, due to lower number of connections and the freedom to parallelize the liquid evaluation process.