This thesis aims to understand the learning mechanisms which underpin the process of visual object recognition in the primate ventral visual system. The computational crux of this problem lies in the ability to retain specificity to recognize particular objects or faces, while exhibiting generality across natural variations and distortions in the view (DiCarlo et al., 2012). In particular, the work presented is focussed on gaining insight into the processes through which transformation-invariant visual representations may develop in the primate ventral visual system. The primary motivation for this work is the belief that some of the fundamental mechanisms employed in the primate visual system may only be captured through modelling the individual action potentials of neurons and therefore, existing rate-coded models of this process constitute an inadequate level of description to fully understand the learning processes of visual object recognition. To this end, spiking neural network models are formulated and applied to the problem of learning transformation-invariant visual representations, using a spike-time dependent learning rule to adjust the synaptic efficacies between the neurons. The ways in which the existing rate-coded CT (Stringer et al., 2006) and Trace (Földiák, 1991) learning mechanisms may operate in a simple spiking neural network model are explored, and these findings are then applied to a more accurate model using realistic 3-D stimuli. Three mechanisms are then examined, through which a spiking neural network may solve the problem of learning separate transformation-invariant representations in scenes composed of multiple stimuli by temporally segmenting competing input representations. The spike-time dependent plasticity in the feed-forward connections is then shown to be able to exploit these input layer dynamics to form individual stimulus representations in the output layer. Finally, the work is evaluated and future directions of investigation are proposed.

Artificial neural networks have shown great potential and have attracted much research interest. One problem faced when simulating such networks is speed. As the number of neurons increases, the time to simulate and train a network increases dramatically. This makes it difficult to simulate and train a large-scale network system without the support of a high-performance computer system. The solution we present is a "real" parallel system - using a parallel machine to simulate neural networks which are intrinsically parallel applications. SpiNNaker is a scalable massively-parallel computing system under development with the aim of building a general-purpose platform for the parallel simulation of large-scale neural systems. This research investigates how to model large-scale neural networks efficiently on such a parallel machine. While providing increased overall computational power, a parallel architecture introduces a new problem - the increased communication reduces the speedup gains. Modeling schemes, which take into account communication, processing, and storage requirements, are investigated to solve this problem. Since modeling schemes are application-dependent, two different types of neural network are examined - spiking neural networks with spike-time dependent plasticity, and the parallel distributed processing model with the backpropagation learning rule. Different modeling schemes are developed and evaluated for the two types of neural network. The research shows the feasibility of the approach as well as the performance of SpiNNaker as a general-purpose platform for the simulation of neural networks. The linear scalability shown in this architecture provides a path to the further development of parallel solutions for the simulation of extremely large-scale neural networks.

Von Neumann Bottleneck, which refers to the limited throughput between the CPU and memory, has already become the major factor hindering the technical advances of computing systems. In recent years, neuromorphic systems started to gain increasing attention as compact and energy-efficient computing platforms. Spike based-neuromorphic computing systems require high performance and low power neural encoder and decoder to emulate the spiking behavior of neurons. These two spike-analog signals converting interface determine the whole spiking neuromorphic computing system's performance, especially the highest performance. Many state-of-the-art neuromorphic systems typically operate in the frequency range between 〖10〗^0KHz and 〖10〗^2KHz due to the limitation of encoding/decoding speed. In this dissertation, all these popular encoding and decoding schemes, i.e. rate encoding, latency encoding, ISI encoding, together with related hardware implementations have been discussed and analyzed. The contributions included in this dissertation can be classified into three main parts: neuron improvement, three kinds of ISI encoder design, two types of ISI decoder design. Two-path leakage LIF neuron has been fabricated and modular design methodology is invented. Three kinds of ISI encoding schemes including parallel signal encoding, full signal iteration encoding, and partial signal encoding are discussed. The first two types ISI encoders have been fabricated successfully and the last ISI encoder will be taped out by the end of 2019. Two types of ISI decoders adopted different techniques which are sample-and-hold based mixed-signal design and spike-timing-dependent-plasticity (STDP) based analog design respectively. Both these two ISI encoders have been evaluated through post-layout simulations successfully. The STDP based ISI encoder will be taped out by the end of 2019. A test bench based on correlation inspection has been built to evaluate the information recovery capability of the proposed spiking processing link. / Doctor of Philosophy / Neuromorphic computing is a kind of specific electronic system that could mimic biological bodies’ behavior. In most cases, neuromorphic computing system is built with analog circuits which have benefits in power efficient and low thermal radiation. Among neuromorphic computing system, one of the most important components is the signal processing interface, i.e. encoder/decoder. To increase the whole system’s performance, novel encoders and decoders have been proposed in this dissertation. In this dissertation, three kinds of temporal encoders, one rate encoder, one latency encoder, one temporal decoder, and one general spike decoder have been proposed. These designs could be combined together to build high efficient spike-based data link which guarantee the processing performance of whole neuromorphic computing system.

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

Dans ces travaux de thèse, nous nous sommes intéressés à l'infuence du bruit synaptique sur la plasticité synaptique dans un réseau de neurones biophysiquement réalistes. Le simulateur utilisé est un système électronique neuromorphique. Nous avons implanté un modèle de neurones à conductances basé sur le formalisme de Hodgkin et Huxley, et un modèle biophysique de plasticité. Ces travaux ont inclus la configuration du système, le développement d'outils pour l'exploiter, son utilisation ainsi que la mise en place d'une plateforme le rendant accessible à la communauté scientique via Internet et l'utilisation de scripts PyNN (langage de description de simulations en neurosciences computationnelles).

Dans cette thèse je propose plusieurs mécanismes de plasticité synaptique qui pourraient expliquer la rapidité, la sélectivité et l'invariance des réponses neuronales dans le cortex visuel. Leur plausibilité biologique est discutée. J'expose également les résultats d'une expérience de psychophysique pertinente, qui montrent que la familiarité peut accélérer les traitements visuels. Au delà de ces résultats propres au système visuel, les travaux présentés ici créditent l'hypothèse de l'utilisation des dates de spikes pour encoder, décoder, et traiter l'information dans le cerveau – c'est la théorie dite du ‘codage temporel'. Dans un tel cadre, la Spike Timing Dependent Plasticity pourrait jouer un rôle clef, en détectant des patterns de spikes répétitifs et en permettant d'y répondre de plus en plus rapidement.

Recentemente observou-se experimentalmente, Johnson et al. (2010), que fatias organotípicas corticais de rato são capazes de completar padrões espaço-temporais, após serem treinadas. Embora se especule que mecanismos de plasticidade sináptica e homeostática estejam por trás do fenômeno, ainda não existe nenhuma explicação detalhada sobre o assunto. Com o intuito de propor uma explicação clara e consistente para os mecanismos que permeiam a resposta da rede aos estímulos como um todo, nos propomos a estudar este fenômeno por meio de uma rede de neurônios de integração-e-disparo dotada de mecanismos de homeostase intrínseca e de plasticidade sináptica dependente de disparos. O sistema construído foi explorado, de modo a determinar em que condições a rede poderia comportar-se como o sistema real, e treinado de forma similar `a realizada experimentalmente por Johnson et al. (2010). / Recently it has been observed experimentally, Johnson et al. (2010), that organotypic cortical slices of rat are capable of completing spatio-temporal patterns after training. Although it is speculated that synaptic and homeostatic plasticity may have an important role in this phenomenon, there is still no detailed explanation about this subject. In order to propose a clear and consistent explanation for the mechanisms that underlie the network response to stimuli as a whole, we propose to study this phenomenon through a network of integrate-and-fire neurons endowed with intrinsic homeostasis and spike-timing dependent plasticity mechanisms. The constructed system was explored, aiming to determine in which conditions the network could behave as the real system, and trained in a way similar as the experimental one done by Johnson et al. (2010).

Dans cette thèse nous tentons de donner un sens mathématique à la proposition : le néocortex se construit un modèle de son environnement. Nous considérons que le néocortex est un réseau de neurones spikants dont la connectivité est soumise à une lente évolution appelée apprentissage. Dans le cas où le nombre de neurones est proche de l'infini, nous proposons une nouvelle méthode de champ-moyen afin de trouver une équation décrivant l'évolution du taux de décharge de populations de neurones. Nous étudions donc la dynamique de ce système moyennisé avec apprentissage. Dans le régime où l'apprentissage est beaucoup plus lent que l'activité du réseau nous pouvons utiliser des outils de moyennisation temporelle pour les systèmes lents/rapides. Dans ce cadre mathématique nous montrons que la connectivité du réseau converge toujours vers une unique valeur d'équilibre que nous pouvons calculer explicitement. Cette connectivité regroupe l'ensemble des connaissances du réseau à propos de son environnement. Nous comparons cette connectivité à l'équilibre avec les stimuli du réseau. Considérant que l'environnement est solution d'un système dynamique quelconque, il est possible de montrer que le réseau encode la totalité de l'information nécessaire à la définition de ce système dynamique. En effet nous montrons que la partie symétrique de la connectivité correspond à la variété sur laquelle est définie le système dynamique de l'environnement, alors que la partie anti-symétrique de la connectivité correspond au champ de vecteur définissant le système dynamique de l'environnement. Dans ce contexte il devient clair que le réseau agit comme un prédicteur de son environnement.

Dans ces travaux de thèse, nous nous sommes intéressés à l'in fluence du bruit synaptique sur la plasticité synaptique dans un réseau de neurones biophysiquement réalistes. Le simulateur utilisé est un système électronique neuromorphique. Nous avons implanté un modèle de neurones à conductances basé sur le formalisme de Hodgkin et Huxley, et un modèle biophysique de plasticité. Ces travaux ont inclus la con figuration du système, le développement d'outils pour l'exploiter, son utilisation ainsi que la mise en place d'une plateforme le rendant accessible à la communauté scientifique via Internet et l'utilisation de scripts PyNN (langage de description de simulations en neurosciences computationnelles).

Recentemente observou-se experimentalmente, Johnson et al. (2010), que fatias organotípicas corticais de rato são capazes de completar padrões espaço-temporais, após serem treinadas. Embora se especule que mecanismos de plasticidade sináptica e homeostática estejam por trás do fenômeno, ainda não existe nenhuma explicação detalhada sobre o assunto. Com o intuito de propor uma explicação clara e consistente para os mecanismos que permeiam a resposta da rede aos estímulos como um todo, nos propomos a estudar este fenômeno por meio de uma rede de neurônios de integração-e-disparo dotada de mecanismos de homeostase intrínseca e de plasticidade sináptica dependente de disparos. O sistema construído foi explorado, de modo a determinar em que condições a rede poderia comportar-se como o sistema real, e treinado de forma similar `a realizada experimentalmente por Johnson et al. (2010). / Recently it has been observed experimentally, Johnson et al. (2010), that organotypic cortical slices of rat are capable of completing spatio-temporal patterns after training. Although it is speculated that synaptic and homeostatic plasticity may have an important role in this phenomenon, there is still no detailed explanation about this subject. In order to propose a clear and consistent explanation for the mechanisms that underlie the network response to stimuli as a whole, we propose to study this phenomenon through a network of integrate-and-fire neurons endowed with intrinsic homeostasis and spike-timing dependent plasticity mechanisms. The constructed system was explored, aiming to determine in which conditions the network could behave as the real system, and trained in a way similar as the experimental one done by Johnson et al. (2010).