Implementação em hardware de uma Rede Neuronal com ummicroprocessador embebido em FPGA

O objectivo deste trabalho é a implementação em hardware de uma Rede Neuronal com um microprocessador embebido, podendo ser um recurso valioso em várias áreas científicas. A importância das implementações em hardware deve-se à flexibilidade, maior desempenho e baixo consumo de energia. Para esta implementação foi utilizado o dispositivo FPGA Virtex II Pro XC2VP30 com um MicroBlaze soft core, da Xilinx. O MicroBlaze tem vantagens como a simplicidade no design, sua reutilização e fácil integração com outras tecnologias. A primeira fase do trabalho consistiu num estudo sobre o FPGA, um sistema reconfigurável que possui características importantes como a capacidade de executar em paralelo tarefas complexas. Em seguida, desenvolveu-se o código de implementação de uma Rede Neuronal Artificial baseado numa linguagem de programação de alto nível. Na implementação da Rede Neuronal aplicou-se, na camada escondida, a função de activação tangente hiperbólica, que serve para fornecer a não linearidade à Rede Neuronal. A implementação é feita usando um tipo de Rede Neuronal que permite apenas ligações no sentido de saída, chamado Redes Neuronais sem realimentação (do Inglês Feedforward Neural Networks - FNN). Como as Redes Neuronais Artificiais são sistemas de processamento de informações, e as suas características são comuns às Redes Neuronais Biológicas, aplicaram-se testes na implementação em hardware e analisou-se a sua importância, a sua eficiência e o seu desempenho. E finalmente, diante dos resultados, fez-se uma análise de abordagem e metodologia adoptada e sua viabilidade.

RBF circuits based on folded cascode differential pairs

We propose new circuits for the implementation of Radial Basis Functions such as Gaussian and Gaussian-like functions. These RBFs are obtained by the subtraction of two differential pair output currents in a folded cascode configuration. We also propose a multidimensional version based on the unidimensional circuits. SPICE simulation results indicate good functionality. These circuits are intended to be applied in the implementation of radial basis function networks. One possible application of these networks is transducer signal conditioning in aircraft and spacecraft vehicles onboard telemetry systems. Copyright 2008 ACM.

Modeling the shape hierarchy for visually guided grasping

The monkey anterior intraparietal area (AIP) encodes visual information about three-dimensional object shape that is used to shape the hand for grasping. We modeled shape tuning in visual AIP neurons and its relationship with curvature and gradient information from the caudal intraparietal area (CIP). The main goal was to gain insight into the kinds of shape parameterizations that can account for AIP tuning and that are consistent with both the inputs to AIP and the role of AIP in grasping. We first experimented with superquadric shape parameters. We considered superquadrics because they occupy a role in robotics that is similar to AIP , in that superquadric fits are derived from visual input and used for grasp planning. We also experimented with an alternative shape parameterization that was based on an Isomap dimension reduction of spatial derivatives of depth (i.e., distance from the observer to the object surface). We considered an Isomap-based model because its parameters lacked discontinuities between similar shapes. When we matched the dimension of the Isomap to the number of superquadric parameters, the superquadric model fit the AIP data somewhat more closely. However, higher-dimensional Isomaps provided excellent fits. Also, we found that the Isomap parameters could be approximated much more accurately than superquadric parameters by feedforward neural networks with CIP-like inputs. We conclude that Isomaps, or perhaps alternative dimension reductions of visual inputs to AIP, provide a promising model of AIP electrophysiology data. Further work is needed to test whether such shape parameterizations actually provide an effective basis for grasp control.

Functional, clustered, feedforward, and mesoscale brain networks

The brain is a network spanning multiple scales from subcellular to macroscopic. In this thesis I present four projects studying brain networks at different levels of abstraction. The first involves determining a functional connectivity network based on neural spike trains and using a graph theoretical method to cluster groups of neurons into putative cell assemblies. In the second project I model neural networks at a microscopic level. Using diferent clustered wiring schemes, I show that almost identical spatiotemporal activity patterns can be observed, demonstrating that there is a broad neuro-architectural basis to attain structured spatiotemporal dynamics. Remarkably, irrespective of the precise topological mechanism, this behavior can be predicted by examining the spectral properties of the synaptic weight matrix. The third project introduces, via two circuit architectures, a new paradigm for feedforward processing in which inhibitory neurons have the complex and pivotal role in governing information flow in cortical network models. Finally, I analyze axonal projections in sleep deprived mice using data collected as part of the Allen Institute's Mesoscopic Connectivity Atlas. After normalizing for experimental variability, the results indicate there is no single explanatory difference in the mesoscale network between control and sleep deprived mice. Using machine learning techniques, however, animal classification could be done at levels significantly above chance. This reveals that intricate changes in connectivity do occur due to chronic sleep deprivation.

Development and evaluation of neural network freeway incident detection models using field data

This paper discusses a multi-layer feedforward (MLF) neural network incident detection model that was developed and evaluated using field data. In contrast to published neural network incident detection models which relied on simulated or limited field data for model development and testing, the model described in this paper was trained and tested on a real-world data set of 100 incidents. The model uses speed, flow and occupancy data measured at dual stations, averaged across all lanes and only from time interval t. The off-line performance of the model is reported under both incident and non-incident conditions. The incident detection performance of the model is reported based on a validation-test data set of 40 incidents that were independent of the 60 incidents used for training. The false alarm rates of the model are evaluated based on non-incident data that were collected from a freeway section which was video-taped for a period of 33 days. A comparative evaluation between the neural network model and the incident detection model in operation on Melbourne's freeways is also presented. The results of the comparative performance evaluation clearly demonstrate the substantial improvement in incident detection performance obtained by the neural network model. The paper also presents additional results that demonstrate how improvements in model performance can be achieved using variable decision thresholds. Finally, the model's fault-tolerance under conditions of corrupt or missing data is investigated and the impact of loop detector failure/malfunction on the performance of the trained model is evaluated and discussed. The results presented in this paper provide a comprehensive evaluation of the developed model and confirm that neural network models can provide fast and reliable incident detection on freeways. (C) 1997 Elsevier Science Ltd. All rights reserved.

Volatility smile extrapolation with an artificial neural network

I use a multi-layer feedforward perceptron, with backpropagation learning implemented via stochastic gradient descent, to extrapolate the volatility smile of Euribor derivatives over low-strikes by training the network on parametric prices.

A reconfigurable neural environment on active networks

This paper proposes the deployment of a neural network computing environment on Active Networks. Active Networks are packet-switched computer networks in which packets can contain code fragments that are executed on the intermediate nodes. This feature allows the injection of small pieces of codes to deal with computer network problems directly into the network core, and the adoption of new computing techniques to solve networking problems. The goal of our project is the adoption of a distributed neural network for approaching tasks which are specific of the computer network environment. Dynamically reconfigurable neural networks are spread on an experimental wide area backbone of active nodes (ABone) to show the feasibility of the proposed approach.

Análise de desempenho da rede neural artificial do tipo multilayer perceptron na era multicore

Artificial neural networks are usually applied to solve complex problems. In problems with more complexity, by increasing the number of layers and neurons, it is possible to achieve greater functional efficiency. Nevertheless, this leads to a greater computational effort. The response time is an important factor in the decision to use neural networks in some systems. Many argue that the computational cost is higher in the training period. However, this phase is held only once. Once the network trained, it is necessary to use the existing computational resources efficiently. In the multicore era, the problem boils down to efficient use of all available processing cores. However, it is necessary to consider the overhead of parallel computing. In this sense, this paper proposes a modular structure that proved to be more suitable for parallel implementations. It is proposed to parallelize the feedforward process of an RNA-type MLP, implemented with OpenMP on a shared memory computer architecture. The research consistes on testing and analizing execution times. Speedup, efficiency and parallel scalability are analyzed. In the proposed approach, by reducing the number of connections between remote neurons, the response time of the network decreases and, consequently, so does the total execution time. The time required for communication and synchronization is directly linked to the number of remote neurons in the network, and so it is necessary to investigate which one is the best distribution of remote connections

Identificação automática das primeiras quebras em traços sísmicos por meio de uma rede neural direta

Apesar do avanço tecnológico ocorrido na prospecção sísmica, com a rotina dos levantamentos 2D e 3D, e o significativo aumento na quantidade de dados, a identificação dos tempos de chegada da onda sísmica direta (primeira quebra), que se propaga diretamente do ponto de tiro até a posição dos arranjos de geofones, permanece ainda dependente da avaliação visual do intérprete sísmico. O objetivo desta dissertação, insere-se no processamento sísmico com o intuito de buscar um método eficiente, tal que possibilite a simulação computacional do comportamento visual do intérprete sísmico, através da automação dos processos de tomada de decisão envolvidos na identificação das primeiras quebras em um traço sísmico. Visando, em última análise, preservar o conhecimento intuitivo do intérprete para os casos complexos, nos quais o seu conhecimento será, efetivamente, melhor aproveitado. Recentes descobertas na tecnologia neurocomputacional produziram técnicas que possibilitam a simulação dos aspectos qualitativos envolvidos nos processos visuais de identificação ou interpretação sísmica, com qualidade e aceitabilidade dos resultados. As redes neurais artificiais são uma implementação da tecnologia neurocomputacional e foram, inicialmente, desenvolvidas por neurobiologistas como modelos computacionais do sistema nervoso humano. Elas diferem das técnicas computacionais convencionais pela sua habilidade em adaptar-se ou aprender através de uma repetitiva exposição a exemplos, pela sua tolerância à falta de alguns dos componentes dos dados e pela sua robustez no tratamento com dados contaminados por ruído. O método aqui apresentado baseia-se na aplicação da técnica das redes neurais artificiais para a identificação das primeiras quebras nos traços sísmicos, a partir do estabelecimento de uma conveniente arquitetura para a rede neural artificial do tipo direta, treinada com o algoritmo da retro-propagação do erro. A rede neural artificial é entendida aqui como uma simulação computacional do processo intuitivo de tomada de decisão realizado pelo intérprete sísmico para a identificação das primeiras quebras nos traços sísmicos. A aplicabilidade, eficiência e limitações desta abordagem serão avaliadas em dados sintéticos obtidos a partir da teoria do raio.

Contribuições na modelagem dinâmica e no controle neural de um braço robótico com elos flexíveis

Em geral, estruturas espaciais e manipuladores robóticos leves têm uma característica similar e inerente que é a flexibilidade. Esta característica torna a dinâmica do sistema muito mais complexa e com maiores dificuldades para a análise de estabilidade e controle. Então, braços robóticos bastantes leves, com velocidade elevada e potencia limitada devem considerar o controle de vibração causada pela flexibilidade. Por este motivo, uma estratégia de controle é desejada não somente para o controle do modo rígido mas também que seja capaz de controlar os modos de vibração do braço robótico flexível. Também, redes neurais artificiais (RNA) são identificadas como uma subespecialidade de inteligência artificial. Constituem atualmente uma teoria para o estudo de fenômenos complexos e representam uma nova ferramenta na tecnologia de processamento de informação, por possuírem características como processamento paralelo, capacidade de aprendizagem, mapeamento não-linear e capacidade de generalização. Assim, neste estudo utilizam-se RNA na identificação e controle do braço robótico com elos flexíveis. Esta tese apresenta a modelagem dinâmica de braços robóticos com elos flexíveis, 1D no plano horizontal e 2D no plano vertical com ação da gravidade, respectivamente. Modelos dinâmicos reduzidos são obtidos pelo formalismo de Newton-Euler, e utiliza-se o método dos elementos finitos (MEF) na discretização dos deslocamentos elásticos baseado na teoria elementar da viga. Além disso, duas estratégias de controle têm sido desenvolvidas com a finalidade de eliminar as vibrações devido à flexibilidade do braço robótico com elos flexíveis. Primeiro, utilizase um controlador neural feedforward (NFF) na obtenção da dinâmica inversa do braço robótico flexível e o calculo do torque da junta. E segundo, para obter precisão no posicionamento... (Resumo completo, clicar acesso eletrônico abaixo)

Enhancing weak signal transmission through a feedforward network

The ability to transmit and amplify weak signals is fundamental to signal processing of artificial devices in engineering. Using a multilayer feedforward network of coupled double-well oscillators as well as Fitzhugh-Nagumo oscillators, we here investigate the conditions under which a weak signal received by the first layer can be transmitted through the network with or without amplitude attenuation. We find that the coupling strength and the nodes' states of the first layer act as two-state switches, which determine whether the transmission is significantly enhanced or exponentially decreased. We hope this finding is useful for designing artificial signal amplifiers.

The time dimension of neural network models

This review attempts to provide an insightful perspective on the role of time within neural network models and the use of neural networks for problems involving time. The most commonly used neural network models are defined and explained giving mention to important technical issues but avoiding great detail. The relationship between recurrent and feedforward networks is emphasised, along with the distinctions in their practical and theoretical abilities. Some practical examples are discussed to illustrate the major issues concerning the application of neural networks to data with various types of temporal structure, and finally some highlights of current research on the more difficult types of problems are presented.

Neural Network Based Optimal Control with Constraints

In the present paper the problems of the optimal control of systems when constraints are imposed on the control is considered. The optimality conditions are given in the form of Pontryagin’s maximum principle. The obtained piecewise linear function is approximated by using feedforward neural network. A numerical example is given.

Neural Approach in Multi-Agent Routing for Static Telecommunication Networks

The problem of multi-agent routing in static telecommunication networks with fixed configuration is considered. The problem is formulated in two ways: for centralized routing schema with the coordinator-agent (global routing) and for distributed routing schema with independent agents (local routing). For both schemas appropriate Hopfield neural networks (HNN) are constructed.