Dealing with complexity: an overview of the neural network approach

The problem of complexity is particularly relevant to the field of control engineering, since many engineering problems are inherently complex. The inherent complexity is such that straightforward computational problem solutions often produce very poor results. Although parallel processing can alleviate the problem to some extent, it is artificial neural networks (in various forms) which have recently proved particularly effective, even in dealing with the causes of the problem itself. This paper presents an overview of the current neural network research being undertaken. Such research aims to solve the complex problems found in many areas of science and engineering today.

Multi-layer radial basis function networks: an extension to the radial basis function

This paper presents the initial research carried out into a new neural network called the multilayer radial basis function network (MRBF). The network extends the radial basis function (RBF) in a similar way to that in which the multilayer perceptron extends the perceptron. It is hoped that by connecting RBFs together in a layered fashion, an equivalent increase in ability can be gained, as is gained from using MLPs instead of single perceptrons. The results of a practical comparison between individual RBFs and MRBF's are also given.

Identification of nonlinear systems with a dynamic recurrent neural network

Two approaches are presented to calculate the weights for a Dynamic Recurrent Neural Network (DRNN) in order to identify the input-output dynamics of a class of nonlinear systems. The number of states of the identified network is constrained to be the same as the number of states of the plant.

Relative order defines a topology for recurrent networks

This paper uses techniques from control theory in the analysis of trained recurrent neural networks. Differential geometry is used as a framework, which allows the concept of relative order to be applied to neural networks. Any system possessing finite relative order has a left-inverse. Any recurrent network with finite relative order also has an inverse, which is shown to be a recurrent network.

Modular non-computational-connectionist-hybrid neural network approach to robotic systems

Spiking neural networks are usually limited in their applications due to their complex mathematical models and the lack of intuitive learning algorithms. In this paper, a simpler, novel neural network derived from a leaky integrate and fire neuron model, the ‘cavalcade’ neuron, is presented. A simulation for the neural network has been developed and two basic learning algorithms implemented within the environment. These algorithms successfully learn some basic temporal and instantaneous problems. Inspiration for neural network structures from these experiments are then taken and applied to process sensor information so as to successfully control a mobile robot.

NeMo: a platform for neural modelling of spiking neurons using GPUs

Simulating spiking neural networks is of great interest to scientists wanting to model the functioning of the brain. However, large-scale models are expensive to simulate due to the number and interconnectedness of neurons in the brain. Furthermore, where such simulations are used in an embodied setting, the simulation must be real-time in order to be useful. In this paper we present NeMo, a platform for such simulations which achieves high performance through the use of highly parallel commodity hardware in the form of graphics processing units (GPUs). NeMo makes use of the Izhikevich neuron model which provides a range of realistic spiking dynamics while being computationally efficient. Our GPU kernel can deliver up to 400 million spikes per second. This corresponds to a real-time simulation of around 40 000 neurons under biologically plausible conditions with 1000 synapses per neuron and a mean firing rate of 10 Hz.

Mind wandering away from pain dynamically engages antinociceptive and default mode brain networks

Human minds often wander away from their immediate sensory environment. It remains unknown whether such mind wandering is unsystematic or whether it lawfully relates to an individual’s tendency to attend to salient stimuli such as pain and their associated brain structure/function. Studies of pain–cognition interactions typically examine explicit manipulation of attention rather than spontaneous mind wandering. Here we sought to better represent natural fluctuations in pain in daily life, so we assessed behavioral and neural aspects of spontaneous disengagement of attention from pain. We found that an individual’s tendency to attend to pain related to the disruptive effect of pain on his or her cognitive task performance. Next, we linked behavioral findings to neural networks with strikingly convergent evidence from functional magnetic resonance imaging during pain coupled with thought probes of mind wandering, dynamic resting state activity fluctuations, and diffusion MRI. We found that (i) pain-induced default mode network (DMN) deactivations were attenuated during mind wandering away from pain; (ii) functional connectivity fluctuations between the DMN and periaqueductal gray (PAG) dynamically tracked spontaneous attention away from pain; and (iii) across individuals, stronger PAG–DMN structural connectivity and more dynamic resting state PAG–DMN functional connectivity were associated with the tendency to mind wander away from pain. These data demonstrate that individual tendencies to mind wander away from pain, in the absence of explicit manipulation, are subserved by functional and structural connectivity within and between default mode and antinociceptive descending modulation networks.

B-spline neural network based single-carrier frequency domain equalisation for Hammerstein channels

A practical single-carrier (SC) block transmission with frequency domain equalisation (FDE) system can generally be modelled by the Hammerstein system that includes the nonlinear distortion effects of the high power amplifier (HPA) at transmitter. For such Hammerstein channels, the standard SC-FDE scheme no longer works. We propose a novel Bspline neural network based nonlinear SC-FDE scheme for Hammerstein channels. In particular, we model the nonlinear HPA, which represents the complex-valued static nonlinearity of the Hammerstein channel, by two real-valued B-spline neural networks, one for modelling the nonlinear amplitude response of the HPA and the other for the nonlinear phase response of the HPA. We then develop an efficient alternating least squares algorithm for estimating the parameters of the Hammerstein channel, including the channel impulse response coefficients and the parameters of the two B-spline models. Moreover, we also use another real-valued B-spline neural network to model the inversion of the HPA’s nonlinear amplitude response, and the parameters of this inverting B-spline model can be estimated using the standard least squares algorithm based on the pseudo training data obtained as a byproduct of the Hammerstein channel identification. Equalisation of the SC Hammerstein channel can then be accomplished by the usual one-tap linear equalisation in frequency domain as well as the inverse Bspline neural network model obtained in time domain. The effectiveness of our nonlinear SC-FDE scheme for Hammerstein channels is demonstrated in a simulation study.

Entropy-Based Approach to Analyze and Classify Mineral Aggregates

This paper presents an automatic method to detect and classify weathered aggregates by assessing changes of colors and textures. The method allows the extraction of aggregate features from images and the automatic classification of them based on surface characteristics. The concept of entropy is used to extract features from digital images. An analysis of the use of this concept is presented and two classification approaches, based on neural networks architectures, are proposed. The classification performance of the proposed approaches is compared to the results obtained by other algorithms (commonly considered for classification purposes). The obtained results confirm that the presented method strongly supports the detection of weathered aggregates.

Inference From Aging Information

For many learning tasks the duration of the data collection can be greater than the time scale for changes of the underlying data distribution. The question we ask is how to include the information that data are aging. Ad hoc methods to achieve this include the use of validity windows that prevent the learning machine from making inferences based on old data. This introduces the problem of how to define the size of validity windows. In this brief, a new adaptive Bayesian inspired algorithm is presented for learning drifting concepts. It uses the analogy of validity windows in an adaptive Bayesian way to incorporate changes in the data distribution over time. We apply a theoretical approach based on information geometry to the classification problem and measure its performance in simulations. The uncertainty about the appropriate size of the memory windows is dealt with in a Bayesian manner by integrating over the distribution of the adaptive window size. Thus, the posterior distribution of the weights may develop algebraic tails. The learning algorithm results from tracking the mean and variance of the posterior distribution of the weights. It was found that the algebraic tails of this posterior distribution give the learning algorithm the ability to cope with an evolving environment by permitting the escape from local traps.

Cross-situational learning of object-word mapping using Neural Modeling Fields

The issue of how children learn the meaning of words is fundamental to developmental psychology. The recent attempts to develop or evolve efficient communication protocols among interacting robots or Virtual agents have brought that issue to a central place in more applied research fields, such as computational linguistics and neural networks, as well. An attractive approach to learning an object-word mapping is the so-called cross-situational learning. This learning scenario is based on the intuitive notion that a learner can determine the meaning of a word by finding something in common across all observed uses of that word. Here we show how the deterministic Neural Modeling Fields (NMF) categorization mechanism can be used by the learner as an efficient algorithm to infer the correct object-word mapping. To achieve that we first reduce the original on-line learning problem to a batch learning problem where the inputs to the NMF mechanism are all possible object-word associations that Could be inferred from the cross-situational learning scenario. Since many of those associations are incorrect, they are considered as clutter or noise and discarded automatically by a clutter detector model included in our NMF implementation. With these two key ingredients - batch learning and clutter detection - the NMF mechanism was capable to infer perfectly the correct object-word mapping. (C) 2009 Elsevier Ltd. All rights reserved.

How language can help discrimination in the Neural Modelling Fields framework

The relationship between thought and language and, in particular, the issue of whether and how language influences thought is still a matter of fierce debate. Here we consider a discrimination task scenario to study language acquisition in which an agent receives linguistic input from an external teacher, in addition to sensory stimuli from the objects that exemplify the overlapping categories that make up the environment. Sensory and linguistic input signals are fused using the Neural Modelling Fields (NMF) categorization algorithm. We find that the agent with language is capable of differentiating object features that it could not distinguish without language. In this sense, the linguistic stimuli prompt the agent to redefine and refine the discrimination capacity of its sensory channels. (C) 2007 Elsevier Ltd. All rights reserved.

A multi-GPU algorithm for large-scale neuronal networks

Large-scale simulations of parts of the brain using detailed neuronal models to improve our understanding of brain functions are becoming a reality with the usage of supercomputers and large clusters. However, the high acquisition and maintenance cost of these computers, including the physical space, air conditioning, and electrical power, limits the number of simulations of this kind that scientists can perform. Modern commodity graphical cards, based on the CUDA platform, contain graphical processing units (GPUs) composed of hundreds of processors that can simultaneously execute thousands of threads and thus constitute a low-cost solution for many high-performance computing applications. In this work, we present a CUDA algorithm that enables the execution, on multiple GPUs, of simulations of large-scale networks composed of biologically realistic Hodgkin-Huxley neurons. The algorithm represents each neuron as a CUDA thread, which solves the set of coupled differential equations that model each neuron. Communication among neurons located in different GPUs is coordinated by the CPU. We obtained speedups of 40 for the simulation of 200k neurons that received random external input and speedups of 9 for a network with 200k neurons and 20M neuronal connections, in a single computer with two graphic boards with two GPUs each, when compared with a modern quad-core CPU. Copyright (C) 2010 John Wiley & Sons, Ltd.

Técnicas de avaliação da confiabilidade em estruturas de concreto armado

Neste trabalho é dado ênfase à inclusão das incertezas na avaliação do comportamento estrutural, objetivando uma melhor representação das características do sistema e uma quantificação do significado destas incertezas no projeto. São feitas comparações entre as técnicas clássicas existentes de análise de confiabilidade, tais como FORM, Simulação Direta Monte Carlo (MC) e Simulação Monte Carlo com Amostragem por Importância Adaptativa (MCIS), e os métodos aproximados da Superfície de Resposta( RS) e de Redes Neurais Artificiais(ANN). Quando possível, as comparações são feitas salientando- se as vantagens e inconvenientes do uso de uma ou de outra técnica em problemas com complexidades crescentes. São analisadas desde formulações com funções de estado limite explícitas até formulações implícitas com variabilidade espacial de carregamento e propriedades dos materiais, incluindo campos estocásticos. É tratado, em especial, o problema da análise da confiabilidade de estruturas de concreto armado incluindo o efeito da variabilidade espacial de suas propriedades. Para tanto é proposto um modelo de elementos finitos para a representação do concreto armado que incorpora as principais características observadas neste material. Também foi desenvolvido um modelo para a geração de campos estocásticos multidimensionais não Gaussianos para as propriedades do material e que é independente da malha de elementos finitos, assim como implementadas técnicas para aceleração das avaliações estruturais presentes em qualquer das técnicas empregadas. Para o tratamento da confiabilidade através da técnica da Superfície de Resposta, o algoritmo desenvolvido por Rajashekhar et al(1993) foi implementado. Já para o tratamento através de Redes Neurais Artificias, foram desenvolvidos alguns códigos para a simulação de redes percéptron multicamada e redes com função de base radial e então implementados no algoritmo de avaliação de confiabilidade desenvolvido por Shao et al(1997). Em geral, observou-se que as técnicas de simulação tem desempenho bastante baixo em problemas mais complexos, sobressaindo-se a técnica de primeira ordem FORM e as técnicas aproximadas da Superfície de Resposta e de Redes Neurais Artificiais, embora com precisão prejudicada devido às aproximações presentes.