886 resultados para Hierarchical neural networks


Relevância:

90.00% 90.00%

Publicador:

Resumo:

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.

Relevância:

90.00% 90.00%

Publicador:

Resumo:

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.

Relevância:

90.00% 90.00%

Publicador:

Resumo:

In this dissertation, different ways of combining neural predictive models or neural-based forecasts are discussed. The proposed approaches consider mostly Gaussian radial basis function networks, which can be efficiently identified and estimated through recursive/adaptive methods. Two different ways of combining are explored to get a final estimate – model mixing and model synthesis –, with the aim of obtaining improvements both in terms of efficiency and effectiveness. In the context of model mixing, the usual framework for linearly combining estimates from different models is extended, to deal with the case where the forecast errors from those models are correlated. In the context of model synthesis, and to address the problems raised by heavily nonstationary time series, we propose hybrid dynamic models for more advanced time series forecasting, composed of a dynamic trend regressive model (or, even, a dynamic harmonic regressive model), and a Gaussian radial basis function network. Additionally, using the model mixing procedure, two approaches for decision-making from forecasting models are discussed and compared: either inferring decisions from combined predictive estimates, or combining prescriptive solutions derived from different forecasting models. Finally, the application of some of the models and methods proposed previously is illustrated with two case studies, based on time series from finance and from tourism.

Relevância:

90.00% 90.00%

Publicador:

Resumo:

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Relevância:

90.00% 90.00%

Publicador:

Resumo:

On this paper, it is made a comparative analysis among a controller fuzzy coupled to a PID neural adjusted by an AGwith several traditional control techniques, all of them applied in a system of tanks (I model of 2nd order non lineal). With the objective of making possible the techniques involved in the comparative analysis and to validate the control to be compared, simulations were accomplished of some control techniques (conventional PID adjusted by GA, Neural PID (PIDN) adjusted by GA, Fuzzy PI, two Fuzzy attached to a PID Neural adjusted by GA and Fuzzy MISO (3 inputs) attached to a PIDN adjusted by GA) to have some comparative effects with the considered controller. After doing, all the tests, some control structures were elected from all the tested techniques on the simulating stage (conventional PID adjusted by GA, Fuzzy PI, two Fuzzy attached to a PIDN adjusted by GA and Fuzzy MISO (3 inputs) attached to a PIDN adjusted by GA), to be implemented at the real system of tanks. These two kinds of operation, both the simulated and the real, were very important to achieve a solid basement in order to establish the comparisons and the possible validations show by the results

Relevância:

90.00% 90.00%

Publicador:

Resumo:

In last decades, neural networks have been established as a major tool for the identification of nonlinear systems. Among the various types of networks used in identification, one that can be highlighted is the wavelet neural network (WNN). This network combines the characteristics of wavelet multiresolution theory with learning ability and generalization of neural networks usually, providing more accurate models than those ones obtained by traditional networks. An extension of WNN networks is to combine the neuro-fuzzy ANFIS (Adaptive Network Based Fuzzy Inference System) structure with wavelets, leading to generate the Fuzzy Wavelet Neural Network - FWNN structure. This network is very similar to ANFIS networks, with the difference that traditional polynomials present in consequent of this network are replaced by WNN networks. This paper proposes the identification of nonlinear dynamical systems from a network FWNN modified. In the proposed structure, functions only wavelets are used in the consequent. Thus, it is possible to obtain a simplification of the structure, reducing the number of adjustable parameters of the network. To evaluate the performance of network FWNN with this modification, an analysis of network performance is made, verifying advantages, disadvantages and cost effectiveness when compared to other existing FWNN structures in literature. The evaluations are carried out via the identification of two simulated systems traditionally found in the literature and a real nonlinear system, consisting of a nonlinear multi section tank. Finally, the network is used to infer values of temperature and humidity inside of a neonatal incubator. The execution of such analyzes is based on various criteria, like: mean squared error, number of training epochs, number of adjustable parameters, the variation of the mean square error, among others. The results found show the generalization ability of the modified structure, despite the simplification performed

Relevância:

90.00% 90.00%

Publicador:

Resumo:

ln this work the implementation of the SOM (Self Organizing Maps) algorithm or Kohonen neural network is presented in the form of hierarchical structures, applied to the compression of images. The main objective of this approach is to develop an Hierarchical SOM algorithm with static structure and another one with dynamic structure to generate codebooks (books of codes) in the process of the image Vector Quantization (VQ), reducing the time of processing and obtaining a good rate of compression of images with a minimum degradation of the quality in relation to the original image. Both self-organizing neural networks developed here, were denominated HSOM, for static case, and DHSOM, for the dynamic case. ln the first form, the hierarchical structure is previously defined and in the later this structure grows in an automatic way in agreement with heuristic rules that explore the data of the training group without use of external parameters. For the network, the heuristic mIes determine the dynamics of growth, the pruning of ramifications criteria, the flexibility and the size of children maps. The LBO (Linde-Buzo-Oray) algorithm or K-means, one ofthe more used algorithms to develop codebook for Vector Quantization, was used together with the algorithm of Kohonen in its basic form, that is, not hierarchical, as a reference to compare the performance of the algorithms here proposed. A performance analysis between the two hierarchical structures is also accomplished in this work. The efficiency of the proposed processing is verified by the reduction in the complexity computational compared to the traditional algorithms, as well as, through the quantitative analysis of the images reconstructed in function of the parameters: (PSNR) peak signal-to-noise ratio and (MSE) medium squared error

Relevância:

90.00% 90.00%

Publicador:

Resumo:

This study aims to seek a more viable alternative for the calculation of differences in images of stereo vision, using a factor that reduces heel the amount of points that are considered on the captured image, and a network neural-based radial basis functions to interpolate the results. The objective to be achieved is to produce an approximate picture of disparities using algorithms with low computational cost, unlike the classical algorithms

Relevância:

90.00% 90.00%

Publicador:

Resumo:

This study shows the implementation and the embedding of an Artificial Neural Network (ANN) in hardware, or in a programmable device, as a field programmable gate array (FPGA). This work allowed the exploration of different implementations, described in VHDL, of multilayer perceptrons ANN. Due to the parallelism inherent to ANNs, there are disadvantages in software implementations due to the sequential nature of the Von Neumann architectures. As an alternative to this problem, there is a hardware implementation that allows to exploit all the parallelism implicit in this model. Currently, there is an increase in use of FPGAs as a platform to implement neural networks in hardware, exploiting the high processing power, low cost, ease of programming and ability to reconfigure the circuit, allowing the network to adapt to different applications. Given this context, the aim is to develop arrays of neural networks in hardware, a flexible architecture, in which it is possible to add or remove neurons, and mainly, modify the network topology, in order to enable a modular network of fixed-point arithmetic in a FPGA. Five synthesis of VHDL descriptions were produced: two for the neuron with one or two entrances, and three different architectures of ANN. The descriptions of the used architectures became very modular, easily allowing the increase or decrease of the number of neurons. As a result, some complete neural networks were implemented in FPGA, in fixed-point arithmetic, with a high-capacity parallel processing

Relevância:

90.00% 90.00%

Publicador:

Resumo:

This work presents an analysis of the control law based on an indirect hybrid scheme using neural network, initially proposed for O. Adetona, S. Sathanathan and L. H. Keel. Implementations of this control law, for a level plant of second order, was resulted an oscillatory behavior, even if the neural identifier has converged. Such results had motivated the investigation of the applicability of that law. Starting from that, had been made stability mathematical analysis and several implementations, with simulated plants and with real plants, for analyze the problem. The analysis has been showed the law was designed being despised some components of dynamic of the plant to be controlled. Thus, for plants that these components have a significant influence in its dynamic, the law tends to fail

Relevância:

90.00% 90.00%

Publicador:

Resumo:

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

Relevância:

90.00% 90.00%

Publicador:

Resumo:

Nowadays, optic fiber is one of the most used communication methods, mainly due to the fact that the data transmission rates of those systems exceed all of the other means of digital communication. Despite the great advantage, there are problems that prevent full utilization of the optical channel: by increasing the transmission speed and the distances involved, the data is subjected to non-linear inter symbolic interference caused by the dispersion phenomena in the fiber. Adaptive equalizers can be used to solve this problem, they compensate non-ideal responses of the channel in order to restore the signal that was transmitted. This work proposes an equalizer based on artificial neural networks and evaluates its performance in optical communication systems. The proposal is validated through a simulated optic channel and the comparison with other adaptive equalization techniques

Relevância:

90.00% 90.00%

Publicador:

Resumo:

One of the current major concerns in engineering is the development of aircrafts that have low power consumption and high performance. So, airfoils that have a high value of Lift Coefficient and a low value for the Drag Coefficient, generating a High-Efficiency airfoil are studied and designed. When the value of the Efficiency increases, the aircraft s fuel consumption decreases, thus improving its performance. Therefore, this work aims to develop a tool for designing of airfoils from desired characteristics, as Lift and Drag coefficients and the maximum Efficiency, using an algorithm based on an Artificial Neural Network (ANN). For this, it was initially collected an aerodynamic characteristics database, with a total of 300 airfoils, from the software XFoil. Then, through the software MATLAB, several network architectures were trained, between modular and hierarchical, using the Back-propagation algorithm and the Momentum rule. For data analysis, was used the technique of cross- validation, evaluating the network that has the lowest value of Root Mean Square (RMS). In this case, the best result was obtained for a hierarchical architecture with two modules and one layer of hidden neurons. The airfoils developed for that network, in the regions of lower RMS, were compared with the same airfoils imported into the software XFoil