By Topic

Neural Networks, 1998. Proceedings. Vth Brazilian Symposium on

Date 9-11 Dec. 1998

Filter Results

Displaying Results 1 - 25 of 48
  • Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)

    Publication Year: 1998
    Request permission for commercial reuse | PDF file iconPDF (219 KB)
    Freely Available from IEEE
  • Index of authors

    Publication Year: 1998, Page(s): 261
    Request permission for commercial reuse | PDF file iconPDF (150 KB)
    Freely Available from IEEE
  • Implementation of a probabilistic neural network for multi-spectral image classification on an FPGA based custom computing machine

    Publication Year: 1998, Page(s):174 - 179
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (108 KB)

    As the demand for higher performance computers for the processing of remote sensing science algorithms increases, the need to investigate new computing paradigms is justified. Field programmable gate arrays (FPGA) enable the implementation of algorithms at the hardware gate level, leading to orders of magnitude performance increase over microprocessor based systems. The automatic classification of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised neural network learning for blind sources separation

    Publication Year: 1998, Page(s):30 - 38
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2336 KB)

    Review of independent component analyses (ICA) and blind sources separation (BSS) employing in terms of unsupervised neural networks technology are given. For example, imagery features occurring in human visual systems are the continuing reduction of redundancy towards the “sparse edge maps”. When edges are multiplying together as the vector inner product they result in almost zero, na... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A realistic computer simulation of primary somatosensory cortex replicating static properties of topographic organization

    Publication Year: 1998, Page(s):169 - 173
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (308 KB)

    A model of the somatosensory system has been constructed with the neuro-simulator GENESIS as a network of 1,024 pyramidal cells and 512 baskets cells connected to 512 tactile receptors representing the hand surface reproducing processes of formation and maintenance of somatotopic maps. The model presents results such as variability in the shapes and sizes of the areas of cortical representation, v... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neo-fuzzy-neuron with real time training applied to flux observer for an induction motor

    Publication Year: 1998, Page(s):67 - 72
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    Presents an alternative algorithm for induction machines rotor flux observation. The novel procedure is based on a neo-fuzzy-neuron (NFN) with real time training. The main characteristics of this novel observer are: quick and accurate convergence and adaptability to system dynamics, requiring only the stator current measurements. The fuzzy-neural network employed here does not require previous tra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimising the widths of radial basis functions

    Publication Year: 1998, Page(s):26 - 29
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (204 KB)

    In the context of regression analysis with penalised linear models (such as RBF networks) certain model selection criteria can be differentiated to yield a re-estimation formula for the regularisation parameter such that an initial guess can be iteratively improved until a local minimum of the criterion is reached. In this paper we discuss some enhancements of this general approach including impro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Convergence in a sparse distributed memory

    Publication Year: 1998, Page(s):165 - 168
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (64 KB)

    A method for converging in the sparse distribution memory, utilizing the Jaeckel activation mechanism, is presented. This is done by identifying the possible errors in the address View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An isolated word speech recognition system based on Kohonen neural network

    Publication Year: 1998, Page(s):151 - 156
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (92 KB)

    Describes a non-uniform segmentation algorithm based on a Kohonen neural network applied to an isolated word recognition system. This procedure realizes a temporal normalization and the resulting fixed number of acoustic vectors is then submitted to a multilayer perceptron network in order to recognize the spoken words View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving reinforcement learning control via online bilinear action interpolation

    Publication Year: 1998, Page(s):102 - 105
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (80 KB)

    Reinforcement learning has been used as a reasonably successful method for the problem of model-free learning of action policies for some control problems. However, it is usually assumed that the process to be controlled is either open loop stable or of slow dynamics, when frequency of failures before acceptable performance or input-output processing time are not issues of primary importance. We c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An adaptive neural fuzzy network model for seasonal stream flow forecasting

    Publication Year: 1998, Page(s):215 - 219
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (128 KB)

    This paper presents an adaptive neural fuzzy network model for seasonal stream flow forecasting. The model is based on a constructive learning method that adds neurons to the network structure whenever new knowledge is necessary so that it learns the fuzzy rules and membership functions essential for modeling a fuzzy system. The model was implemented to forecast monthly average inflow on an one-st... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extracting rules from feedforward Boolean neural networks

    Publication Year: 1998, Page(s):61 - 66
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (180 KB)

    A method to extract rules from a feedforward Boolean neural networks (BNN) is described. We argue that rule extraction in BNN is more feasible and more natural than in other artificial neural networks models. This technique allows the understanding of how the neural networks reach a solution of a problem. A straight forward application of rule extraction from neural networks is the design of exper... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learnability in sequential RAM-based neural networks

    Publication Year: 1998, Page(s):20 - 25
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (76 KB)

    It is well known that, in a broad sense, recurrent neural networks are equivalent to Turing machines. However, in general, such computational power has not been achieved by the current learning algorithms. In this paper, the learning capability of the existing algorithms for sequential RAM-based neural networks is analysed. These learning algorithms are proved to have limitations which prevent the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Factor semantics for document retrieval

    Publication Year: 1998, Page(s):198 - 203
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (124 KB)

    Principal component analysis is a useful technique for reducing the dimensionality of datasets, a paramount need in high dimensional term spaces. We study three neural networks with Hebbian-like learning that approximately produce the principal components of a document database. The explained variance of the solutions shows how much information the reduced space retains. In this database the first... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Some results on activation and scaling of sparse distributed memory

    Publication Year: 1998, Page(s):157 - 160
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (160 KB)

    We consider two aspects on the efficiency of Kanerva's sparse distributed memory (SDM). First, it has been suggested that in certain situations it would make sense to use different activation probabilities for writing and reading in SDM. However, here we model such a situation and find that, at least approximately, it is optimal to use the same probabilities for writing and reading. Second, and mo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A self-organizing algorithm for image compression

    Publication Year: 1998, Page(s):146 - 150
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (264 KB)

    Presents a modification of Kohonen's algorithm used in designing codebooks for vector quantization (VQ) of images. Kohonen's original algorithm builds up a map of the input signal in a one or two dimensional array of neurons. In the present work, the map is built in the synaptic space itself. Another modification is introduced: instead of finding the winning neuron around which the neighborhood is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Competitive and temporal Hebbian learning for production of robot trajectories

    Publication Year: 1998, Page(s):96 - 101
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (116 KB)

    This paper proposes an unsupervised neural algorithm for trajectory production of a 6-DOF robotic arm. The model encodes these trajectories in a single training iteration by using competitive and temporal Hebbian learning rules and operates by producing the current and the next position for the robotic arm. In this paper we will focus on trajectories with at least one common point. These types of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A self-organizing map model for analysis of musical time series

    Publication Year: 1998, Page(s):140 - 145
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (264 KB)

    Proposes a representation for unvoiced musical sequences, and tests experimentally our hierarchical artificial neural model on a musical time series-the third voice of the sixteenth four-part fugue in G minor of the Well-Tempered Clavier (vol. I) of J.S. Bach. The results obtained suggest that the model can perform efficiently on both recognition and discrimination of real musical sequences. It co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fault detection and isolation in robotic manipulators and the radial basis function network trained by the Kohonen's self-organizing map

    Publication Year: 1998, Page(s):85 - 90
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (156 KB)

    In this work, artificial neural networks are employed in a fault detection and isolation scheme for robotic manipulators. Two networks are utilized: a multilayer perceptron is employed to reproduce the manipulator dynamical behavior, generating a residual vector that is classified by a radial basis function network, giving the fault isolation. Two methods are utilized to choose the radial unit cen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-organizing modeling in forecasting daily river flows

    Publication Year: 1998, Page(s):210 - 214
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (100 KB)

    In a new approach, which corresponds in a better way to the actions of human nervous system, the connections between several neurons are not fixed but change in dependence on the neurons themselves. This article presents a GMDH (group method of data handling) algorithm with active neurons. These neurons are able, during the learning or self-organizing process, to estimate which inputs are importan... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CALIBRA for fuzzy concepts

    Publication Year: 1998, Page(s):130 - 134
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (72 KB)

    This paper presents a system for calibration of the involved parameters in the classification and characterization process of fuzzy concepts that use t-norm differentiable and related membership families for the definition of characterizing functions. An empirical evaluation using the data set iris shows the comparability with the classical methods of classification. We also make a conjecture that... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On Kolmogorov's superpositions and Boolean functions

    Publication Year: 1998, Page(s):55 - 60
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (84 KB)

    The paper overviews results dealing with the approximation capabilities of neural networks, as well as bounds on the size of threshold gate circuits. Based on an explicit numerical (i.e., constructive) algorithm for Kolmogorov's superpositions we show that for obtaining minimum size neural networks for implementing any Boolean function, the activation function of the neurons is the identity functi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Training linear neural network with early stopped learning and ridge estimation

    Publication Year: 1998, Page(s):14 - 19
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1100 KB)

    This paper addresses the problem of supervised learning in layered neural network with linear units and includes an analysis of the effect of noise on training algorithms. We survey most of the known results on linear networks. The connections to classical statistical ideas such as ordinary least squares are emphasized View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design of radial basis function network as classifier in face recognition using eigenfaces

    Publication Year: 1998, Page(s):118 - 123
    Cited by:  Papers (8)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (76 KB)

    In this paper we investigate alternative designs of a radial basis function network acting as classifier in a face recognition system. The inputs to the RBF network are the projections of a face image over the principal components. A database of 250 facial images of 25 persons is used for training and evaluation. Two RBF designs are studied: the forward selection and the Gaussian mixture model. Bo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Realization of a mixed-mode neural coprocessor for signal processing

    Publication Year: 1998, Page(s):180 - 185
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (80 KB)

    A hybrid architecture for neural coprocessing is presented. A fixed set of analog multipliers and capacitors (analog memory) emulates multilayer perceptrons through digitally-controlled multiplexing. Parallelism is partially preserved, then, without direct analog implementation of the whole structure. Details of system VLSI implementation are given, along with simulation results that validate syst... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.