Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop

Aug. 31 1992-Sept. 2 1992

Filter Results

Displaying Results 1 - 25 of 64
  • An electronic parallel neural CAM for decoding

    Publication Year: 1992, Page(s):581 - 587
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (288 KB)

    The authors report measurements taken on an electronic neural system configured for content addressable memory (CAM) using a high-capacity architecture. It is shown that Boltzmann and mean-field learning networks can be implemented in a parallel, analog VLSI system. This system was used to perform experiments with mean-field CAM. The hardware settles on a stored codeword in about 10 mu s roughly i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Globally trained neural network architecture for image compression

    Publication Year: 1992, Page(s):289 - 295
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (321 KB)

    The authors discuss the development of a coding system for image transmission based on block-transform coding and vector quantization. Moreover, a classification of the image blocks is performed in the spatial domain. An architecture incorporating both multilayered perceptron and self-organizing feature map neural networks and a block classification is considered to realize the image coding scheme... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spectral representations for speech recognition by neural networks - A tutorial

    Publication Year: 1992, Page(s):214 - 222
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (301 KB)

    Spectrum-based speech representations are discussed. Spectral representations, in order to be useful for speech recognition, need to be justified from both the computational (analytical) and the perceptual viewpoints. The authors' discussion of spectral representations, therefore, includes both the computational model and the associated measures of similarity that are appropriate for neural networ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Text-independent talker identification system combining connectionist and conventional models

    Publication Year: 1992, Page(s):131 - 138
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (391 KB)

    Several techniques have been used for speaker identification which have different characteristics and capabilities. The respective merits of three different systems respectively employing neural networks, hidden Markov models, and multivariate autoregressive models are compared. A novel text-independent speaker identification system based on the cooperation of these different techniques is present... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Empirical risk optimisation: neural networks and dynamic programming

    Publication Year: 1992, Page(s):121 - 130
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (430 KB)

    The authors propose a novel system for speech recognition which makes a multilayer perceptron and a dynamic programming module cooperate. It is trained through a cost function inspired by learning vector quantization which approximates the empirical average risk of misclassification. All the modules of the system are trained simultaneously through gradient backpropagation; this ensures the optimal... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural Networks for Signal Processing II. Proceedings of the IEEE-SP Workshop (Cat. No.92TH0430-9)

    Publication Year: 1992
    Request permission for commercial reuse | |PDF file iconPDF (32 KB)
    Freely Available from IEEE
  • Adaptive segmentation of textured images using linear prediction and neural networks

    Publication Year: 1992, Page(s):401 - 410
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (624 KB)

    An adaptive technique for classifying and segmenting textured images is presented. This technique uses an efficient least squares algorithm for recursive estimation of two-dimensional autoregressive texture models and neural networks for recursive classification of the models. A network with fixed, but space-varying, interconnection weights is used to optimally select a small representative set of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Some new results in nonlinear predictive image coding using neural networks

    Publication Year: 1992, Page(s):411 - 420
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (288 KB)

    The problem of nonlinear predictive image coding with multilayer perceptrons is considered. Some important aspects of coding, including the training of multilayer perceptrons, the adaptive scheme, and the robustness to the channel noise, are discussed in detail. Computer simulation results show that nonlinear predictors have better predictive performances than the linear DPCM. It is shown that the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A system identification perspective on neural nets

    Publication Year: 1992, Page(s):423 - 435
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (508 KB)

    The authors review some of the basic system identification machinery to reveal connections with neural networks. In particular, they point to the role of regularization in dealing with model structures with many parameters, and show the links to overtraining in neural nets. Some provisional explanations for the success of neural nets are also offered View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Prediction of chaotic time series using recurrent neural networks

    Publication Year: 1992, Page(s):436 - 443
    Cited by:  Papers (3)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (356 KB)

    The authors propose to train and use a recurrent artificial neural network (ANN) to predict a chaotic time series. Instead of training the network with the next sample in the time series as is normally done, a sequence of samples that follows the present sample will be utilized. Dynamical parameters extracted from the time series provide the information to set the length of these training sequence... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fast simulator for neural networks on DSPs or FPGAs

    Publication Year: 1992, Page(s):597 - 605
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (380 KB)

    The authors present a description of their achievements and current research on the implementation of a fast digital simulator for artificial neural networks. This simulator is mapped either on a parallel digital signal processor (DSP) or on a set of field programmable gate arrays (FPGAs). Powerful tools have been developed that automatically compile a graphical neural network description into exe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonlinear system identification using multilayer perceptrons with locally recurrent synaptic structure

    Publication Year: 1992, Page(s):444 - 453
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (388 KB)

    It is proved that a multilayer perceptron (MLP) with infinite impulse response (IIR) synapses can represent a class of nonlinear block-oriented systems. This includes the well-known Wiener, Hammerstein, and cascade or sandwich systems. Previous methods used to model these systems such as the Volterra series representation are known to be extremely inefficient, and so the IIR MLP represents an effe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real time CCD-based neural network system for pattern recognition applications

    Publication Year: 1992, Page(s):606 - 616
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (588 KB)

    A generic NNC (neural network classifier) capable of providing 1.9 billion programmable connections per second is described. Applications for these generic processors include image and speech recognition as well as sonar signal identification. To demonstrate the modularity and flexibility of the CCD (charge coupled device) NNCs, two generic multilayer system-level boards capable of both feedforwar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Chaotic signal emulation using a recurrent time delay neural network

    Publication Year: 1992, Page(s):454 - 463
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (352 KB)

    The authors describe a method for training a dispersive neural network to imitate a chaotic signal without using any knowledge of how the signal was generated. In a dispersive network, each connection has both an adaptable time delay and an adaptable weight. The network was first trained as a feedforward signal predictor and then connected recurrently for signal synthesis. The authors evaluate the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Prediction with recurrent networks

    Publication Year: 1992, Page(s):464 - 473
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (320 KB)

    The authors study extrapolation of time series using recurrent neural networks. They use the real-time recurrent learning algorithm introduced by R. J. Williams and D. Zipser (1989), both in the original form for first order nets and in a form for second order nets. It is shown that both the first order and the second order nets are able to learn to simulate the Mackey-Glass series. The prediction... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A two-layer Kohonen neural network using a cochlear model as a front-end processor for a speech recognition system

    Publication Year: 1992, Page(s):139 - 148
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (364 KB)

    The authors describe a two-layer neural network speech recognition system based on Kohonen's algorithm. A cochlear model is used as a front-end processor for the system. The basilar membrane is represented by a cascade of 128 digital filters, of which 90 filters fall within the speech bandwidth of 250 Hz to 4 kHz. The outputs of these 90 filters are presented as the input vector to the first layer... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised multi-level segmentation of multispectral images

    Publication Year: 1992, Page(s):363 - 372
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (520 KB)

    The authors describe a scheme that performs multilevel segmentation of an image at many scales using a multiresolution texture representation. Each level uses anisotropic diffusion to segment a multispectral image at successively lower resolutions. Texture and statistical similarities between and within levels guides the diffusion process. The restriction of coarse-to-fine segmentation is removed,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of frequency-domain neural networks to the active control of harmonic vibrations in nonlinear structural systems

    Publication Year: 1992, Page(s):474 - 483
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (352 KB)

    The authors show how a nonlinear adaptive controller of quasi-neural architecture can be used to control harmonic vibrations even when it has to act through a nonlinear actuator element. The controller comprises a fixed nonlinearity to generate harmonics of the sinusoidal reference signal and a linear adaptive combiner. The coefficients in the adaptive combiner are adjusted using a steepest descen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-structuring hidden control neural models

    Publication Year: 1992, Page(s):149 - 156
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (292 KB)

    The authors propose a self-structuring hidden control (SHC) neural model for pattern recognition which establishes a near-optimal architecture during training. A significant network architecture reduction in terms of the number of hidden processing elements (PEs) is typically achieved. The SHC model combines self-structuring architecture generation with nonlinear prediction and hidden Markov model... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Supervised learning on large redundant training sets

    Publication Year: 1992, Page(s):79 - 89
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (404 KB)

    A novel algorithm combining the good properties of offline and online algorithms is introduced. The efficiency of supervised learning algorithms on small-scale problems does not necessarily scale up to large-scale problems. The redundancy of large training sets is reflected as redundancy gradient vectors in the network. Accumulating these gradient vectors implies redundant computations. In order t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the complexity of neural networks with sigmoidal units

    Publication Year: 1992, Page(s):23 - 28
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (252 KB)

    Novel techniques based on classical tools such as rational approximation and harmonic analysis are developed to study the computational properties of neural networks. Using such techniques, one can characterize the class of function whose complexity is almost the same among various models of neural networks with feedforward structures. As a consequence of this characterization, for example, it is ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural networks and nonparametric regression

    Publication Year: 1992, Page(s):511 - 521
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (676 KB)

    The problem of estimating an unknown function from a finite number of noisy data points is a problem of fundamental importance for many applications in signal processing, machine vision, pattern recognition, and process control. Recently, several new computational techniques for nonparametric regression have been proposed by statisticians and by researchers in artificial neural networks. The autho... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Autoassociative neural networks for image compression: a massively parallel implementation

    Publication Year: 1992, Page(s):373 - 381
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (484 KB)

    A massively parallel implementation on the associative string processor (ASP) machine of a neural-network-based technique for image compression is presented. Despite the linear structure of the ASP and the use of fixed arithmetic for the implementation, promising results are shown in terms of learning speed, on the order of 109 connections per second, and the quality of the reconstructe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive decision-feedback equalizer using forward-only counterpropagation networks for Rayleigh fading channels

    Publication Year: 1992, Page(s):570 - 578
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (272 KB)

    A forward-only counterpropagation network (FCPN) is proposed for nonlinear equalization of digital transmission channels. The FCPN is a type of multilayer feedforward network proposed by Hecht-Nielsen. Its learning mechanism is a combination of unsupervised self-organizing and supervised training. A decision-feedback equalizer based on FCPN was simulated on a digital computer. The results show tha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Noise density estimation using neural networks

    Publication Year: 1992, Page(s):484 - 492
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (292 KB)

    A neural network for estimation of unknown noise densities and their gradients is presented. The network structure is similar to a radial basis function. The learning rule is, however, different and has an unsupervised nature that ensures a valid probability density. The algorithm is fast and provides good estimates of noise densities. One and two dimensional examples are reported View full abstract»

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