By Topic

IEE Proceedings F - Radar and Signal Processing

Issue 6 • Date Dec. 1992

Filter Results

Displaying Results 1 - 10 of 10
  • Self-supervised adaptive networks

    Publication Year: 1992, Page(s):371 - 377
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (574 KB)

    A scheme for training multilayer unsupervised networks is presented, in which control signals propagate downwards from the higher layers to influence the optimisation of the lower layers. Because there is no external teacher involved, this is called self-supervised training. The author demonstrates both theoretically and numerically how self-supervision emerges when a simple network built out of v... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Orthogonal least-squares algorithm for training multioutput radial basis function networks

    Publication Year: 1992, Page(s):378 - 384
    Cited by:  Papers (28)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (554 KB)

    A constructive learning algorithm for multioutput radial basis function networks is presented. Unlike most network learning algorithms, which require a fixed network structure this algorithm automatically determines an adequate radial basis function network structure during learning. By formulating the learning problem as a subset model selection, an orthogonal least-squares procedure is used to i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Use of Kohonen self-organising feature maps for HMM parameter smoothing in speech recognition

    Publication Year: 1992, Page(s):385 - 390
    Cited by:  Papers (4)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (601 KB)

    The authors present a new method for smoothing the parameters of hidden Markov models (HMMs) which produces improved speech recognition results when only a limited amount of training data is available. The method uses the Kohonen self-organising feature map (KSOFM) as a clustering technique in codebook design for discrete HMMs. Neighbouring information provided by two-dimensional or three-dimensio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast learning-algorithms for a self-optimising neural network with an application to isolated word recognition

    Publication Year: 1992, Page(s):391 - 396
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (482 KB)

    A short description of the feature finding neural net (FFNN) for the recognition of isolated words is given. As has been shown in the literature, during recognition model FFNN is faster than the classical HMM and DTW recognisers and yields similar recognition rates. In the paper, the emphasis is placed on optimal and fast algorithms for selecting features from the speech signal that are relevant f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison of connectionist and traditional methods applied to phrase classification and grammaticality determination

    Publication Year: 1992, Page(s):397 - 404
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (736 KB)

    Two sentence classification experiments are described. In the first, the neural net HODYNE (Higher Order Dynamic Topology Net) is shown to be better than a keyword method at classifying banking phrases. In the second, three techniques are compared at determining the grammaticality of strings of syntactic tags from the LOB (Lancaster Oslo Bergen) corpus: a method using the statistics of tag pairs. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic location of visual features by a system of multilayered perceptrons

    Publication Year: 1992, Page(s):405 - 412
    Cited by:  Papers (8)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (1105 KB)

    A two-stage neural vision system for locating facial features is described. The first stage generates search regions in an image at low spatial resolution and the second pinpoints the features at high resolution. Both stages employ multilayered perceptrons trained to detect specific visual details, followed by sophisticated global postprocessing of their outputs. This work demonstrates the power o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • BARTIN: minimising Bayes risk and incorporating priors using supervised learning networks

    Publication Year: 1992, Page(s):413 - 419
    Cited by:  Papers (2)  |  Patents (5)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (618 KB)

    BARTIN (BAyesian Real-Time Network) is a general structure for learning Bayesian minimum risk decision schemes. It comprises two user-specified supervised learning nets (an observer and a utility network) and associated elements. This two stage structure allows separate minimisation of risk and compensation for changes in prior probabilities. It is able to learn Bayesian minimum risk decision sche... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of the sleep EEG using a multilayer network with spatial organisation

    Publication Year: 1992, Page(s):420 - 425
    Cited by:  Papers (8)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (489 KB)

    Since its discovery some 50 years ago, the electroencephalogram (EEG) has formed the basis for the classification of sleep into several stages. Such classification has been laboriously performed by visual examination of the EEG and related signals, or, more recently, by automated techniques. Both visual scoring and most automated analyses rely on the application of a predefined set of rules. The a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Novel analogue VLSI design for multilayer networks

    Publication Year: 1992, Page(s):426 - 430
    Cited by:  Papers (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (548 KB)

    The authors introduce a new pulse-stream analogue VLSI design which has been optimised for the implementation of multilayer networks. The requirements of fully-trained multilayer perceptrons have been analysed to produce a set of specifications for the hardware design. The pulse-stream circuits described in the paper are driven from a fixed-frequency master clock, and a synaptic multiply-and-add c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural control of locomotion in a quadrupedal robot

    Publication Year: 1992, Page(s):431 - 436
    Cited by:  Papers (3)  |  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (642 KB)

    The authors present results of a first study demonstrating that the apparently complex task of controlling walking in a real quadrupedal robot with highly nonlinear interactions between the control elements can be learned quickly by a crude and simple reinforcement learning algorithm. They can as yet say little that is useful about the contribution of reflexes to learned walking, and nothing about... View full abstract»

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

Aims & Scope

The latest version of this title is Radar, Sonar & Navigation, IET.

Full Aims & Scope