By Topic

Neural Networks for Processing [1993] III. Proceedings of the 1993 IEEE-SP Workshop

Date 6-9 Sept. 1993

Filter Results

Displaying Results 1 - 25 of 63
  • Neural Networks for Signal Processing III - Proceedings of the 1993 IEEE-SP Workshop

    Publication Year: 1993
    Request permission for commercial reuse | PDF file iconPDF (37 KB)
    Freely Available from IEEE
  • Application of ordered codebooks to image coding

    Publication Year: 1993, Page(s):291 - 300
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (404 KB)

    The application of self-organizing feature maps to image vector quantization (VQ) is considered. Their property of ordering, which is absent in conventional vector quantizers, can be used in order to improve the quality of the quantized images or to simplify the VQ process. A differential coding technique is presented which exploits the correlation between addresses relating to adjacent blocks. An... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applying neural network developments to sign language translation

    Publication Year: 1993, Page(s):301 - 310
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (468 KB)

    Neural networks are used to extract relevant features of sign language from video images of a person communicating in American Sign Language or Signed English. The key features are hand motion, hand location with respect to the body, and handshape. A modular design is under way to apply various techniques, including neural networks, in the development of a translation system that will facilitate c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multisensor image classification by structured neural networks

    Publication Year: 1993, Page(s):311 - 320
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (524 KB)

    The application of structured neural networks to the supervised classification of multisensor images is discussed. The purpose is to give a criterion for network architecture definition and to allow the interpretation of the network behavior. The latter result can be used to understand the importance of sensors and related channels to the classification task. The networks' architecture is configur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Lyapunov function for additive neural networks and nonlinear integral equations of Hammerstein type

    Publication Year: 1993, Page(s):11 - 13
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (140 KB)

    Using the properties of the nonlinear integral equations of the Hammerstein type, a new Lyapunov function for additive neural networks is constructed. The function does not require monotonicity of the transfer function as does the previously discovered Lyapunov function for the additive networks. Instead positivity of the symmetric part of the weight matrix is required. The results on the Hammerst... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network image analysis and classification in hybrid lung nodule detection (HLND) system

    Publication Year: 1993, Page(s):517 - 526
    Cited by:  Papers (4)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (496 KB)

    A hybrid lung nodule detection (HLND) system based on artificial neural network architectures is developed for improving diagnostic accuracy and speed of lung cancerous pulmonary radiology. The configuration of the HLND system includes the following processing phases: (1) pre-processing to enhance the figure-background contrast; (2) quick selection of nodule suspects based upon the most prominent ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonlinear multilayer principal component type subspace learning algorithms

    Publication Year: 1993, Page(s):68 - 77
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (452 KB)

    A hidden layer is introduced into nonlinear principal component type learning algorithms. The algorithms are derived from nonlinear optimization criteria. Both subspace type and hierarchical versions are considered. The algorithms are tested in context with harmonic retrieval and directions-of-arrival estimation problems using impulsive and colored noise. Some of the nonlinear algorithms have inte... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluation of character recognition systems

    Publication Year: 1993, Page(s):485 - 496
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    Eleven different Census Optical Character Recognition Systems systems are evaluated using correlations between the answers of different systems, comparing the decrease in error rate as a function of confidence of recognition, and comparing the writer dependence of recognition. This comparison shows that methods that use different algorithms for feature extraction and recognition perform with very ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Compressing moving pictures using the APEX neural principal component extractor

    Publication Year: 1993, Page(s):321 - 330
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (444 KB)

    An application of the optimal Karhunen-Loe`ve transform (KLT) in place of the traditional discrete cosine transform (DCT) for compressing intra-frames in the MPEG protocol is proposed. The I-frames attain the smallest compression ratio since they are coded without reference to any other frames. The difficulty of KLT (additional bit-rate is required to make the image-dependent transform basis... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • VLSI Hamming neural net showing digital decoding

    Publication Year: 1993, Page(s):405 - 410
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (196 KB)

    The electrical performance in PSpice for a VLSI Hamming neural net in CMOS 2-micron technology is presented. It features analog parallel processing and digital decoding, keeping the low circuit-interconnection complexity of early schemes View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical recurrent networks for learning musical structure

    Publication Year: 1993, Page(s):216 - 225
    Cited by:  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (500 KB)

    Layered neural networks employing feedback links have been proposed for certain sequential pattern tasks in automatic music composition. A hierarchical version of this type of network is studied. The use of such a hierarchical neural network for modeling coarse and fine temporal structure in music is investigated. This network is trained on two classical waltzes and then used to generate novel wal... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A hybrid learning method for multilayer neural networks

    Publication Year: 1993, Page(s):14 - 21
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (248 KB)

    A Newton learning approach for training a multilayer neural network is provided based on an efficient derivation of Hessian matrix of the network. Since the Newton's method converges almost quadratically, the convergence performance is improved. A hybrid learning method is developed in conjunction with the conventional backpropagation algorithm. Its performance is demonstrated by the classical XOR... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Text-Dependent speaker verification using recurrent time delay neural networks for feature extraction

    Publication Year: 1993, Page(s):353 - 361
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (304 KB)

    The possible application of time delay neural network (TDNN) to the text-dependent speaker verification problem is described and evaluated. Each person to be verified has a personalized neural network, which is trained to extract representative feature vector of the speaker by a particular utterance. A novel model called recurrent time delay neural networks is investigated. The training is carried... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hidden Markov models and neural networks for fault detection in dynamic systems

    Publication Year: 1993, Page(s):582 - 592
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (520 KB)

    It is shown how both pattern recognition methods (in the form of neural networks) and hidden Markov models (HMMs) can be used to automatically monitor online data for fault detection purposes. Monitoring for anomalies or faults poses some technical problems which are not normally encountered in typical HMM applications such as speed recognition. In particular, the ability to detect data from previ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Printed circuit boards inspection using two new algorithms of dilatation and connectivity preserving shrinking

    Publication Year: 1993, Page(s):527 - 536
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (444 KB)

    Two new algorithms of dilatation and connectivity preserving shrinking as a contribution to the resolution of the problem of the inspection of the printed circuit boards (PCBs) are presented. The algorithms developed are fast and achieve dilatation, shrinking, and connectivity preserving shrinking (CPS) in two iterations. The algorithm of PCB inspection does not require any synchronization, and it... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Designer networks for time series processing

    Publication Year: 1993, Page(s):78 - 87
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (472 KB)

    The conventional tapped-delay neural net may be analyzed using statistical methods and the results of such analysis can be applied to model optimization. The authors review and extend efforts to demonstrate the power of this strategy within time series processing. They attempt to design compact networks using the so-called optima brain damage (OBD) method. The benefits from compact architectures a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A modified recurrent cascade-correlation network for radar signal pulse detection

    Publication Year: 1993, Page(s):497 - 506
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (528 KB)

    A Jordan-style cascade-correlation architecture is developed for radar signal pulse detection. The cascade-correlation learning architecture is modified to facilitate hardware implementation of the network. The network is constructed using only two hidden layers, with nodes added to the layers in a lateral fashion. Comparisons to networks trained using backpropagation and genetic algorithms indica... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Competitive learning and winning-weighted competition for optimal vector quantizer design

    Publication Year: 1993, Page(s):50 - 59
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (404 KB)

    It is essential to build a nonparametric model to estimate a probability density function p(x) in the areas of vector quantization, pattern recognition, control, and many others. A generalization of Kohonen learning, the winning-weighted competitive learning (WWCL), is presented for a better approximation of p(x) and fast learning convergence by introducing the principle of maximum information pre... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new learning algorithm for minimizing spotting errors

    Publication Year: 1993, Page(s):333 - 342
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (556 KB)

    A new learning algorithm, called minimum spotting error formalization (MSPE), is proposed for designing a high performance word spotting system. An overall spotting system, comprising word models and decision thresholds, primarily needs to be optimized to minimize all spotting errors; the word models and the thresholds should no longer be separately and heuristically designed. MSPE features a rigo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Target recognition using multiple sensors

    Publication Year: 1993, Page(s):411 - 420
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    A novel approach to multisensor target recognition is presented. Currently available multisensor recognition algorithms/systems have low recognition rates when tested in battlefield conditions. The authors' approach make no assumptions on either sensors or targets, and uses some biologically inspired algorithms to build a multisensor target recognition system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network-based helicopter gearbox health monitoring system

    Publication Year: 1993, Page(s):431 - 440
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (436 KB)

    The results of two neural hardware implementations of a helicopter gearbox health monitoring system (HMS) are summarized. The first hybrid approach and implementation to fault diagnosis is outlined, and results are summarized using three levels of fault characterization: fault detection (fault or no fault), classification (hear or bearing fault), and identification (fault sub-classes). Initial har... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Characterization of network responses to known, unknown, and ambiguous inputs

    Publication Year: 1993, Page(s):226 - 231
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    Neural networks typically classify patterns by mapping the input feature space to the corners of the m-dimensional unit hypercube where m is the number of output classes. When classifier networks of graded threshold neurons are presented with patterns that are strong, ambiguous, or unknown, characteristic responses are emitted. A second tier network can be used to characterize the decision of the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • LS-based training algorithm for neural networks

    Publication Year: 1993, Page(s):22 - 29
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (580 KB)

    A new training algorithm is presented as a faster alternative to the backpropagation (BP) method. The new approach is based on the solution of a linear system at each step of the learning phase. The squared error at the output of each layer before the nonlinearity is minimized on the entire set of the learning patterns by a block least squares (LS) algorithm. The optimal weights for each layer are... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of coarse parallel architectures for artificial neural processing

    Publication Year: 1993, Page(s):450 - 459
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (692 KB)

    A methodology for comparing various neural architectures and implementations is illustrated. The methodology consists of writing the artificial neural network (ANN) equations in a summation form and the applying a tool termed algorithmic timing parameter decomposition (ATPD). ATPD decomposes an algorithm or set of equations into a computation time formula comprising basic system primitives. A part... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new learning approach based on equidistortion principle for optimal vector quantizer design

    Publication Year: 1993, Page(s):362 - 371
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (448 KB)

    The authors theoretically derive a basic principle called the equidistortion principle for the design of optimal vector quantizers. This principle can be regarded as a extension of Gersho's theory (1979). A new learning algorithm is presented with a selection mechanism based on this principle. Since no probabilistic model is assumed in deriving the principle, the associated algorithm, unlike conve... View full abstract»

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