IEEE International Symposium on Circuits and Systems,

8-11 May 1989

Filter Results

Displaying Results 1 - 25 of 548
  • A hierarchical system for character recognition

    Publication Year: 1989, Page(s):1 - 4 vol.1
    Cited by:  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (335 KB)

    A hierarchical system for character recognition with hidden-Markov model knowledge sources that solves both the context-sensitive problem and the character-instantiation problem is presented. The algorithms and the structure of the system are described, and its operation is discussed. The system achieves 97 to 99% accuracy using a two-level architecture and has been implemented using a systolic ar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fast and flexible residue decoder based on the Chinese remainder theorem

    Publication Year: 1989, Page(s):200 - 203 vol.1
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (330 KB)

    An implementation of a fast and flexible residue decoder based on the Chinese remainder theorem (CRT) is proposed for decoding a set of residues to its equivalent representation in a weighted binary number system. This decoder is flexible, since the decoded data can be selected to be either unsigned magnitude of two's complement binary number. It is shown that this residue decoder is extremely fas... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new class of node-splitting problems and applications

    Publication Year: 1989, Page(s):309 - 312 vol.1
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (384 KB)

    A new class of node-splitting problems for graphs is introduced and studied. The goal of the splitting process is to minimize the number of node-splitting operations needed to transform a given input graph into a new graph that has a property (bipartite, planar, nonseparable, etc.) that the original graph does not have. It is shown that the node splitting problem is NP-complete when the property i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Perspectives on realizations of neural networks

    Publication Year: 1989, Page(s):818 - 819 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (121 KB)

    Summary form only given. The authors consider a pulse-coded formulation of neural networks. The philosophy on which this formulation is based is that of H.D. Crane (Proc. IRE, vol.50, no.10, p.2048-60, Oct. 1962), where the neuristor is introduced. The neuristor is a device which abstracts some of the signal handling properties of biological neural systems, the primary ones singled out being (a) f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Power dissipation estimate by switch level simulation (CMOS circuits)

    Publication Year: 1989, Page(s):881 - 884 vol.2
    Cited by:  Papers (17)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (289 KB)

    A method for calculating power dissipation of digital CMOS circuits is presented. The estimate is made during switch-level simulation and is thus based on the simulated activity in the circuit. Dissipation from dynamic switching, the short-circuit component, and static currents are considered. The average power dissipation is overestimated by as little as 5-10% compared to SPICE results, if X-stat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A modified FFT-based filter for noise reduction of EEG measurements in identifying task learning processes

    Publication Year: 1989
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (39 KB)

    Summary form only given. A novel digital bandpass filter, which yields noise-free measurements of EEG signals, is presented. The accuracy of the digital bandpass filter depends on the performance of the discrete Fourier transform method, which is adopted in the filter. A revised discrete Fourier transform method is proposed to decrease the transformation error due to the finiteness of the EEG time... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CMOS circuit for MOS transistor threshold adjustment: a means for neural network weight adjustment

    Publication Year: 1989, Page(s):1221 - 1222 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (89 KB)

    Summary form only given. A new CMOS circuit is described that behaves like an MOS transistor with a threshold voltage that is easily adjusted by external control. The circuit is designed to be used in neural-type circuit applications, where threshold voltage adjustments can act to fix the connection weights which determine the amount of transmission from one neuron's output to another neuron's inp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Convolution-backprojection image reconstruction for bistatic synthetic aperture radar

    Publication Year: 1989, Page(s):1512 - 1515 vol.3
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (389 KB)

    The algorithm presented accounts for the elliptical nature of the wavefronts over the ground patch (resulting in elliptical-arc projections) and is based on the convolution-backprojection (CBP) algorithm of computer tomography. Essentially, three changes were made to the CBP algorithm. First, instead of backprojection along straight lines, the backprojection is along the same elliptical arcs from ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The ST18940/41: an advanced single-chip digital signal processor

    Publication Year: 1989, Page(s):1559 - 1562 vol.3
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (354 KB)

    A description is given of the architecture, the internal resources and the performance of a second-generation, monolithic, programmable digital signal processor. The architecture and instruction set of the ST DSP family are designed to allow a straightforward expansion by adding new functions or improving the existing ones in parallel with advances in VLSI technology while ensuring upward software... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Continuous-time and switched capacitor monolithic filters based on current and charge simulation

    Publication Year: 1989, Page(s):1580 - 1583 vol.3
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    The authors are concerned primarily with low-pass filters. A typical section on an LCR network for polynomial low-pass filters, which are those not possessing transmission zeros at finite frequencies, is presented. For this kind of filter, a signal-flow-graph (SFG) representation may conveniently be obtained. The authors choose as variables for the SFG the inductor currents and capacitor voltages ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonlinear robust variable structure control of pointing and tracking with operator spline estimation

    Publication Year: 1989
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (68 KB)

    Summary form only given. Variable control (VSC) in effect consists of designing a control input based on a simplified or inaccurate dynamic model, to which a variable correction is added, based on estimates of the model errors, sufficient incipiently to overshoot the desired controlled trajectory (sliding manifold). To suppress chattering, an optimally time-varying boundary layer can be generated ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Conjugate gradient techniques for adaptive filtering

    Publication Year: 1989, Page(s):1752 - 1757 vol.3
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (385 KB)

    The technique of conjugate gradients is applied to the adaptive filtering problem. The method provides convergence comparable to that of RLS (recursive-least-squares) schemes and has a computational requirement that is intermediate between the LMS (least-mean-square) and the RLS methods. It does not suffer from any known stability problems.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Accuracy management for VLSI timing analysis

    Publication Year: 1989, Page(s):2027 - 2031 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (460 KB)

    The authors show that algorithms of different accuracy levels can be carefully and automatically mixed to get a desired global accuracy. For instance, highly accurate algorithms may only be required along critical paths to produce a highly accurate delay estimate. They outline several linear-time heuristic algorithms, based on a detailed analysis of simple logic chains, that allow the management o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A semi-analytic slope delay model for CMOS switch-level timing verification

    Publication Year: 1989, Page(s):2032 - 2035 vol.3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (275 KB)

    A novel slope delay model for CMOS switch-level timing verification is presented. It differs from conventional methods in being semi-analytic in character. The model assumes that all input waveforms are trapezoidal in overall shape, but that they vary in their slope. This simplification is quite reasonable and does not seriously affect precision, but it facilitates rapid solution. The model divide... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A study of voice/non-voice discrimination method using neural networks for integrated packet switching system

    Publication Year: 1989, Page(s):2096 - 2099 vol.3
    Cited by:  Papers (1)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (301 KB)

    Voice packet technology, which handles analog signals such as DTMF (dual-tone multifrequency) signals and voiceband data as well as voice, image and data, is a key technology for a fast packet-switching system for multimedia communication. Transmission of voice signal in packets involves echo canceling, bandwidth-compression coding, and silence compression. However, if nonvoice signals like DTMF s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A recursive solution for strongly nonlinear systems by combining Volterra principles with the harmonic balance technique

    Publication Year: 1989, Page(s):2159 - 2164 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (527 KB)

    An algorithm is presented for determining the steady-state solution of a strongly nonlinear system. It combines an existing Volterra approach for weakly nonlinear systems with some principles that are used in the harmonic balance technique. A uniform method is realized that is applicable in a large class of problems. To demonstrate its possibilities an operational amplifier causing slew-induced di... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 1989 IEEE International Symposium on Circuits and Systems (Cat. No.89CH2692-2)

    Publication Year: 1989
    Request permission for commercial reuse | PDF file iconPDF (31 KB)
    Freely Available from IEEE
  • Systolic architectures for Hopfield network, BAM and multi-layer feed-forward network

    Publication Year: 1989, Page(s):790 - 793 vol.2
    Cited by:  Papers (4)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (204 KB)

    The systolic array architectures of a number of well-known artificial neural networks are presented. The artificial neural networks considered include the Hopfield neural network, bidirectional associative memories, and the multilayer feedforward neural network. The architectures presented are regular and are designed to operate in pipelined fashion View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ionic-channel signal processing using artificial neural network

    Publication Year: 1989, Page(s):786 - 789 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB)

    A specifically designed neural network is used to process ionic-channel signals. The model includes three major stages: the normalization, neural network main body and postprocessing stages. In the normalization stage, the real world signal is preprocessed and preconditioned for the use by the neural network. The main body of the model, the neural network, functions as a pattern recognizer, using ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An application of neural net in decoding error-correcting codes

    Publication Year: 1989, Page(s):782 - 785 vol.2
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (156 KB)

    A neural net architecture is implemented as a maximum-likelihood decoder. Any block binary code can be easily decoded. In a von Neumann computer, the computation of all the Hamming distances requires exponential time; however, polynomial-time is needed for the neural net, taking advantage of parallel computation. In fact, picking the maximum is a polynomial-time problem. Since the decoding problem... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural network for temporal pattern recognition

    Publication Year: 1989, Page(s):778 - 781 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (284 KB)

    A neural network that can be trained to recognize a sequence of events in time is presented. It utilizes a process of temporal integration, which is implemented by providing each node with a fading memory and the use of a special interconnect pattern. A simulation model for a motion detector based on the proposed network was implemented. It can be trained to distinguish between several speeds of a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distributed transmission lines and time-domain analysis in SPICE-like circuit simulators

    Publication Year: 1989, Page(s):709 - 712 vol.1
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (336 KB)

    Several problems arising in the SPICE implementation of the time-domain analysis of circuits with distributed transmission lines are indicated. It is shown that some simple modifications of the original handling of transmission lines can significantly reduce both the memory requirements and the CPU time needed for this analysis. The modifications make it possible to trade simulation time for accur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image morphological operations by neural circuits

    Publication Year: 1989, Page(s):774 - 777 vol.2
    Cited by:  Papers (1)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB)

    An approach to implementing neural computing with Boolean programmable logic is presented. A technique for the implementation of image morphological operations using a neural architecture is developed. Image morphological operations, by their very nature, involve repeated computations over large data structures. Parallelism appears to be a necessary attribute of a hardware system which can efficie... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Network sensitivity analysis via symbolic formulation

    Publication Year: 1989, Page(s):705 - 708 vol.1
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (260 KB)

    A personal computer program for the sensitivity analysis of linear networks is presented. The program, which is part of an integrated program package for the symbolic analysis of electric circuits, is based on artificial intelligence techniques and, in particular, on symbolic manipulation of algebraic expressions. The program obtains the network sensitivity functions in completely symbolic form wi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A unifying viewpoint of multilayer perceptrons and hidden Markov models

    Publication Year: 1989, Page(s):770 - 773 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (256 KB)

    A generic iterative model for artificial neural networks (ANNs) is proposed which covers a wide variety of existing neural networks: single-layer feedback networks, multilayer feedforward networks, hierarchical competitive networks, and hidden Markov models. From the phase-retrieve point of view, the hidden Markov models described by the trellis structure can be regarded as a homogeneous (recurren... View full abstract»

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