By Topic

Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on

Date 30 May-2 Jun 1994

Go

Filter Results

Displaying Results 1 - 25 of 126
  • CMOS design of two winner-take-all circuits using pulse duty cycle synaptic weighting

    Publication Year: 1994 , Page(s): 379 - 382 vol.6
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (292 KB)  

    In this paper the pulse coded Neural Processing Element (NPE) is used to realize two Winner-Take-All (WTA) systems which use an Hebbian type learning rule for setting the synaptic weights. The two systems, temporal and maximum-level, use the same circuit with a small connection change. In the NPE the average pulse duty cycle modulation technique is used to achieve pulse coded weighting for an artificial neuron. The average pulse duty cycle serves as an information mechanism to determine the weight multiplication. SPICE simulations check the theory with a CMOS prototype chip designed and fabricated through MOSIS. Measurements on the chip compared with simulation results verify the operation of the WTA circuitry View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generation of signals in a buck converter with sliding mode control

    Publication Year: 1994 , Page(s): 157 - 160 vol.6
    Cited by:  Papers (9)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (244 KB)  

    Time-dependent sliding surfaces are used in the generation of signals at the load resistance of a buck converter. Restrictions on these signals are derived from the condition of existence of sliding regime. The use of two sliding zones in the generation of a specified signal is studied View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analogue CMOS VLSI implementation of cellular neural networks with continuously programmable templates

    Publication Year: 1994 , Page(s): 367 - 370 vol.6
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (312 KB)  

    This paper presents the CMOS realisation of a programmable cellular neural network. An analogue programmable synapse circuit was designed that allows a large dynamic range for the template weights. Tuning circuits transform the digital values specified by the user to the corresponding analogue tuning voltages. A chip containing a 4x4 programmable CNN has been fabricated in a 2.4 μm CMOS process View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Studies on the stability of two dimensional analog nonlinear circuits

    Publication Year: 1994 , Page(s): 77 - 80 vol.6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (220 KB)  

    The paper proposes: (1) linearization procedure for nonlinear state equations obtained from two-dimensional (2-D) analog nonlinear circuits and; (2) characterization of the equilibrium point stability based on various two-variable (2-V) Hurwitz properties. It is concluded that at the equilibrium point (EP), 2-D nonlinear circuit is asymptotically stable if the characteristic equation obtained from linearized system exhibits 2-V very strict Hurwitz property. The necessary condition for the asymptotic stability imposes the 2-V scattering Hurwitz property on the characteristic polynomial of the linearized system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An approach to testability improvement of mixed-signal boards

    Publication Year: 1994 , Page(s): 161 - 164 vol.6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (324 KB)  

    The increasing complexity of mixed-signal boards makes an integrated analogue/digital testability approach an attractive proposition. This paper investigates one such approach based on the use of mixed-signal test support ICs together with standard board level test infrastructures. The architecture of a test support IC and preliminary experimental results are also presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • MAN: mass attraction network

    Publication Year: 1994 , Page(s): 455 - 458 vol.6
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (268 KB)  

    In this study, a binary associative memory, inspired from Newton's mass attraction theory is proposed and some related analysis is given. In the model, memory items are considered as masses in the interior or at the corners of a hypercube. In recall, “attraction forces” are computed and the memory item, whose “force” is the greatest, becomes the output pattern. Since the operation of the model is highly parallel, the network is extremely fast. Retrieving a memory item takes only two steps. The proposed model has been observed to be superior to Hamming net, Hopfield network and Harmony theory in various aspects View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Influence of the drive-signal resonant overtone on subharmonic injection-locking characteristics

    Publication Year: 1994 , Page(s): 209 - 212 vol.6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (284 KB)  

    The influence of a small but nonzero resonant overtone of the drive-signal on the static and dynamic characteristics of subharmonic injection-locked oscillators is investigated by means of a perturbation based phasor-domain approach. Both theoretical and computer simulation results show that, if certain conditions on the circuit parameters occur, even a very small amplitude overtone (e.g., -60 dBc) significantly affects the system behaviour. This fact may explain the discrepancies sometimes observed between experiments and predictions based on previous analysis methods View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Algorithms for the automatic design of the decomposed state model of an one-dimensional piecewise-linear system

    Publication Year: 1994 , Page(s): 45 - 48 vol.6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (284 KB)  

    Present paper deals with the problem of automatic design of the implicit state model (in its decomposed parametric form) of any one-dimensional piecewise-linear (PWL) system. This model consists of the internal and the external parts which provides the possibility of finding the model parameters, i.e. to solve separately the two main problems of an one-dimensional PWL model design: (i) existence of the individual breakpoints of the resultant PWL characteristic (determined by the internal block), (ii) setting of the breakpoint co-ordinates (determined by the external block) View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design and simulation of nonlinear switched capacitor autonomous circuits containing nonlinear active resistor

    Publication Year: 1994 , Page(s): 165 - 168 vol.6
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (240 KB)  

    The design and simulation of nonlinear switched capacitor autonomous circuits containing nonlinear active resistor is described in this paper. First, a new kind of SC nonlinear active resistor circuit is proposed. Then the novel SC nonlinear active resistor is used in the design of nonlinear SC autonomous circuits, in particular, a NR LC SC oscillator circuit and an autonomous circuit derived from Chua's circuit. Finally the computer simulation of NRLC SCO and chaotic oscillation of the three order SC autonomous circuit are discussed and some results are presented in this paper View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Minimal training set size estimation for neural network-based function approximation

    Publication Year: 1994 , Page(s): 403 - 406 vol.6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (372 KB)  

    A new approach to the problem of n-dimensional continuous and sampled-data function approximation using a two-layer neural network is presented. The generalized Nyquist theorem is introduced to solve for the optimum number of training examples in n-dimensional input space. Choosing the smallest but still sufficient set of training vectors results in a reduced learning time for the network. Analytical formulas and algorithm for training set size reduction are developed and illustrated by two-dimensional data examples View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A multilayer feedforward neural network model for digital hardware implementation

    Publication Year: 1994 , Page(s): 343 - 346 vol.6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (228 KB)  

    A design algorithm for two-layer feedforward neural networks (2FNNs) for discrete input-output mapping is proposed. In this algorithm, uniformly quantized discrete weights are used, which could be in the form of either one-powers-of-two (OPOT) values or sum-of-powers-of-two (SPOT) values. The simplified sigmoid activation functions (SSAFs) are used at hidden neurons and the step functions are used at output neurons to further reduce the hardware implementation cost. Simulation results indicate that such networks can retain nearly identical recall performances as those of the corresponding networks using continuous weights and sigmoid activation functions (SAFs), while having increased computational speed in applications and reduced cost in digital hardware implementation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance of Yamakawa's chaotic chips and Chua's circuits for secure communications

    Publication Year: 1994 , Page(s): 105 - 108 vol.6
    Cited by:  Papers (3)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (268 KB)  

    In this paper, we demonstrate how Yamakawa's chaotic chips and Chua's circuits can be used to implement a secure communication system based on chaotic modulation/demodulation systems. Furthermore, their performance for the secure communication is discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An adaptive neural network VQ algorithm and its implementation on the DSP32C signal processor

    Publication Year: 1994 , Page(s): 443 - 446 vol.6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (292 KB)  

    In this paper the implementation of an adaptive vector quantization (VQ) algorithm is described based on a computation and memory efficient neural network model described in previous publications. The adaptive neural VQ (ANVQ) algorithm is based on the full search VQ, and utilizes the modified frequency sensitive competitive learning algorithm for training the codebook. The ANVQ algorithm improves the codebook search speed and utilization and gives better output SNR compared to conventionally designed VQ algorithms, and for signals not included in the codebook training-sequence. Furthermore, the ANVQ model architecture is very suitable for VLSI implementation. A C++ interface to the DSP32C signal processor is used for implementation of the ANVQ algorithm View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A discriminative training algorithm for predictive neural network models

    Publication Year: 1994 , Page(s): 431 - 434 vol.6
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (288 KB)  

    Predictive neural network models are powerful speech recognition models based on a nonlinear pattern prediction. Those models, however, suffer from poor discrimination between acoustically similar speech signals. In this paper, we propose a new discriminative training algorithm for predictive neural network models based on the generalized probabilistic descent (GPD) algorithm and the minimum classification error formulation. The proposed algorithm allows direct minimization of a recognition error rate. Evaluation of our training algorithm on Korean digits shows its effectiveness by 30% reduction of recognition error View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multilayer neural network structure as Volterra filter

    Publication Year: 1994 , Page(s): 253 - 256 vol.6
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (300 KB)  

    The paper presents the application of the successive linearization to the neural network implementation of the Volterra filter. Applying the signal flow graph approach the new learning rules for adaptation of weights of the obtained multilayer network structure are given. The presented multilayer structure is applied to signal processing including the identification of the parameters of the plant, noise canceling and signal prediction View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new non competitive unsupervised neural network for clustering

    Publication Year: 1994 , Page(s): 273 - 276 vol.6
    Cited by:  Papers (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (276 KB)  

    In this paper a new unsupervised neural network, characterized by the absence of competition between its elements, is introduced. The kernel of this network is a new neural unit able to perform clustering even acting alone. It is shown how this network overcomes some of the major drawbacks of classical unsupervised competitive architectures View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Handwritten numeral recognition with multiple features and multistage classifiers

    Publication Year: 1994 , Page(s): 323 - 326 vol.6
    Cited by:  Papers (9)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (316 KB)  

    Multiple expert system is shown to be a promising strategy for handwritten numeral recognition. This paper presents a multiple expert system using neural networks. In the proposed system, the authors have developed (1) an incremental clustering neural network algorithm with merging and canceling process, (2) a modified directional histogram feature extraction method and (3) a subclass method with learning rejection neuron strategy. Our experimental results on a large set of data show the efficiency and robustness of the proposed system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the synchronization of oscillators coupled by one negative resistor

    Publication Year: 1994 , Page(s): 205 - 208 vol.6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (248 KB)  

    There have been many investigations of the mutual synchronization of oscillators. In this study we consider N oscillators which have the same natural frequency, mutually coupled by one negative resistor. In this system, according to the negative range of the coupling negative resistor, we can observe various interesting synchronization phenomena, because this system tends to minimize the power consumption in the coupling negative resistor. Especially when the I-V characteristics of the coupling negative resistor are not third-power, but linear and negative, this system tends to be stable by producing the power in the coupling one. The phase states are changed according to the negative range of the coupling negative resistor View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Behavioral testing of cellular neural networks

    Publication Year: 1994 , Page(s): 229 - 232 vol.6
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (388 KB)  

    This paper addresses the functional behavior of Cellular Neural Networks (CNN). The impact of variable convergence times on the proper operation of the network is discussed A test method is presented to determine the functionality of the network. The function fault models assume that the cells are unable to switch between limiting states. The proposed method attains 100% stuck-at fault coverage without any extra hardware for its implementation. Moreover, the required number of test vectors is constant and independent of the array size which makes it suitable for practical implementations. The paper discusses the new fault model, presents the algorithmic procedures and shows simulated testing results View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On estimation of nonlinear systems by nonparametric techniques

    Publication Year: 1994 , Page(s): 189 - 192 vol.6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (288 KB)  

    In the paper the estimation of block oriented systems is discussed. Particular attention is devoted to memoryless and dynamical systems with cascade structure. An optimal model of a memoryless cascade system is given and estimated by the kernel regression estimate. Nonlinear dynamical systems of the Hammerstein and Wiener type are estimated by means of nonparametric techniques. The convergence of estimation procedures is investigated View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Invariant sets for general second-order low-pass delta-sigma modulators with DC inputs

    Publication Year: 1994 , Page(s): 1 - 4 vol.6
    Cited by:  Papers (11)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (376 KB)  

    An invariant set, S, is a set of points in state space which has the property that all trajectories emanating from points in S remain in S. Such sets are useful in the context of delta-sigma modulation as they yield rigorous theoretical bounds on the state variables. This paper describes analytic and algorithmic methods for finding invariant sets of second-order delta-sigma modulators with DC inputs. The noise transfer functions of the modulators studied have two zeros near z=1 and arbitrary poles. The state-variable bounds which result are quite tight, with the algorithmic method providing the tightest bounds View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Torus doubling and hyperchaos in a five dimensional hysteresis circuit

    Publication Year: 1994 , Page(s): 113 - 116 vol.6
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (248 KB)  

    This article discusses a simple five dimensional autonomous circuit that includes one piecewise linear hysteresis element. We derive theoretical formulae of its three dimensional return map, its Jacobian matrix and Jacobian. Applying these to evaluate Lyapunov exponents, we clarify torus doubling route to area expanding chaos and volume expanding chaos which is a kind of hyperchaos. We also investigate basic bifurcation of these phenomena. Some attractors from the return map are verified by laboratory measurements View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Time-multiplexing CNN simulator

    Publication Year: 1994 , Page(s): 407 - 410 vol.6
    Cited by:  Papers (9)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (296 KB)  

    A novel approach to simulate Cellular Neural Networks (CNN) is presented in this paper. The approach, time-multiplexing simulation, is prompted by the need to simulate hardware models and test hardware implementations of CNN. For practical size applications, due to hardware limitations, it is impossible to have a one-on-one mapping between the CNN hardware processors and all the pixels of the image. This simulator provides a solution by processing the input image block by block, with the number of pixels in a block being the same as the number of CNN processors in the hardware. The algorithm for implementing this simulator is also presented, along with some simulation results and comparisons View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Predicting complex chaotic time series via complex valued MLPs

    Publication Year: 1994 , Page(s): 29 - 32 vol.6
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (292 KB)  

    In the paper it is proposed the use of a complex valued multi-layer perceptron neural network (MLP) with complex activation functions and complex connection strengths in order to perform the estimation of chaotic time series. In particular, the Ikeda map is taken into consideration. A comparison between the behavior of the real MLP and the complex one is also reported, showing that the complex valued MLP requires a smaller topology as well as a lower number of parameters in order to reach comparable performance View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Power oscillator design: class E

    Publication Year: 1994 , Page(s): 153 - 156 vol.6
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (200 KB)  

    An analytic approach to the design of high efficiency tuned power oscillator is presented. By employing large-signal S-parameters, theoretical conditions for optimum operation of the oscillator have been formulated and discussed. Loss due to non-zero switching time, saturation resistance etc. of the transistor employed is accounted for. Various oscillators at 900 MHz were designed using the derived theory. Experimental results showed that the measured data are in good agreement with the predicted data View full abstract»

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