By Topic

[Proceedings] 1991 IEEE International Joint Conference on Neural Networks

18-21 Nov. 1991

Filter Results

Displaying Results 1 - 25 of 444
  • Operational fault tolerance of the ADAM neural network system

    Publication Year: 1991, Page(s):1 - 6 vol.1
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (357 KB)

    The author investigates the fault tolerance of the Advanced Distributed Associative Memory (ADAM), focusing on its operational use. The effect of the reliability of recall of variously configured ADAM systems is examined by injecting faults individually, and also in various combinations since correlations between them will influence their overall effect on the system. Analysis of the results indic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 1991 IEEE International Joint Conference on Neural Networks (Cat. No.91CH3065-0)

    Publication Year: 1991
    Request permission for commercial reuse | PDF file iconPDF (47 KB)
    Freely Available from IEEE
  • Neural activities and cluster-formation in a random neural network

    Publication Year: 1991, Page(s):2156 - 2161 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    An approach to a macroscopic description of a cluster-formation algorithm by neural activities in a random neural network is considered. The activity interaction between clusters of neurons and the network entropy through the medium of the activity parameter x(p ) for the input pattern p, are introduced as a system energy. By using the neural state transition rule simila... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of neural sequential associator to long-term stock price prediction

    Publication Year: 1991, Page(s):1196 - 1201 vol.2
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB)

    A neural sequential associator using feedback multilayer neural networks in duplicate is proposed to analyze the inherent structure in the sequence and to predict the future sequence based on this structure. It is shown that the present method gives a better performance than that of neural networks without feedback when applied to the prediction of long-term stock prices View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural searchlight processor that differentiates any images with common features by transitory synchronization

    Publication Year: 1991, Page(s):2150 - 2155 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (244 KB)

    The neural cocktail-party processor (NCPP) is known as a theoretical model of the visual binding by coherent oscillation of neurons, a hypothesis that transitory synchronization of neuronal activities might link fragmentarily represented visual information in the widely spaced areas of the brain to establish coherent images. However, NCPP was made under an assumption that the images to be recogniz... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Control of a robotic manipulating arm by a neural network simulation of the human cerebral and cerebellar cortical processes

    Publication Year: 1991, Page(s):1444 - 1447 vol.2
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (188 KB)

    The authors propose a system commanding a robotic manipulating arm under visual control, based on brain modeling. In this model, the movement command is learned by a network which links two subsystems together: a cerebral subsystem which can learn a goal, and a second subsystem responsible for quantitative adjustments and coordination. Those two subsystems are complementary because each subsystem ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Inverse nonlinear control using neural networks

    Publication Year: 1991, Page(s):2098 - 2103 vol.3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (224 KB)

    A strategy for controlling a class of nonlinear dynamical systems using techniques based on neural networks is presented. The inverse nonlinear controller using neural networks is called the INC/NN controller. Properties of the controller are discussed, and results of some real-time experiments in applying the proposed INC/NN controller to a position control system with inherent nonlinearities are... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An object-oriented neural network language

    Publication Year: 1991, Page(s):1606 - 1611 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (280 KB)

    The author points out that there are many commonalities of neural network and object-oriented methodology, and gives an informal overview of the object-oriented neural network language (OONNL), specifically designed for the neurocomputer (software simulation/hardware implementation). It is a procedural and general-purpose language, which allows parallelism via the object-oriented concept. The para... View full abstract»

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

    Publication Year: 1991, Page(s):1641 - 1646 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    A novel structured backpropagation network is described. It is different from the classic network as it requires prior knowledge of the problems that the network is dealing with by constructing an appropriate structure to match the problem. This approach can reduce training time and minimize the convergent problems that exist in the classic approaches. This new hybrid network architecture is super... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Software engineering effort models using neural networks

    Publication Year: 1991, Page(s):1190 - 1195 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (312 KB)

    The authors discuss and demonstrate the use of neural network (NN) techniques for constructing software engineering effort models using the backpropagation and self-organizing neural network (SONN) algorithms. NN models have some important properties which are advantageous in this context, including the distribution free property, the learning capability, and the ease of parallel implementations. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Time series prediction with linear and nonlinear adaptive networks

    Publication Year: 1991, Page(s):379 - 384 vol.1
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (268 KB)

    Backpropagation networks with a single hidden layer were trained to perform one-step prediction on a variety of scalar time series. The performance of such nets typically equals or exceeds that of the linear adaptive predictor of the same order. Comparisons of the linear and nonlinear predictors were made with periodic, chaotic, and random time series, including broadband ocean acoustic ambient no... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Least MSE reconstruction for self-organization. II. Further theoretical and experimental studies on one-layer nets

    Publication Year: 1991, Page(s):2368 - 2373 vol.3
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (440 KB)

    For pt.I, see ibid., pp. 2362-2367 (1991). The one-layer case of a new self-organizing network is studied. The net is based on using the least mean square error reconstruction (LMSER) principle for guiding learning which results in a local learning rule denoted by LMSER. It is proven that for one layer with n1 linear units, the LMSER rule will let their weight vectors converge ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vowel recognition by a neural network using vocal tract area function

    Publication Year: 1991, Page(s):2144 - 2149 vol.3
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (144 KB)

    A new system for vowel recognition by a neural network using the vocal tract area function is developed. A method by which the vocal tract area function is directly estimated from speech waves is presented. The effect of the adaptive inverse filter is given to autocorrelation coefficients directly, which reduces the computation time to about 30% of that necessary for the conventional method. A neu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A study of human hand position control learning-output feedback inverse model

    Publication Year: 1991, Page(s):1434 - 1443 vol.2
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (464 KB)

    The acquisition of an inverse-kinematic model is required for motor control in humans. With the direct inverse modeling method that is a conventional method, a sufficient inverse model cannot be obtained when the input and output correspondence of the target system is not one-to-one and is non-linear. The problem is seeking the inverse-kinematic model of the human arm, including a wrist, falls int... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network to support unstructured economic decision process

    Publication Year: 1991, Page(s):2092 - 2097 vol.3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (280 KB)

    The authors use an artificial neural network to support unstructured economic decision processes. Based on the features of the economic decision process and the weaknesses of the error backpropagation algorithm, they derived an improved backpropagation algorithm and applied it in a macroeconomic evaluation decision process, with better results. The improved error backpropagation algorithm overcome... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive decision-feedback equalization of digital transmission channels using forward-only counterpropagation networks

    Publication Year: 1991, Page(s):220 - 225 vol.1
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (240 KB)

    An application of the forward-only counterpropagation network (FCPN) is proposed for nonlinear equalization of digital transmission channels. The learning mechanism of the FCPN is a combination of unsupervised self-organization and supervised training. A decision-feedback equalizer (DFE) based on FCPN was simulated on a digital computer. The results of the simulation demonstrate a superior bit-err... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A face graph method using a fuzzy neural network for expressing conditions of complex systems

    Publication Year: 1991, Page(s):1600 - 1605 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (248 KB)

    The face graph method with such varying elements as dyes, eyebrows, mouth, etc. is used for expressing multidimensional data. Since human beings are very sensitive to human faces, one can easily evaluate the multidimensional data expressed by the face graph. The authors present a novel approach of the face graph method using a fuzzy neural network for expressing conditions of complex systems. Expe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Weight value initialization for improving training speed in the backpropagation network

    Publication Year: 1991, Page(s):2396 - 2401 vol.3
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (216 KB)

    A method for initialization of the weight values of multilayer feedforward neural networks is proposed to improve the learning speed of a network. The proposed method suggests the minimum bound of the weights based on dynamics of decision boundaries, which is derived from the generalized delta rule. Computer simulation in several neural network models showed that the proper selection of the initia... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hardware requirements to digital VLSI implementation of neural networks

    Publication Year: 1991, Page(s):1873 - 1878 vol.3
    Cited by:  Papers (2)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (308 KB)

    The authors focus on efficient implementation of artificial neural networks by means of digital VLSI hardware. They tackle the issue of hardware constraints, such as weights and states precision, finite arithmetic, and activation function realization. The emphasis is on the digital implementation of the learning phase and backpropagation networks. A new theorem is presented, which states the preci... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A constant-time neural network for multiple selection

    Publication Year: 1991, Page(s):1184 - 1189 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (356 KB)

    A MAXNET with constant-time response and with multiple selection of several maximum values, CTMAXNET, is presented. The constant-time response for CTMAXNET is proved. A cost analysis of VLSI implementation for CTMAXNET is presented, and it is shown that CTMAXNET has a smaller cost than MAXNET. From the example of ART1, it is shown that including MAXNET leads to misclassification while including CT... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A dynamical network capable of storing sequences of static or periodic patterns

    Publication Year: 1991, Page(s):373 - 378 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (264 KB)

    The author proposes a modification of the neural network model of B. Baird (1988,1989) in which the constraint of symmetrical interaction between the modes representing the patterns stored is eliminated. This makes it possible to construct the system with the ordered transitions between the patterns which were the stable attractors in the original model. Although in this case there is no strict ev... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An implementation of short-timed speech recognition on layered neural nets

    Publication Year: 1991, Page(s):2228 - 2234 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (276 KB)

    The authors show a new way to handle the sequential nature of speech signals in multilayer perceptrons (MLPs) or other neural net machines. A static model in the form of state transition probability matrices representing short speech units such as syllables which correspond to Chinese utterances of isolated characters were adopted and as learning patterns for MLPs. The network architecture and lea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Least MSE reconstruction by self-organization. I. Multi-layer neural-nets

    Publication Year: 1991, Page(s):2362 - 2367 vol.3
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (364 KB)

    A self-organizing net based on the least mean square error reconstruction (LMSER) principles is proposed, which produces a local learning rule. The author introduces the architecture of this multilayer net, proves the stability of its dynamic process in the perception phase, and derives the local learning rule which performs gradient descent of the least MSE of the reconstruction. It is shown that... View full abstract»

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

    Publication Year: 1991, Page(s):128 - 133 vol.1
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (284 KB)

    The high degree complexity of the features associated with a unit in neural networks suggested that the introduction of fuzziness into the activity of the unit would be appropriate. It is demonstrated that the idea of imprecise distinction between excitation and inhibition can be manipulated easily by fuzzy activation functions. A mathematical formulation of fuzzy activation functions, which are g... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Inherent structure detection by neural sequential associator

    Publication Year: 1991, Page(s):2140 - 2143 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (216 KB)

    A sequential associator based on a feedback multilayer neural network is proposed to analyze inherent structures in a sequence generated by a nonlinear dynamical system and to predict a future sequence based on these structures. The network represents time correlations in the connection weights during learning. It is capable of detecting the inherent structure and explaining the behavior of system... View full abstract»

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