[Proceedings] 1992 RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers

- 1992

Filter Results

Displaying Results 1 - 25 of 150
  • Statistical research and multilayered neural networks

    Publication Year: 1992, Page(s):1172 - 1178 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (309 KB)

    Discusses two possible trends in research into three-layered neural networks synthesized from the paradigm of variable-structure neural networks and used for pattern recognition. These trends are: (i) minimizing the dimension of the space of attributes, and (ii) evaluating the permissible spread in weighting coefficients in order to determine the class of accuracy of electrical parameters of the c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Structure optimization of multilayer neural networks with cross connections

    Publication Year: 1992, Page(s):509 - 520 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (400 KB)

    Problems of choosing the structure (the number of layers and the number of neurons in a layer) for multilayer neural networks with cross connections and consisting of neurons with two lattices are considered for the solution of pattern recognition problems. Consideration is given to multilayer neural networks with complete cross connections where the attribute set of each layer consists of initial... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers (Cat. NO.92TH0483-8)

    Publication Year: 1992
    Request permission for commercial reuse | PDF file iconPDF (35 KB)
    Freely Available from IEEE
  • A multilayer neural adaptive network as a model of nonlinear plants

    Publication Year: 1992
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (45 KB)

    Summary form only given. A multilayer neural adaptive network is chosen as a model for complex nonlinear plants. The basic element of the neural network (NN) is the sigmoid perceptron. The tuning of NN weights is based on measurements of the vector input and output of a nonlinear plant, the output of which is affected by an additive random noise. Optimal convergence rate algorithms for tuning the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On a possible creative neurocomputer system

    Publication Year: 1992
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (54 KB)

    Summary form only given. It is suggested that one way to develop neural net computer systems may be through the use of the computer as a generator but not as a transformer of information. The core of these hypothetical computer systems must consist of two functional modules: a knowledge generator, based on the physical dissipative process, and a transformer of information into a structural form si... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Influence of stimuli on the comportment of an artificial neural population

    Publication Year: 1992, Page(s):846 - 854 vol.2
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (416 KB)

    The dynamic behavior (comportment) of an artificial neural network depends not only on the synaptic weights, but also on the stimuli input. Without stimuli, the network stable state is permanent or oscillatory. The external stimuli input modifies the neural state, changing it from one stable permanent state to another or from an oscillatory to a permanent state, or changing the frequency of oscill... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The new nondeterministic model of sigmoidal neural network

    Publication Year: 1992, Page(s):836 - 845 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (364 KB)

    A new way to derive an artificial neural network of sigmoidal neurons from a nondeterministic model of logic circuits is presented. It can be used to classify the behavior of biological neural nets and of methods for synthesising fuzzy integrated-circuit chips. Some results of a computer simulation of a sigmoidal network from logic elements are examined. The most promising feature of the proposed ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • When algorithms became local: solving computational geometry problems on neural networks

    Publication Year: 1992, Page(s):1044 - 1055 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (384 KB)

    Optimal local parallel algorithms for computing the Voronoi diagram, Delaunay triangulation, the Gabriel graph, the relative neighborhood graph, the influence graph, the minimal spanning tree, and other structures over a finite planar set are presented. The parallel algorithms offered are intended for realization in a cellular automata processor View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A set of travelling fronts of excitation in the model of homogeneous neuro-like medium with nonlocal coupling

    Publication Year: 1992, Page(s):855 - 864 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (312 KB)

    The influence of arbitrary nonlocal coupling on the existence and properties of autowave processes in a bistable medium is investigated. Approximation of the individual activity function F(x) by a Heaviside unit function allows one to obtain some analytical results. The calculations clearly testify to the relation between the instability of the plane front of excitation, observed by A.V. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distinguishing line-detection from texture segregation using a modular network-based model

    Publication Year: 1992, Page(s):411 - 413 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (220 KB)

    In order to enable task-dependent processing of lines, edges, and textures, the authors introduce a network-based model for the front-end visual system. The purpose of this model is to provide different representations of a retinal image in such a way that different actions and decisions about the presence of objects in the visual scene can be undertaken at a further stage. In particular, as a sta... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network for image Fourier transform classification

    Publication Year: 1992, Page(s):196 - 207 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (360 KB)

    Considers the performance of a neural-network (NN)-based visual control system with NNs of different types (multilayered perceptrons and Hamming nets). They discuss the possible compensation of disturbances arising in a coherent-optical processor by NN learning. Simulation shows that different NNs have different behaviors for two types of input distorted data: the perceptron NN is more suitable fo... View full abstract»

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

    Publication Year: 1992, Page(s):1056 - 1067 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (364 KB)

    It is necessary to introduce many parameters describing the structure and input signal of a pattern recognition system during the construction of open-loop structures of multilayer neural networks in order to provide maximum probability of correct recognition in practice. The availability of a large number of parameters, i.e., hundreds and thousands, poses some difficulties for learning and for th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A bibliographic data base `Neural Networks and Neurocomputers'

    Publication Year: 1992, Page(s):1125 - 1126 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (88 KB)

    A neural networks and neurocomputers database at Moscow University containing about 7000 references is ready for use. The earliest works date from the 1940s and the latest ones reflect the present status of investigations. The database includes publications on mathematical and computer simulation studies of properties of neural network schemes, biological investigations explicitly using connection... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A model of the neural network for storage and retrieval of temporal sequences

    Publication Year: 1992, Page(s):865 - 869 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (128 KB)

    A novel method for the storage and the retrieval of temporal sequences of frames (neural movies) using the backpropagation learning procedure is proposed. The strengths of the connections in the network are adjusted during learning to store the various sequences. The neural network is able to repeat periodically during retrieval one sequence of frames from the recorded set. A simulation model was ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Structure of neural assembly

    Publication Year: 1992, Page(s):423 - 434 vol.1
    Cited by:  Papers (1)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (484 KB)

    The process of neural assembly formation in neural networks with a low level of activity is investigated. The experiments conducted show the possibility of forming neural assemblies with nucleus and fringe and of restoring both the nucleus and the nucleus with fringe. This proves that the neural network has additional functions: to form prototypes and to restore the assembly nucleus and assembly f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An articulatory-formant speech synthesizer via a neural network

    Publication Year: 1992, Page(s):13 - 24 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB)

    An articulatory-formant synthesizer oriented toward implementation by a neural network is proposed. Speech output is the sum of the formant filters' responses terminated by an appropriate source of excitation. A model of articulatory dynamics is adopted for the synthesizer. A fast procedure for eigenfrequency calculation which makes it possible to reduce the computational cost in the synthesis to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Anthropomorphic neuropreprocessing for visual interface

    Publication Year: 1992, Page(s):208 - 218 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (324 KB)

    A functional description of the Image Preprocessing Anthropomorphic System (IPPAS) is presented. IPPAS's ability to correctly represent the basic threshold characteristics of human vision in the space, spatial-frequency, luminance, and time domains is shown. IPPAS is based on a functional threshold vision model proposed by the author View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Methods for solving of differential equations in neural basis

    Publication Year: 1992, Page(s):919 - 927 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (236 KB)

    Several new methods for solving ordinary differential equations of first order are considered. These methods are intended for use on a neural network. These methods have several merits compared to traditional numerical methods. A method for solving differential equations on the Hopfield network and an iterative method for solving differential equations are described View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of neural networks to fluorescent diagnostics of organic pollution in natural waters

    Publication Year: 1992, Page(s):763 - 773 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (412 KB)

    A neural net has been used to build a sea water express-diagnostics system that does not require an expert's participation. The network can classify sea water pollution on the basis of its total luminescent spectrum. A typical minimal detectable PSP (pollutant's spectrum portion) value is 0.2; this value corresponds to a concentration of 0.5-10 p.p.m. for dissolved organic matter (DOM) in water (1... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Information criteria for a sound source localization by human

    Publication Year: 1992, Page(s):113 - 119 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (184 KB)

    An information measure is suggested for analysis of sound source localization efficiency by humans. Using this measure, the influence of signal-to-noise ratio, observation time, and frequency analysis bandwidth is studied, as well as the presence of a local source of interference. The proposed information measure can be used for working out models of the human auditory system, especially in solvin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neuron network for low-level vision: texture segmentation

    Publication Year: 1992, Page(s):1068 - 1074 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (172 KB)

    An approach to low-level-vision neural net modeling which is based on the works of N.V. Pozin et al. (1978) on simulation of peripheral neuron structures in the auditory and visual system is proposed. The four-layered neural net described has two modes of processing: texture segmentation of images of visual scenes and extraction of texture boundaries of the images. The efficiency of the neural net... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the transfer function of macro-neuron

    Publication Year: 1992, Page(s):1127 - 1132 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (184 KB)

    In artificial intelligence models which are characterized by large volumes of associative memory, it is very important to find a compact description of the memory elements, while preserving the neural logic. The authors describe results of a numerical experiment which shows a way to correctly replace neurons by macro-neurons (ensembles) View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The project of a parallel computer for hardware support of processing semantic and neural networks

    Publication Year: 1992, Page(s):623 - 634 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB)

    The project described results from research on models of knowledge representation by means of semantic networks. As a result, the knowledge representation language SCL (Semantic Code Language) has been developed. Its texts are semantic networks and its representational and operational capabilities highly exceed those of similar languages based on first-order logic. The number of knowledge processi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neuronal net coordinating varying gaits and walk cycle phases in polypods

    Publication Year: 1992, Page(s):990 - 993 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (124 KB)

    A neuronal net which provides coordination for a certain gait and for separate phases of the walking cycle, and which ensures an appropriate functional order (phase relations corresponding to normal walking in polypods), is discussed. The intersegmental neuronal subnet generates temporal windows during which this or that limb may be moved to another position (the swing phase in the step cycle). At... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A model of wave associative processing

    Publication Year: 1992, Page(s):870 - 880 vol.2
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (280 KB)

    A novel approach to the design of devices demonstrating the behavior of biological organisms that can be based on the associative memory mechanism is presented. A model of associative memory is proposed in which the dependent number of memory elements linearly increases with the number of medium elements, and every element of the medium is impressed with the activities of all the other elements. T... View full abstract»

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