[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.
  • 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 history of US presidential elections from Siberian NC point of view

    Publication Year: 1992, Page(s):1000 - 1010 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (416 KB)

    The author discusses the type of neurocomputer (NC) being developed in Krasnoyarsk (by S.E. Gilev, A.N. Gorban, and E.M. Mirkes), described the results of some experiments, and concludes with a discussion on possible future applications of neurocomputers in the social sciences. Tests performed with the program US presidential elections are described View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Some problems of building and learning of neural networks while creating user's expert systems

    Publication Year: 1992, Page(s):1133 - 1135 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (116 KB)

    An experimental confirmation has been obtained of the possibility of neural network expert systems based on learning that uses examples without using any rules of logical deduction. This approach is used in the environment NEXSY, which provides users with the means for expert system creation by themselves. It has been possible to learn the fields of optimal use of algorithms and regimes of neural ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • `Physiological' time in the analysis and modelling of real and artificial neural nets

    Publication Year: 1992, Page(s):226 - 230 vol.1
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (156 KB)

    It is proposed that existing neurobiological data on the properties of single nerve cells and of the systems formed by them will allow, when reproduced in models, a new paradigm of the functioning of neuronal nets, based on the inner time scale concept to be introduced. The concept of inner (physiological) time provides a new approach to modeling processes in neuronal networks. Different inner tim... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The retrieval possibilities of autoassociative networks under variation of the interconnection architecture

    Publication Year: 1992, Page(s):1011 - 1016 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (168 KB)

    The dependence of the main retrieval characteristics of autoassociative neural networks-the memory capacity and the basins of attractors-on the architecture of connections is studied in the framework of the macrodynamical approach. The continuous-time version of the macrodynamical system of equations is analyzed. It is shown that in the limit of diluted connection structure the retrieval possibili... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On neurophysiological mechanism of the puncture therapy

    Publication Year: 1992, Page(s):635 - 637 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (108 KB)

    A possible mechanism for the medical effect of puncture therapy that is based on neurophysiological data, the theory of recognition, and neurocomputing is proposed. It is hypothesized that the structure of the recognition system that is involved should contain a number of plates. A comparison of the morphological, anatomical, and biochemical data allows one to interpret the functions of every plat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A model for active knowledge representation by neural nets and its application

    Publication Year: 1992, Page(s):1136 - 1138 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (88 KB)

    A model for active knowledge representation, planning and decision making by neural nets, and a computer program for play generation based on this model, are described. The model was developed on the basis of J.A. Anderson's (1983) model of cognition and a methodological approach for personality simulation called `artificial metempsychosis' View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Predictive neural clustering system and its applications to bacteria properties predictions

    Publication Year: 1992, Page(s):231 - 241 vol.1
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (408 KB)

    A clustering criterion referred to as the Lakatos criterion is considered. A empty-class prediction approach is developed. Empty class representatives can be considered as predictions generated by the network. This interpretation is used in a predictive neural clustering system which can explore different core neural paradigms able to generate the empty classes. This system has been applied to mic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Encoding of simple two-dimensional visual images

    Publication Year: 1992, Page(s):1017 - 1020 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (112 KB)

    Considers the temporal encoding of visual images, when the distribution of light intensities in the receptive field is converted into a sequence of uniform pulses. The term `simple image' is used to designate an image consisting of a single figure (pattern) against a homogeneous background. The rules governing operation of the functional units of cybernetic systems performing image encoding are co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Structural base of integration in the white rat neuronal complexes of SI barrel cortex

    Publication Year: 1992, Page(s):638 - 640 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (132 KB)

    The general features of dendritic fields of various neurons have been studied by the method of quantitative analysis described by T.A. Leontovich (1978). Three types of neurons were apparent with Golgi staining; all of them were located in the rat barrel field cortex, processing vibrissal information, and differed from one other by the complexity of their integrative functions. The structural pecu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The modified unlearning procedure for enhancing storage capacity in Hopfield network

    Publication Year: 1992, Page(s):242 - 251 vol.1
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (288 KB)

    The authors propose a solvable iterative algorithm of unlearning type for self-correction of Hebbian connectivity. It is shown that, for almost all unlearning sequences, the resulting connection matrix asymptotically converges to the projector matrix. The corresponding convergence rate is calculated and confirmed with numerical simulations View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Information data base on neurocomputers `Neurobank'

    Publication Year: 1992, Page(s):1021 - 1024 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (132 KB)

    An information database on neurocomputers called Neurobank, its purposes, and its subdivision are described. The sources of the information in Neurobank are recently published works on neurocomputers from the Soviet and foreign periodical press and from spectral conferences as well as archives from the 1960s and 1970s. The subdivisions of Neurobank are neutral networks, neuromathematics, neurocomp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Some applications of second-order connectionist networks to speech recognition problems

    Publication Year: 1992, Page(s):94 - 100 vol.1
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (468 KB)

    Second-order connectionist networks have been identified as good models for representing acoustic phonetic invariance, since they can modulate separating hypersurfaces or transform data representations as a function of context. These capabilities are illustrated for two problems in vowel recognition: speaker normalization and phonetic context dependency. The idea of context dependency can also be ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Homogeneous ANN using in image processing and picture generation

    Publication Year: 1992, Page(s):1221 - 1226 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (268 KB)

    A systematic investigation of feasible dynamic structures in homogeneous artificial neural networks (ANNs) with lateral inhibition is presented. The main features may be studied by using a binary (Boolean) net consisting of bistable elements. A two-parameter coupling function describing lateral inhibition is used. It allows one to perform sufficiently complete, analytical ANN research and divide t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Equilibrium states and oscillation of an artificial dynamic neural network

    Publication Year: 1992, Page(s):928 - 939 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (384 KB)

    Some theoretical results related to the behavior of a large collection of neurons composed of two and three families are presented. Each of them is represented by the mean value of the characteristic parameters such as the potential membrane and weights of the connections. Description in the state space has been retained. Attention is given to the determination of the equilibrium states and to the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spatial information processing in higher area of visual system

    Publication Year: 1992, Page(s):641 - 646 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (220 KB)

    A study of receptive fields of neurons of prestriate-cortex cats has shown that they consist of different zones from one to nine. It was also shown that the orientation and spatial-frequency characteristics of different neurons depend on the number of simultaneously stimulated zones, and the properties of different zones depend on the characteristics of different elements in the striate cortex. Ev... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cooperative neural networks underlying image description in visual cortex

    Publication Year: 1992, Page(s):387 - 398 vol.1
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (452 KB)

    Experimental data concerning different types of nonlinear spatial frequency filters in the cat visual cortex are presented. The results of the functional reorganization of the spatial frequency filtering properties of the receptive fields (RFs) are discussed. It is found that cooperative neural nets determine the rules of visual information processing due to the control mechanisms caused by attent... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Formation of pulsed sources in neuro-like media

    Publication Year: 1992, Page(s):521 - 528 vol.1
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (204 KB)

    A model for a neurolike medium with a self-consistent excitation threshold is studied. The action of the second component of the medium leads to the loss of stability by the stationary excitation area which is stable for the U-component. Pulsed structures can appear as a result of the interaction of different moving objects of the medium. Thus, it is shown how quasi-periodic pulsations form from t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An algorithm of selective perception and analysis of environmental information by a neural network under the influence of inner afferentation

    Publication Year: 1992, Page(s):1140 - 1141 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (76 KB)

    The concept of a two-level (cortical and subcortical) four-step algorithm underlying the process of conditional learning has been developed. This algorithm makes use of both the ascending afferent pathways to the cortex and the reverse corticofugal influence on subcortical structures View full abstract»

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