Neural Networks, 1999. IJCNN '99. International Joint Conference on

Volume 6 • 10-16 July 1999

Go

Filter Results

Displaying Results 1 - 25 of 147
  • IJCNN '99 [front matter]

    Publication Year: 1999, Page(s):i - iv
    Request permission for commercial reuse | PDF file iconPDF (2679 KB)
    Freely Available from IEEE
  • A generation method of substantially seeded rights unbalancing in a tournament-type match table by the frame of balanced 2-3-4 trees structure

    Publication Year: 1999, Page(s):3717 - 3721 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (473 KB)

    A tournament-type match table has been widely employed to decide the winner of games. In the case of a balanced table, participants can win after the same number of games, or one time less, depending on the number of participants. Spectators want to watch good exciting games, especially in semi-finals and the final, so powerful participants are given seeded rights in the table. Powerful participan... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An adaptive neural network approach to hypertext clustering

    Publication Year: 1999, Page(s):3722 - 3726 vol.6
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (558 KB)

    The WWW is an online hypertextual collection, and a more sophisticated algorithm for Web page clustering may have to be based on combined term-similarity and hyperlink-similarity measures. It has been observed that nearly all currently employed techniques for document classification on the Web make use of textual information only. In addition, most of these techniques are incapable of discovering ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applications of multilayer feedforward networks on WWW document search

    Publication Year: 1999, Page(s):3727 - 3729 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (270 KB)

    In this paper, we study the problem of designing intelligent World Wide Web document search engines with multilayer feedforward networks. We introduce an innovative application of multilayer feedforward networks on designing intelligent search engine. We give a bound on the number of trials needed to search for any collection of documents represented by a disjunction of discretized attributes. View full abstract»

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

    Publication Year: 1999, Page(s):3730 - 3733 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (338 KB)

    In this paper, three types of chess endgames were studied and three layer feedforward neural networks were applied to learn the hidden rules in chess endgames. The purpose of this paper is to convert the symbolic rules of chess endgames into numerical information that neural networks can learn. The neural networks have been proved efficient in learning and playing some simple cases of chess endgam... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TD methods applied to mixture of experts for learning 9/spl times/9 Go evaluation function

    Publication Year: 1999, Page(s):3734 - 3739 vol.6
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (479 KB)

    The temporal difference (TD) method is applied on a committee of neural network experts to learn the board evaluation function for the oriental board game Go. The game has simple rules but requires complex strategies to play well, and the conventional tree search algorithm for computer games makes a poor Go program. Thus, the game Go is an ideal problem domain for exploring machine learning algori... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The scout cluster architecture for cognitive computing

    Publication Year: 1999, Page(s):3740 - 3744 vol.6
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (447 KB)

    In this paper, the scout cluster is introduced as a processing architecture capable of developing rapid solutions to difficult cognitive problems. Most cognitive problems have a non-deterministic aspect to them, making the discovery of an efficient algorithm for their solution difficult or impossible. Scouting performs rapid parallel searches in hardware in an uncoordinated manner that makes it al... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Solving jigsaw puzzles using Hopfield neural networks

    Publication Year: 1999, Page(s):3745 - 3749 vol.6
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (366 KB)

    We show that an intelligent system can be developed to solve the jigsaw puzzles problem using neural networks. More specifically, we employ the Hopfield neural networks to perform the matching of outer contours of the puzzle pieces. Although we consider matching puzzle pieces, a similar technique can be employed to solve related practical problems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neuro-based optimization algorithm for tiling problems with rotation

    Publication Year: 1999, Page(s):3750 - 3753 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    This paper describes a neuro-based optimization algorithm for 2D tiling problems which are to pack a checkerboard with polyominoes. First, we review the previous neuro-based parallel algorithms for filing problems without rotation. Next, we expand the algorithm, which has been proposed for 2D tiling problems without rotation, to the optimization one for 2D tiling problems with rotation, where a no... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cellular neural networks for information storage and retrieval: a new design method

    Publication Year: 1999, Page(s):3754 - 3757 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (239 KB)

    In this paper a new approach to information storage and retrieval using cellular neural networks is developed. The objective is achieved by considering a suitable discrete-time model of these networks and by designing them so that the input information are fed via external inputs rather than initial conditions. The technique, which exploits globally asymptotically stable networks, leads to a facil... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The impulse response of BP neural networks and its application to seismic wavelet extraction

    Publication Year: 1999, Page(s):3758 - 3761 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (306 KB)

    Artificial neural networks (ANNs) are increasingly being applied in geophysical data interpretation largely due to the fact that they have been shown to be universal function approximators. However, as ANNs act like "black boxes", there is concern about their reliability. An understanding of the learning of BP neural networks for certain kinds of function approximation can be archived by utilizing... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network for seismic principal components analysis

    Publication Year: 1999, Page(s):3762 - 3767 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (686 KB)

    The neural network using an unsupervised generalized Hebbian algorithm (GHA) is adopted to find the principal eigenvectors of a covariance matrix in different kinds of seismograms. We have shown that the extensive computer results of the principal components analysis (PCA) using neural net of GHA can extract the information of seismic reflection layers and uniform neighboring traces. The analyzed ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An infrasonic event neural network classifier

    Publication Year: 1999, Page(s):3768 - 3773 vol.6
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (553 KB)

    An integral part of the Comprehensive Nuclear Test Ban Treaty International Monitoring System is an infrasonic monitoring network that is capable of detecting and verifying nuclear explosions. Reliable detection of such events must be made from data that may contain other sources of infrasonic phenomena, such as volcano eruptions, mountain associated waves (MAW), gravity waves, and microbaroms, to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using NNs to retrieve multiple geophysical parameters from satellite data

    Publication Year: 1999, Page(s):3774 - 3778 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    A new approach in satellite retrievals, multi-parameter empirical retrievals, is introduced. It is shown that single-parameter retrievals, compared with multi-parameter retrievals, contain significant additional "artificial" systematic and random errors. These errors may be avoided using multi-parameter retrieval algorithms. Neural networks (NNs) are well suited for developing such multi-parameter... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • DeepNet: an ultrafast neural learning code for seismic imaging

    Publication Year: 1999, Page(s):3779 - 3784 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (574 KB)

    A feedforward multilayer neural net is trained to learn the correspondence between seismic data and well logs. The introduction of a virtual input layer, connected to the nominal input layer through a special nonlinear transfer function, enables ultrafast (single iteration), near-optimal training of the net using numerical algebraic techniques. A unique computer code, named DeepNet, has been devel... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network system for cloud classification from satellite images

    Publication Year: 1999, Page(s):3785 - 3790 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (649 KB)

    Highly accurate, automated cloud detection and classification methods are essential for processing multispectral meteorological satellite in an operational environment and providing data for meteorological and climatological studies. They help to discover hazardous meteorological phenomena such as hail storms developing on tops of clouds, hurricanes and cyclones. Weather prediction and rainfall es... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison of two different PNN training approaches for satellite cloud data classification

    Publication Year: 1999, Page(s):3791 - 3795 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (496 KB)

    This paper presents a new training algorithm for probabilistic neural networks (PNNs) using the minimum classification error (MCE) criterion. A comparison is made between the MCE training scheme and the widely used maximum likelihood learning on a cloud classification problem using satellite imagery data. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical neural network approach to ocean colour extraction from remotely sensed imagery

    Publication Year: 1999, Page(s):3796 - 3801 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (760 KB)

    Radiative transfer algorithms in combination with empirical formulae have been the most popular approach to the analysis of oceanic water types from remotely sensed satellite images of the Earth. These methods produce occasional errors created by unstable atmospheric components and disable monitoring of coastal zones. As the assumptions on sensor. Earth surface and atmospheric interaction with ele... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time short-term natural water inflows forecasting using recurrent neural networks

    Publication Year: 1999, Page(s):3802 - 3805 vol.6
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (349 KB)

    Accurate, time and site-specific forecasts of natural inflows into hydropower reservoirs are highly important for operating and scheduling. This paper investigates the effectiveness of recurrent neural networks (RNN) for real-time short-term natural water inflows forecasting. The models use antecedent inflows and precipitation data, and actual weather descriptors to generate short-term (1-7 days a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network technology for strata strength characterization

    Publication Year: 1999, Page(s):3806 - 3809 vol.6
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (326 KB)

    The process of drilling and bolting the roof is currently one of the most dangerous jobs in underground mining, resulting in about 1,000 accidents with injuries each year in the United States. To increase the safety of underground miners, researchers from the Spokane Research Laboratory of the National Institute for Occupational Safety and Health are applying neural network technology to the class... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural nets and star/galaxy separation in wide field astronomical images

    Publication Year: 1999, Page(s):3810 - 3815 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    One of the most relevant problems in the extraction of scientifically useful information from wide field astronomical images (both photographic plates and CCD frames) is the recognition of the objects against a noisy background and their classification in unresolved (starlike) and resolved (galaxies) sources. In this paper we present a neural network based method capable to perform both tasks and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluation and identification of lightning models by artificial neural networks

    Publication Year: 1999, Page(s):3816 - 3820 vol.6
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (337 KB)

    This paper describes a novel approach for mapping lightning models using artificial neural networks. The networks acts as identifier of structural features of the lightning models so that output parameters can be estimated and generalised from an input parameter set. Simulation examples are presented to validate the proposed approach. More specifically, the neural networks are used to compute elec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiplicative-additive neural networks with active neurons

    Publication Year: 1999, Page(s):3821 - 3823 vol.6
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (250 KB)

    An artificial neural network is a flexible mathematical structure which is capable of identifying complex nonlinear relationships between input and output data sets. Such neural networks have been characterized by passive neurons that are not able to select and estimate their own inputs. In a new approach, which corresponds in a better way to the actions of human nervous system, the connections be... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated galaxy classification in large sky surveys

    Publication Year: 1999, Page(s):3824 - 3829 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (717 KB)

    Current efforts to perform automatic galaxy classification using artificial neural network image classifiers are reviewed. For both digitized photographic Schmidt plate data and newly obtained WEPC2 images from the Hubble space telescope, a variety of 2D photometric parameter spaces produce a segregation of galaxy Hubble types. Through the use of hidden node layers, a neural network is capable of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sensitivity analysis, neural networks, and the finance

    Publication Year: 1999, Page(s):3830 - 3835 vol.6
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (563 KB)

    The paper investigates whether the sensitivity analysis can be used not only as a tool to read the knowledge embedded in artificial neural networks (ANNs), but also as a tool to evaluate the effectiveness of ANN learning. The simulation of the Black-Scholes formula is employed for this object. The Black-Scholes formula, in which the mapping between the call price and five relevant variables is a m... View full abstract»

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