By Topic

1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227)

4-9 May 1998

Go

Filter Results

Displaying Results 1 - 25 of 158
  • The 1998 IEEE International Joint Conference on Neural Networks Proceedings [front matter]

    Publication Year: 1998, Page(s):i - xxxvi
    Request permission for commercial reuse | PDF file iconPDF (2194 KB)
    Freely Available from IEEE
  • Author's index

    Publication Year: 1998, Page(s): A
    Request permission for commercial reuse | PDF file iconPDF (466 KB)
    Freely Available from IEEE
  • Image recognition using fractal parameters

    Publication Year: 1998, Page(s):1883 - 1888 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (352 KB)

    Concerns the applications of fractal theory to image recognition and we propose the method that can enhance learning rate and recognition rate by using fractal parameters that are composed of input vectors for a neural network in an image recognition model. Fractal parameters with the properties of self-similarity and recursiveness can recover lossless original images through iterating processes. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neuro-fuzzy posture estimation for visual vehicle guidance

    Publication Year: 1998, Page(s):2086 - 2091 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (708 KB)

    This paper presents a neuro-fuzzy approach to visual guidance of a mobile robot vehicle in local manoeuvres. It is based on the transfer of the skills of an experienced driver to an automatic controller. The resulting controller processes video sensor data to generate corresponding steering and velocity commands in real time. Neither a geometric environment model nor analytic models of the video s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • BYY dependence reduction theory and blind source separation

    Publication Year: 1998, Page(s):2495 - 2500 vol.3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (560 KB)

    Bayesian Ying-Yang dependence reduction (BYY-DR) system and theory is introduced, together with a generic stochastic implementing procedure and a generic model selection criterion. Their specific forms in the forward, backward, bi-directional architectures are further elaborated. The forward one provides a general information theoretic DR scheme, which is applied to blind source separation (BSS) p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-organization, scaling, and parallelism

    Publication Year: 1998, Page(s):2039 - 2044 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (884 KB)

    The problem of learning in the absence of external intelligence is discussed in the context of a simple model. The model departs from the traditional gradient-descent based approaches to learning by operating at a highly susceptible “critical” state, with low activity and sparse connections between firing neurons. Quantitative studies in the context of two simple association tasks demo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scene segmentation in video sequences by an RPCL neural network

    Publication Year: 1998, Page(s):1877 - 1882 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (396 KB)

    Video database management systems require efficient methods to abstract video information. Identification of shots in a video sequence is an important task for summarizing the content of a video. We describe a neural network based technique for automatic clustering of video frames in video sequences. From each frame the features that describe the image content are extracted to form a signature. Th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robot path planning for maze navigation

    Publication Year: 1998, Page(s):2081 - 2085 vol.3
    Cited by:  Papers (9)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (408 KB)

    This paper presents the application of multilayer perceptrons to the robot path planning problem, and in particular to the task of maze navigation. Previous published results implied that the training of feedforward multilayered networks failed, because of the nonsmoothness of data. Here the same maze problem is revisited View full abstract»

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

    Publication Year: 1998, Page(s):2419 - 2424 vol.3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (448 KB)

    A new neural network model of a commercial SCD elevator is proposed. The main goal of the research project is to improve elevator ride comfort via speed profile design. The main objective in modeling is to obtain a good and reliable tool for process analysis and control system development. The work consists of measurement and filter planning as well as actual model identification. Much emphasis is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A two-observation Kalman framework for maximum-likelihood modeling of noisy time series

    Publication Year: 1998, Page(s):2489 - 2494 vol.3
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    Modeling a noisy time series requires the dual estimation of both the model parameters and the underlying clean time series. Most approaches estimate the model parameters by minimizing the mean squared prediction error, but estimate the time series by minimizing another cost function. We justify the use of the same maximum-likelihood cost for both parameter and time series estimation, and present ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modular SRV reinforcement learning: an architecture for nonlinear control

    Publication Year: 1998, Page(s):2034 - 2038 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    Demonstrates the application of a hybrid reinforcement-modular neural network architecture to nonlinear control problems. Specifically, the method of action-critic reinforcement learning, modular neural networks, and winner-takes-all updating are combined. This provides an architecture able to both support temporal difference learning, and probabilistic partitioning of the input space. Furthermore... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimal feedback controller approximation using neural networks and nonlinear programming techniques

    Publication Year: 1998, Page(s):2110 - 2115 vol.3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB)

    A direct method for creating a neural network to approximate an optimal feedback controller is presented in this paper. The method is direct in the sense that the weight adaptation is tied directly to the solution of the optimal control problem. To achieve this goal, the optimal control problem is first converted into a parameter optimization problem with the weights and biases of the network bein... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identifying part-of-speech patterns for automatic tagging

    Publication Year: 1998, Page(s):1873 - 1876 vol.3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (244 KB)

    Some part-of-speech tagging errors are very damaging to the ability to further process the text. For systems that use part-of-speech tagging as a prelude to parsing and knowledge extraction, it is imperative to have the cleanest possible tagging. A state-of-the-art rule-based tagger has an error rate of approximately 39% when annotating main verbs that have not been previously seen. We apply neura... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of table-form documents using high order correlation method

    Publication Year: 1998, Page(s):1851 - 1856 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB)

    Table-form document recognition has many applications in office automation. An algorithm is proposed in the paper for automatic form processing. A high order correlation method was originally developed for point target detection in three-dimensional space. It computes the spatio-temporal cross-correlations of consecutive data to extract track information in series of images. It was shown that the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive learning rate and limited error signal for multilayer perceptrons with n-th order cross-entropy error

    Publication Year: 1998, Page(s):2357 - 2360 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (308 KB)

    Although an n-th order cross-entropy (nCE) error function resolves the incorrect saturation problem of conventional error backpropagation algorithm, the performance of multilayer perceptrons (MLPs) using the nCE function depends heavily on the order of nCE. In this paper, we propose an adaptive learning rate to make the MLP performance insensitive to the order of nCE. Additionally, we propose a me... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling gait transitions of quadruped based on gait kinematics and CMAC neural networks

    Publication Year: 1998, Page(s):2075 - 2080 vol.3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (488 KB)

    The gait transition models of a quadruped are studied based on gait kinematics and CMAC neural networks are applied to learn and generalize these gait transition models. Three gait transition cases are studied: from wave gait to continuous follow-the-leader gait, from walk to trot, and from trot to gallop. Four solution methods are proposed for solving the gait transition models. Computer simulati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network complexity classification based on the problem

    Publication Year: 1998, Page(s):2413 - 2418 vol.3
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (544 KB)

    This paper presents a complexity power study of different artificial neural networks (ANNs) structures, specifically the feedforward and the recurrent neural networks. We use the `order of a predicate' concept to classify a problem in a given class and show that the neural network structure, determined by its topology (direct or recurrent) and the presence or absence of hidden neurons, must be con... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ATM call admission control using sparse distributed memory. II

    Publication Year: 1998, Page(s):1799 - 1803 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (352 KB)

    For pt.I see ICNN'97, vol.2, p.1321-5 (1997). Call admission control (CAC) is a key technology of ATM network traffic control. It should be adaptable to the rapid and various changes of the ATM network environment. Conventional approach to the ATM CAC requires network analysis in detail in all cases. The optimal implementation is said to be very difficult. Therefore, a neural approach has been emp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural learning of chaotic dynamics: the error propagation algorithm

    Publication Year: 1998, Page(s):2483 - 2488 vol.3
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (600 KB)

    An algorithm is introduced that trains a neural network to identify chaotic dynamics from a single measured time-series. The algorithm has four special features: the state of the system is extracted from the time-series using delays, followed by weighted principal component analysis data reduction; the prediction model consists of both a linear model and a multi-layer-perceptron; the effective pre... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A quasi-local Levenberg-Marquardt algorithm for neural network training

    Publication Year: 1998, Page(s):2242 - 2246 vol.3
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (356 KB)

    Although the Levenberg-Marquardt algorithm has been extensively used as a neural network training method, it suffers from being very expensive, both in memory and number of operations required, when the network to be trained has a significant number of adaptive weights. In this work we propose a modification of this method that considers the concept of neural neighbourhoods. It is shown that, by p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Probabilistic neural networks for multi-user detection in code divisional multiple access communication channels

    Publication Year: 1998, Page(s):2557 - 2560 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (472 KB)

    A probabilistic neural network is proposed and applied for implementation of a maximum likelihood detector and classifier. The network is trained using the algorithm based on Parzen probability density function estimation theory for detection of signals in CDMA multi-user communications Gaussian channel. By viewing these multi-user detector's problem as a nonlinear classification decision problem,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TD based reinforcement learning using neural networks in control problems with continuous action space

    Publication Year: 1998, Page(s):2028 - 2033 vol.3
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    While most of the research on reinforcement learning assumed a discrete control space, many of the real world control problems need to have continuous output. This can be achieved by using continuous mapping functions for the value and action functions of the reinforcement learning architecture. Two questions arise here however. One is what sort of function representation to use and the other is h... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A temporal adaptive probability neural network for cloud classification from satellite imagery

    Publication Year: 1998, Page(s):1732 - 1737 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (684 KB)

    Cloud classification from satellite imagery is an important but very difficult task. Temporal changes are one of the main factors that cause degradation in the classifier performance when a sequence of imagery is to be processed A probability neural network (PNN)-based cloud classification system and its temporal updating scheme is proposed in this paper. This novel approach can track the temporal... View full abstract»

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

    Publication Year: 1998, Page(s):2104 - 2109 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    In this article, the influence of uncertainty on weights and biases of neural networks on the input/output behavior is investigated. Moreover, a uncertainty description of uncertain neural networks is derived and an appropriate norm bound of the model uncertainty, which is needed for robust control design, is derived. Finally, feedback linearization is used in order to fully incorporate neural net... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fast exact parallel implementation of the k-nearest neighbour pattern classifier

    Publication Year: 1998, Page(s):1867 - 1872 vol.3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (496 KB)

    A neural network architecture is presented that precisely implements the k-nearest-neighbour (k-NN) pattern classification rule. Given n exemplars, the size of the architecture grows O(n) and the time taken per classification grows O(log n). This offers perhaps the most useful neural implementation of the k-NN classifier compared to previous implementations, which suffer either from worst-case exp... View full abstract»

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