By Topic

Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470)

Date 1999

Go

Filter Results

Displaying Results 1 - 25 of 90
  • Chemical structure matching using correlation matrix memories

    Publication Year: 1999 , Page(s): 619 - 624 vol.2
    Cited by:  Papers (4)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (500 KB)  

    This paper describes the application of the relaxation by elimination (RBE) method to matching the 3D structure of molecules in chemical databases within the frame work of binary correlation matrix memories. The paper illustrates that, when combined with distributed representations, the method maps well onto these networks, allowing high performance implementation in parallel systems. It outlines ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computationally efficient locally-recurrent neural networks for online signal processing

    Publication Year: 1999 , Page(s): 684 - 689 vol.2
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (448 KB)  

    A general class of computationally efficient locally recurrent networks (CERN) is described for real-time adaptive signal processing. The structure of the CERN is based on linear-in-the-parameters single-hidden-layered feedforward neural networks such as the radial basis function (RBF) network, the Volterra neural network (VNN) and the functionally expanded neural network (FENN), adapted to employ... View full abstract»

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

    Publication Year: 1999 , Page(s): xxvi - xxix
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (192 KB)  

    First Page of the Article
    View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Regularisation of RBF-networks with the Bayesian evidence scheme

    Publication Year: 1999 , Page(s): 533 - 538 vol.2
    Cited by:  Papers (1)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (364 KB)  

    We propose a novel regularisation method for Gaussian multiple networks, which adopts a Bayesian approach and draws on the evidence scheme to optimise the hyperparameters. This leads to a new, modified form of the EM algorithm, which is compared with the original scheme on three classification problems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Independent component analysis by the PFANN neural network

    Publication Year: 1999 , Page(s): 696 - 701 vol.2
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (352 KB)  

    The aim of the paper is to present a neural technique for performing independent component analysis of eterokurtic signals by the functional-link network. Based upon entropy optimization, the proposed approach relies on the use of a neural network formed by neural units endowed with adaptive activation functions that allow the recursive approximation of the cumulative distribution functions of the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An optimal connection radius for long-range synchronization

    Publication Year: 1999 , Page(s): 557 - 562 vol.2
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (432 KB)  

    We demonstrate, by means of computer simulations of a realistic cerebellar circuit model, the existence of an optimal axonal length (connection radius) for establishing long-range synchronous oscillations. Beyond the optimal axonal length, conduction delays hamper synchronization. The conduction delays also codetermine the oscillation frequency, making synchrony frequency-dependent. Large conducti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • VC dimension bounds for higher-order neurons

    Publication Year: 1999 , Page(s): 563 - 568 vol.2
    Cited by:  Papers (4)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (448 KB)  

    We investigate the sample complexity for learning using higher-order neurons. We calculate upper and lower bounds on the Vapnik-Chervonenkis dimension and the pseudo dimension for higher-order neurons that allow unrestricted interactions among the input variables. In particular, we show that the degree of interaction is irrelevant for the VC dimension and that the individual degree of the variable... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-organizingly emerging activeness architecture realized by coherent neural networks

    Publication Year: 1999 , Page(s): 726 - 731 vol.2
    Cited by:  Papers (1)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (436 KB)  

    Coherent activeness architecture: a self-organizing activeness (or intentionality) architecture using coherent neural networks is proposed for the future brain-type information processing systems. It utilizes coherent neural network modules whose behavior (forward processing, learning, self-organization, etc.) is controlled by their carrier-wave frequencies. The behaviors constructs an orthogonal ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of IC fabrication processes using self-organizing maps

    Publication Year: 1999 , Page(s): 631 - 636 vol.2
    Cited by:  Papers (2)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (780 KB)  

    The analysis of integrated circuit (IC) fabrication processes is an important task in order to optimize the yield and to detect problems in very early state. Neural networks seem to be a promising approach to data analysis, especially when there is a large amount of data with many nonlinearities. In this paper we describe the use of self-organizing maps (SOM) for visualization and analysis of data... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of a reduced Hopfield neural net on dynamic routing in real time communication network

    Publication Year: 1999 , Page(s): 637 - 642 vol.2
    Cited by:  Papers (2)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (360 KB)  

    We propose a virtue token algorithm for finding an optimal route in real time communication network, and use a Hopfield neural net to implement it. Our Hopfield neural net routing method cannot only satisfy the routing requirement of a dynamic communication network, but can also be implemented into hardware. Moreover, our Hopfield neural net can be reduced to a much smaller scale, thus making the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Time-slicing: a model for cerebellar function based on synchronization, reverberation, and time windows

    Publication Year: 1999 , Page(s): 539 - 544 vol.2
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (484 KB)  

    We present a new theory of cerebellar function that is based on synchronization, delayed reverberation, and time windows for triggering spikes. We show that granule cells admit messy fiber activity to the parallel fibers only if the Golgi cells are firing synchronously and if the spikes arrive within short and well-defined time windows. The time window mechanism organizes neuronal activity in disc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Linear programs for automatic accuracy control in regression

    Publication Year: 1999 , Page(s): 575 - 580 vol.2
    Cited by:  Papers (14)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (384 KB)  

    We have recently proposed a new approach to control the number of basis functions and the accuracy in support vector machines. The latter is transferred to a linear programming setting, which inherently enforces sparseness of the solution. The algorithm computes a nonlinear estimate in terms of kernel functions and an ε>0 with the property that at most a fraction ν of the training set h... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Avalanches of activity in a network of integrate-and-fire neurons with stochastic input

    Publication Year: 1999 , Page(s): 545 - 550 vol.2
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (400 KB)  

    In globally coupled networks of integrate-and-fire neurons with random input, avalanches of spike activity can be observed. We analytically derive an expression for avalanche size distributions valid for arbitrary values of the coupling coefficient α, and for arbitrary network sizes N. For small values of α, avalanches comprising only few neurons dominate. At a critical value, α<... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature extraction algorithms for pattern classification

    Publication Year: 1999 , Page(s): 738 - 742 vol.2
    Cited by:  Patents (1)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (320 KB)  

    Feature extraction is often an important preprocessing step in classifier design, in order to overcome the problems associated with having a large input space. A common way of doing this is to use principle component analysis to find the most important features. However, it has been recognised that this may not produce an optimal set of features in some problems since the method relies on the seco... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The study of micro-arousals using neural network analysis of the EEG

    Publication Year: 1999 , Page(s): 625 - 630 vol.2
    Cited by:  Papers (2)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (396 KB)  

    This paper describes the use of neural networks to analyse the EEG from patients with recurrent micro-arousal episodes. A bank of bandpass filters and AR modelling have been used separately to represent EEG data from 7 chronic patients, divided into three different classes, each class corresponded to a different a sleep stage. A radial basis function network has been trained to classify normal sle... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • KBANNs and the classification of 31P MRS of malignant mammary tissues

    Publication Year: 1999 , Page(s): 982 - 987 vol.2
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (468 KB)  

    Knowledge-based artificial neural networks (KBANNs) is a hybrid methodology that combines knowledge of a domain in the form of simple rules with connectionist learning. This combination allows the use of small sets of data (typical of medical diagnosis tasks) to train the network. The initial structure is set from the dependencies of a set of rules and it is only necessary to refine these rules by... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Components of brain activity-data analysis for fMRI

    Publication Year: 1999 , Page(s): 1023 - 1028 vol.2
    Cited by:  Patents (1)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (424 KB)  

    Functional magnetic resonance imaging (fMRI) is a promising method to determine noninvasively the spatial distribution of brain activity in a given situation, e.g. in response to a stimulus or during task solving. The fMRI signal is very small and often cannot be identified from the anatomical images. Thus data analysis methods are required to localize the activity. We discuss different data analy... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning error-correcting output codes from data

    Publication Year: 1999 , Page(s): 743 - 748 vol.2
    Cited by:  Papers (5)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (392 KB)  

    A polychotomizer which assigns the input to one of K⩾3 classes is constructed using a set of dichotomizers which assign the input to one of two classes. Defining classes in terms of the dichotomizers is the binary decomposition matrix of size K×L where each of the K⩾3 classes is written as error-correcting output codes (ECOC), i.e., an array of the responses of binary decisions made ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A spatio-temporal neural network applied to visual speech recognition

    Publication Year: 1999 , Page(s): 797 - 802 vol.2
    Cited by:  Papers (3)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (424 KB)  

    We present a new neural architecture called spatio-temporal neural network (STNN). In this work, we have utilised the Hermitian distance as the basis of spatio-temporal data comparison to adapt a supervised (RCE) and an unsupervised (K-means) learning algorithms for training the STNN weights. A visual speech recognition (automatic lip-reading) system based on STNN is developed and the results obta... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards an FPGA based reconfigurable computing environment for neural network implementations

    Publication Year: 1999 , Page(s): 661 - 666 vol.2
    Cited by:  Papers (7)  |  Patents (1)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (484 KB)  

    Three computational characteristics can be attributed to neural networks: parallelism, modularity, and dynamic-adaptation. We argue that these computational characteristics of neural networks map nicely to fine-grained FPGA based reconfigurable computing architectures. Neural network architectures are decomposed into a set of parameterized neural computation modules and implemented in the FPGAs as... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recurrent learning of input-output stable behaviour in function space: A case study with the Roessler attractor

    Publication Year: 1999 , Page(s): 761 - 766 vol.2
    Cited by:  Papers (1)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (404 KB)  

    We analyse the stability of the input-output behaviour of a recurrent network. It is trained to implement an operator implicitly given by the chaotic dynamics of the Roessler attractor. Two of the attractors coordinate functions are used as network input and the third defines the reference output. Using previously developed methods we show that the trained network is input-output stable and comput... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vicarious learning in mobile neurally controlled agents: the V-MAXSON architecture

    Publication Year: 1999 , Page(s): 904 - 909 vol.2
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (472 KB)  

    Extends MAXSON (a neural reinforcement learning system) to include vicarious learning. It shows that V-MAXSON can improve individual survival as well as promote survival of the group View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Active topographic mapping of proximities

    Publication Year: 1999 , Page(s): 952 - 957 vol.2
    Cited by:  Papers (5)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (452 KB)  

    We deal with the question of how to reduce the computational costs of obtaining and clustering dissimilarity data. We show that for pairwise clustering, a large portion of the dissimilarity data can be neglected without incurring a serious deterioration of the clustering solution. This fact can be exploited by selecting the dissimilarity values that are supposed to be most relevant in a well-direc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A nonlinear oscillator network circuit for image segmentation with double-threshold phase detection

    Publication Year: 1999 , Page(s): 655 - 660 vol.2
    Cited by:  Papers (3)  |  Patents (1)
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (480 KB)  

    This paper proposes a new image segmentation processing method using oscillator networks. Accurate image segmentation in the time domain is achieved by introducing a new double-threshold phase detection processing. We also propose LSI circuits for the oscillator network and the new segmentation processing using pulse modulation circuit techniques. As some of the circuit components of the original ... View full abstract»

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

    Publication Year: 1999 , Page(s): 515 - 520 vol.2
    Save to Project icon | Click to expandAbstract | PDF file iconPDF (408 KB)  

    A new constructive learning algorithm, called Hamming clustering (HC), for binary neural networks is proposed. It is able to generate a set of rules in if-then form underlying an unknown classification problem starting from a training set of samples. The performance of HC has been evaluated through a variety of artificial and real-world benchmarks. In particular, its application in the diagnosis o... View full abstract»

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