By Topic

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

1999

Go

Filter Results

Displaying Results 1 - 25 of 90
  • Fast winner search for SOM-based monitoring and retrieval of high-dimensional data

    Publication Year: 1999, Page(s):940 - 945 vol.2
    Cited by:  Papers (7)  |  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (432 KB)

    Self-organizing maps (SOMs) are widely used in engineering and data-analysis tasks, but so far rarely in very large-scale problems. The reason is the amount of computation. Winner search, finding the position of a data sample on the map, is the computational bottleneck: comparison between the data vector and all of the model vectors of the map is required. In this paper a method is proposed for re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of gene regulatory sequences by bagging of neural networks

    Publication Year: 1999, Page(s):988 - 993 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (500 KB)

    The authors use an ensemble of multilayer perceptrons to build a model for a type of gene regulatory sequence called a G-box. A variant of the bagging method (bootstrap-and-aggregate) improves the performance of the ensemble over that of a single network. Through a decomposition of the generalization error of the ensemble into bias and variance components, the authors estimate this error from the ... View full abstract»

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

    Publication Year: 1999, Page(s):934 - 939 vol.2
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (420 KB)

    Based on the assumption that a pattern is constructed out of features which are either fully present or absent, we propose a vector quantisation method which constructs patterns using binary combinations of features. For this model there exists an efficient EM-like learning algorithm which learns a set of representative codebook vectors. In terms of a generative model, the collection of allowed bi... 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
    IEEE is not the copyright holder of this material | 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.
  • An analysis of initial state dependence in generalized LVQ

    Publication Year: 1999, Page(s):928 - 933 vol.2
    Cited by:  Papers (5)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (348 KB)

    The author proposed a new formulation of learning vector quantisation (LVQ) called generalized LVQ (GLVQ) based on the minimum classification error criterion. In this paper, the initial state dependence in GLVQ is discussed, and it is clarified that the learning rule should be modified to make it insensitive to the initial values of reference vectors. The robustness of the modified GLVQ for the in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Is a biological temporal learning rule compatible with learning synfire chains?

    Publication Year: 1999, Page(s):551 - 556 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (408 KB)

    The author investigates how a biologically realistic temporal learning rule and the neuronal firing threshold jointly determine the recall speed of a synfire chain trained by sequential activation of its nodes. Numerical analysis of an idealised system of discrete spike response model neurons yields the relationship between threshold and speed of recall, in particular showing that recall is not po... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Effectiveness of feature extraction in neural network architectures for novelty detection

    Publication Year: 1999, Page(s):976 - 981 vol.2
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (476 KB)

    This paper examines the performance of seven neural network architectures in classifying and detecting novel events contained within data collected from turbine sensors. Several different multilayer perceptrons were built and trained using backpropagation, conjugate gradient and quasi-Newton training algorithms. In addition, linear networks, radial basis function networks, probabilistic networks a... 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)
    IEEE is not the copyright holder of this material | 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.
  • Nonlinear dimensionality reduction with input distances preservation

    Publication Year: 1999, Page(s):922 - 927 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (300 KB)

    A new error term for dimensionality reduction, which clearly improves the quality of nonlinear principal component analysis neural networks, is introduced, and some illustrative examples are given. The method maintains the original data structure by preserving the distances between data points View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mixture conditional density estimation with the EM algorithm

    Publication Year: 1999, Page(s):821 - 825 vol.2
    Cited by:  Papers (14)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (300 KB)

    It is well-known that training a neural network with least squares corresponds to estimating a parametrized form of the conditional average of target's given inputs. In order to approximate multi-valued mappings, e.g., those occurring in inverse problems, a mixture of conditional densities must be used. In this paper we apply the EM algorithm to fit a mixture of Gaussian conditional densities when... 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
    IEEE is not the copyright holder of this material | 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.
  • Neural-based queueing system modelling for service quality estimation in B-ISDN networks

    Publication Year: 1999, Page(s):970 - 975 vol.2
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (460 KB)

    This paper addresses an original scheme based on feedforward neural networks, for modelling queueing systems fed with busy traffic. A neural network is trained to anticipate the average number of waiting cells, the cell loss rate and the coefficient of variation of the cell inter-departure time, given the mean rate, the peak rate and the coefficient of variation of the cell inter-arrival time. Our... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Local minima and plateaus in multilayer neural networks

    Publication Year: 1999, Page(s):597 - 602 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (368 KB)

    Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the geometric structure of the parameter space of three-layer perceptrons in order to show the existence of local minima and plateaus. It is proved that a critical point of the model with H-1 hidden units always gives a critical point of the model with H hidden units. Based on this result, we prove that... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Backtracking deterministic annealing for constraint satisfaction problems

    Publication Year: 1999, Page(s):868 - 873 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (488 KB)

    We present a deterministic annealing approach to the solution of quadratic constraint satisfaction problems with complex interlocking constraints, such as exemplified in polyomino tiling puzzles. We first analyze the dynamical properties of the solution strategies implemented by deterministic annealing (DA) in the analog neural representation of Potts-mean-field (PMF) and penalty-function-based co... 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)
    IEEE is not the copyright holder of this material | 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.
  • A constructivist neural network model of German verb inflection in agrammatic aphasia

    Publication Year: 1999, Page(s):916 - 921 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (564 KB)

    We present a constructivist neural network that closely models the performance of agrammatic aphasics on German participle inflection. The network constructs a modular architecture leading to a double dissociation between regular and irregular verbs, and lesioning the trained network accounts for data obtained from aphasic subjects. We analyze the internal structure of the network with respect to ... 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
    IEEE is not the copyright holder of this material | 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.
  • Deriving cluster analytic distance functions from Gaussian mixture models

    Publication Year: 1999, Page(s):815 - 820 vol.2
    Cited by:  Papers (5)  |  Patents (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (400 KB)

    The reliable detection of clusters in datasets of non-trivial dimensionality is notoriously difficult. Clustering algorithms are generally driven by some distance function (usually Euclidean) defined over pairs of examples, which implicitly treats distances within and between clusters alike. In this paper, a more effective distance measure is proposed, derived from an a priori estimated Gaussian m... 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
    IEEE is not the copyright holder of this material | 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.
  • A new neuro-fuzzy system for efficient ATM traffic control

    Publication Year: 1999, Page(s):964 - 969 vol.2
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (468 KB)

    We present and apply the fuzzy adaptive system ART-based (FasArt) neuro-fuzzy system to the problems of connection admission control (CAC) and usage parameter control (UPC). FasArt provides the advantages of both a fuzzy logic system (simplicity and interpretability of fuzzy rules) and an ART-based neural network (fast, stable and incremental learning). An extensive experimental work in the Ptolem... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Quadratic programming for learning sparse codes

    Publication Year: 1999, Page(s):593 - 596 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (284 KB)

    Olshausen and Field (1996) used a neural network, capable of discovering sparsely distributed representations by using the principle of redundancy reduction, for the efficient coding of natural images. They showed how the resulting response functions of the units relate to the properties of simple cells in the mammalian primary visual cortex. In order to model the function of later stages of visua... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network training using multi-channel data with aggregate labelling

    Publication Year: 1999, Page(s):862 - 867 vol.2
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (420 KB)

    The solution of classification problems using statistical techniques requires appropriately labelled training data. In the case of multi-channel data, however, the labels may only be available in aggregate form rather than as separate labels for each individual-channel. Standard techniques, using a trained model to classify each channel separately, are therefore precluded. We present a method of t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural associative processing of document images

    Publication Year: 1999, Page(s):720 - 725 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (412 KB)

    Binary neural associative memories are attractive for image processing because of their speed of operation for learning associations and for recalling them. We have added feedback to a feedforward associative memory, to produce a pattern completion network which performs translation-invariant pattern completion, and at the same time resolves contradictory image information. The image completion is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • MLP emulation of N-gram models as a first step to connectionist language modeling

    Publication Year: 1999, Page(s):910 - 915 vol.2
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (536 KB)

    In problems such as automatic speech recognition and machine translation, where the system response must be a sentence in a given language, language models are employed in order to improve system performance. These language models are usually N-gram models (for instance, bigram or trigram models) which are estimated from large text databases using the occurrence frequencies of these N-grams. Nakam... View full abstract»

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

    Publication Year: 1999, Page(s):iv - xxv
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (640 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.