2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)

25-29 July 2004

Go

Filter Results

Displaying Results 1 - 25 of 184
  • Noise induced phenomena in jump diffusion models for single neuron spike activity

    Publication Year: 2004, Page(s):3025 - 3028 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (593 KB) | HTML iconHTML

    Noise plays an important role in neural transmission and stochastic neuronal models can be employed to help the understanding of coding principles. The attempt to detect instances, where the noise plays a positive role increasing the reliability of the signal or synchronizing the spike trains of different neurons, requests the use of suitable biologically compatible mathematical models. A contribu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Kernel-based canonical coordinate decomposition of two-channel nonlinear maps

    Publication Year: 2004, Page(s):3019 - 3024 vol.4
    Cited by:  Papers (5)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (720 KB) | HTML iconHTML

    A kernel-based formulation for decomposing nonlinear maps of two data channels into their canonical coordinates is derived. Each data channel is implicitly mapped to a high dimensional feature space defined by a nonlinear kernel. The canonical coordinates of the nonlinear maps are then found by transforming the kernel maps with the eigenvector matrices of a coupled asymmetric generalized eigenvalu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Kernels based on weighted Levenshtein distance

    Publication Year: 2004, Page(s):3015 - 3018 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (622 KB) | HTML iconHTML

    In some real world applications, the sample could be described as a string of symbols rather than a vector of real numbers. It is necessary to determine the similarity or dissimilarity of two strings in many training algorithms. The widely used notion of similarity of two strings with different lengths is the weighted Levenshtein distance (WLD), which implies the minimum total weights of single sy... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture classification by support vector machines with kernels for higher-order Gabor filtering

    Publication Year: 2004, Page(s):3009 - 3014 vol.4
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (783 KB) | HTML iconHTML

    A support vector machine (SVM), which employs a kernel corresponding to feature extraction of local higher order moment spectra (LHOMS) of an image, is introduced. In order to overcome the curse of dimensionality when utilizing LHOMS image features in conventional multi channel filtering, an inner product kernel of LHOMS is derived. In the experiments, the SVM with LHOMS kernel is applied to image... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A loudspeaker response model using tuneable approximate piecewise linear regression

    Publication Year: 2004, Page(s):2711 - 2716 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (670 KB) | HTML iconHTML

    A practical loudspeaker frequency response interpolation model is developed using a tuneable approximate piecewise linear regression (TAPLR) model that can provide a complete amplitude and phase response over the full frequency range of the loudspeaker. This is achieved by taking a finite number of standard one-twelfth octave frequency amplitude measurements at a one meter distance in front of the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sparse coding and NMF

    Publication Year: 2004, Page(s):2529 - 2533 vol.4
    Cited by:  Papers (87)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (906 KB) | HTML iconHTML

    Non-negative matrix factorization (NMF) is a very efficient parameter-free method for decomposing multivariate data into strictly positive activations and basis vectors. However, the method is not suited for overcomplete representations, where usually sparse coding paradigms apply. We show how to merge the concepts of non-negative factorization with sparsity conditions. The result is a multiplicat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applications of Clifford support vector machines and Clifford moments for classification

    Publication Year: 2004, Page(s):3003 - 3008 vol.4
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (663 KB) | HTML iconHTML

    This paper introduces the Clifford support vector machines as a generalization of the real- and complex- valued support vector machines using the Clifford geometric algebra. In this framework we handle the design of kernels involving the Clifford or geometric product for linear and nonlinear classification. We present an interesting application to classify mechanical tools using the concept of Cli... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network models for fabric drape prediction

    Publication Year: 2004, Page(s):2925 - 2929 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (665 KB) | HTML iconHTML

    Neural networks are used to predict the drape coefficient (DC) and circularity (CTR) of many different kinds of fabrics. The neural network models used were the multilayer perceptron using backpropagation (BP) and the radial basis function (RBF) neural network. The BP method was found to be more effective than the RBF method but the RBF method was the fastest when it came to training. Comparisons ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Randomized approach to verification of neural networks

    Publication Year: 2004, Page(s):2819 - 2824 vol.4
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (744 KB) | HTML iconHTML

    Rigorous verification of neural nets is necessary in safety-critical applications such as commercial aviation. This paper investigates feasibility of a randomized approach to the problem. The previously developed deterministic verification method suffers from exponential growth of computational complexity as a function of problem dimensionality, which limits its applicability to low dimensional ca... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Expert systems and artificial neural networks applied to stellar optical spectroscopy: a comparative analysis

    Publication Year: 2004, Page(s):2705 - 2710 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (748 KB) | HTML iconHTML

    This work presents a comparative study of two computational techniques - expert systems and artificial neural networks - applied to a specific field of astrophysics, the classification of the optical spectra of stars. We present a description of various expert systems and neural networks models, and the comparison of the results obtained by each technique individually and by a combination of both.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design and optimization of Amari neural fields for early auditory-visual integration

    Publication Year: 2004, Page(s):2523 - 2528 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (824 KB) | HTML iconHTML

    We introduce a computational model of sensor fusion based on the topographic representations of a "two-microphone and one camera" configuration. Our aim is to perform a robust multimodal attention-mechanism in artificial systems. In our approach, we consider neurophysiological findings to discuss the biological plausibility of the coding and extraction of spatial features, but also meet the demand... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Acoustic model combination for recognition of speech in multiple languages using support vector machines

    Publication Year: 2004, Page(s):3065 - 3069 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (625 KB) | HTML iconHTML

    We study the performance of support vector machine based classifiers in acoustic model combination for recognition of context dependent sub word units of speech in multiple languages. In acoustic model combination, the data for similar sub word units across languages are shared to train acoustic models for multilingual speech. Sharing of data across languages leads to an increase in the number of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Support vector classifiers via gradient systems with discontinuous righthand sides

    Publication Year: 2004, Page(s):2997 - 3002 vol.4
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (711 KB) | HTML iconHTML

    This paper implements support vector machines (SVM) for the discrimination of nonseparable classes using gradient systems with discontinuous righthand sides. The gradient systems are obtained from an exact penalty method applied to the constrained quadratic optimization problems. Global convergence to the solution of the corresponding constrained problems is shown to be independent of the penalty ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CPCA: a multiplierless neural PCA

    Publication Year: 2004, Page(s):2689 - 2692 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (720 KB) | HTML iconHTML

    A multiplier-less neural architecture for PCA is proposed. The aim is to reduce the VLSI complexity of its implementation by eliminating the multipliers. Comparisons with standard PCA methods show no degradation in performances (in most cases they are even improved) while the reduced hardware complexity allows for efficient low power implementations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognizing objects in non-controlled backgrounds by an appearance two-step approach

    Publication Year: 2004, Page(s):2565 - 2570 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (673 KB) | HTML iconHTML

    This work presents a method for identifying real three-dimensional objects in non-controlled backgrounds using independent component analysis to eliminate redundant image information present in each object image. The proposed method is a two-step process that allows a coarse color-based detection and an exact localization using shape information. The paper describes an efficient implementation, ma... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural block control for a synchronous electric generator

    Publication Year: 2004, Page(s):2919 - 2924 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (614 KB) | HTML iconHTML

    We present a novel identification and control scheme, which is able to identify and to control a synchronous generator using a neural identifier. The generator is modelled as a full (eight) order one. A third order neural network such as the one presented in R. A. Felix, et al. (June 2003), is used to identify the dynamics, of the synchronous generator. Moreover, a discontinuous control law based ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Labeled and unlabeled data in text categorization

    Publication Year: 2004, Page(s):2971 - 2976 vol.4
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (739 KB) | HTML iconHTML

    There is a growing interest in exploring the use of unlabeled data as a way to improve classification performance in text categorization. The ready availability of this kind of data in most applications makes it an appealing source of information. This work reports a study carried out on the Reuters-21578 corpus to evaluate the performance of support vector machines when unlabeled examples are int... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Homomorphic processing system and ratio rule for color image enhancement

    Publication Year: 2004, Page(s):2507 - 2511 vol.4
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (692 KB) | HTML iconHTML

    Homomorphic filter is an illumination-reflectance model that can be used to develop a frequency domain procedure for improving the appearance of an image by simultaneous gray-level range compression and contrast enhancement. Many previously reported methods on homomorphic filter for color images shows that the homomorphic filter consistently provides excellent dynamic range compression but is lack... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the need for on-line learning in brain-computer interfaces

    Publication Year: 2004, Page(s):2877 - 2882 vol.4
    Cited by:  Papers (64)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (757 KB) | HTML iconHTML

    We motivate the need for on-line learning in brain-computer interfaces (BCI) and illustrate its benefits with the simplest method, namely fixed learning rates. However, the use of this method is supported by the risk of hampering the user to acquire suitable control of the BCI if the embedded classifier changes too rapidly. We report the results with 3 beginner subjects in a series of consecutive ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image enlargement as an edge estimation

    Publication Year: 2004, Page(s):2577 - 2581 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1051 KB) | HTML iconHTML

    A robust image enlargement algorithm is presented in this paper. We formulate the image enlargement process as an edge information estimation process. In order to achieve a higher resolution, we first perform pixel duplication [W.K. Pratt, 1991] on the target image to form an initial high resolution image. Then the edge details of the enlarged image are estimated by using a novel neural network ca... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Variant of feature extraction and coding-reconstruction of the images using neuron-like algorithms

    Publication Year: 2004, Page(s):2519 - 2522 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (633 KB) | HTML iconHTML

    Procedures of various feature extractions in synchronous modes, segmentation for the subsequent coding and reconstruction of the initial gray-tone image are realized. The model of a two-dimensional layer describing a one-layer (one-component) distributed neuron-like system is used for the computer simulation. The system consists of active neuron-like elements with a nonlocal coupling function betw... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient training of large neural networks for language modeling

    Publication Year: 2004, Page(s):3059 - 3064 vol.4
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (753 KB) | HTML iconHTML

    Recently there has been increasing interest in using neural networks for language modeling. In contrast to the well-known backoff n-gram language models, the neural network approach tries to limit the data sparseness problem by performing the estimation in a continuous space, allowing by this means smooth interpolations. The complexity to train such a model and to calculate one n-gram probability ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A quick learning method that gambles: a learning system that hates learning

    Publication Year: 2004, Page(s):2847 - 2852 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (669 KB) | HTML iconHTML

    This work presents a quick machine learning system inspired by human learning behavior. Data-mining systems based on machine-learning usually need a large number of iterations to acquire correct solutions, whereas people usually find appropriate hidden rules after only a small number of observations of the instances in a dataset. We think that this quick learning is the result of using tentative h... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The support vector machine learning using the second order cone programming

    Publication Year: 2004, Page(s):2991 - 2996 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (643 KB) | HTML iconHTML

    We propose a data dependent learning method for the support vector machine. This method is based on the technique of second order cone programming. We reformulate the SVM quadratic problem into the second order cone problem. The proposed method requires decomposing the kernel matrix of SVM optimization problem. In this paper we apply Cholesky decomposition method. Since the kernel matrix is positi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Histogram coding for recognition of contours presented by Bezier curves

    Publication Year: 2004, Page(s):2559 - 2563 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (708 KB) | HTML iconHTML

    In the pattern recognition area, one of the most important tasks is the ability of a neural network to classify objects regardless of affine transformations. Contoured objects can be described with Bezier curves and the description is affine transformation invariant. Direct use of the curves for a neural network input isn't applicable because it's possible that descriptions of the same objects con... View full abstract»

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