By Topic

Neural Networks, IEEE Transactions on

Issue 6 • Date June 2011

Filter Results

Displaying Results 1 - 22 of 22
  • Table of contents

    Publication Year: 2011 , Page(s): C1
    Request Permissions | PDF file iconPDF (110 KB)  
    Freely Available from IEEE
  • IEEE Transactions on Neural Networks publication information

    Publication Year: 2011 , Page(s): C2
    Request Permissions | PDF file iconPDF (39 KB)  
    Freely Available from IEEE
  • Causality Analysis of Neural Connectivity: Critical Examination of Existing Methods and Advances of New Methods

    Publication Year: 2011 , Page(s): 829 - 844
    Cited by:  Papers (4)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (887 KB) |  | HTML iconHTML  

    Granger causality (GC) is one of the most popular measures to reveal causality influence of time series and has been widely applied in economics and neuroscience. Especially, its counterpart in frequency domain, spectral GC, as well as other Granger-like causality measures have recently been applied to study causal interactions between brain areas in different frequency ranges during cognitive and... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discriminant Independent Component Analysis

    Publication Year: 2011 , Page(s): 845 - 857
    Cited by:  Papers (5)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (856 KB) |  | HTML iconHTML  

    A conventional linear model based on Negentropy maximization extracts statistically independent latent variables which may not be optimal to give a discriminant model with good classification performance. In this paper, a single-stage linear semisupervised extraction of discriminative independent features is proposed. Discriminant independent component analysis (dICA) presents a framework of linea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implementation Study of an Analog Spiking Neural Network for Assisting Cardiac Delay Prediction in a Cardiac Resynchronization Therapy Device

    Publication Year: 2011 , Page(s): 858 - 869
    Cited by:  Papers (5)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (1729 KB) |  | HTML iconHTML  

    In this paper, we aim at developing an analog spiking neural network (SNN) for reinforcing the performance of conventional cardiac resynchronization therapy (CRT) devices (also called biventricular pacemakers). Targeting an alternative analog solution in 0.13-μm CMOS technology, this paper proposes an approach to improve cardiac delay predictions in every cardiac period in order to assist t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Kernel Map Compression for Speeding the Execution of Kernel-Based Methods

    Publication Year: 2011 , Page(s): 870 - 879
    Request Permissions | Click to expandAbstract | PDF file iconPDF (878 KB) |  | HTML iconHTML  

    The use of Mercer kernel methods in statistical learning theory provides for strong learning capabilities, as seen in kernel principal component analysis and support vector machines. Unfortunately, after learning, the computational complexity of execution through a kernel is of the order of the size of the training set, which is quite large for many applications. This paper proposes a two-step pro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Automatic Parameter Setting Method of a Simplified PCNN for Image Segmentation

    Publication Year: 2011 , Page(s): 880 - 892
    Cited by:  Papers (7)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (998 KB) |  | HTML iconHTML  

    An automatic parameter setting method of a simplified pulse coupled neural network (SPCNN) is proposed here. Our method successfully determines all the adjustable parameters in SPCNN and does not need any training and trials as required by previous methods. In order to achieve this goal, we try to derive the general formulae of dynamic threshold and internal activity of the SPCNN according to the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive Learning Control for Finite Interval Tracking Based on Constructive Function Approximation and Wavelet

    Publication Year: 2011 , Page(s): 893 - 905
    Cited by:  Papers (3)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (609 KB) |  | HTML iconHTML  

    Using a constructive function approximation network, an adaptive learning control (ALC) approach is proposed for finite interval tracking problems. The constructive function approximation network consists of a set of bases, and the number of bases can evolve when learning repeats. The nature of the basis allows the continuous adaptive learning of parameters when the network undergoes any structura... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Transformation Invariant On-Line Target Recognition

    Publication Year: 2011 , Page(s): 906 - 918
    Cited by:  Papers (1)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (776 KB) |  | HTML iconHTML  

    Transformation invariant automatic target recognition (ATR) has been an active research area due to its widespread applications in defense, robotics, medical imaging and geographic scene analysis. The primary goal for this paper is to obtain an on-line ATR system for targets in presence of image transformations, such as rotation, translation, scale and occlusion as well as resolution changes. We i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analyzing the Scaling of Connectivity in Neuromorphic Hardware and in Models of Neural Networks

    Publication Year: 2011 , Page(s): 919 - 935
    Cited by:  Papers (11)  |  Patents (1)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (959 KB) |  | HTML iconHTML  

    In recent years, neuromorphic hardware systems have significantly grown in size. With more and more neurons and synapses integrated in such systems, the neural connectivity and its configurability have become crucial design constraints. To tackle this problem, we introduce a generic extended graph description of connection topologies that allows a systematical analysis of connectivity in both neur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Practical Training Framework for Fitting a Function and Its Derivatives

    Publication Year: 2011 , Page(s): 936 - 947
    Cited by:  Papers (1)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (625 KB) |  | HTML iconHTML  

    This paper describes a practical framework for using multilayer feedforward neural networks to simultaneously fit both a function and its first derivatives. This framework involves two steps. The first step is to train the network to optimize a performance index, which includes both the error in fitting the function and the error in fitting the derivatives. The second step is to prune the network ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Observability of Boolean Control Networks With State Time Delays

    Publication Year: 2011 , Page(s): 948 - 954
    Cited by:  Papers (8)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (183 KB) |  | HTML iconHTML  

    This brief deals with the problem of the observability for the Boolean control networks with time delays in states. First, using semi-tensor product of matrices and the matrix expression of logic, the Boolean control networks with state delays can be converted into discrete time delay dynamics. Then, the observability of the Boolean control networks via two kinds of inputs is investigated by givin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature Selection Using Probabilistic Prediction of Support Vector Regression

    Publication Year: 2011 , Page(s): 954 - 962
    Cited by:  Papers (6)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (315 KB) |  | HTML iconHTML  

    This paper presents a new wrapper-based feature selection method for support vector regression (SVR) using its probabilistic predictions. The method computes the importance of a feature by aggregating the difference, over the feature space, of the conditional density functions of the SVR prediction with and without the feature. As the exact computation of this importance measure is expensive, two ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improvements on Twin Support Vector Machines

    Publication Year: 2011 , Page(s): 962 - 968
    Cited by:  Papers (13)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (221 KB) |  | HTML iconHTML  

    For classification problems, the generalized eigenvalue proximal support vector machine (GEPSVM) and twin support vector machine (TWSVM) are regarded as milestones in the development of the powerful SVMs, as they use the nonparallel hyperplane classifiers. In this brief, we propose an improved version, named twin bounded support vector machines (TBSVM), based on TWSVM. The significant advantage of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hyperellipsoidal Statistical Classifications in a Reproducing Kernel Hilbert Space

    Publication Year: 2011 , Page(s): 968 - 975
    Cited by:  Papers (1)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (270 KB) |  | HTML iconHTML  

    Standard support vector machines (SVMs) have kernels based on the Euclidean distance. This brief extends standard SVMs to SVMs with kernels based on the Mahalanobis distance. The extended SVMs become a special case of the Euclidean distance when the covariance matrix in a reproducing kernel Hilbert space is degenerated to an identity. The Mahalanobis distance leads to hyperellipsoidal kernels and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stability and Dissipativity Analysis of Distributed Delay Cellular Neural Networks

    Publication Year: 2011 , Page(s): 976 - 981
    Cited by:  Papers (11)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (192 KB) |  | HTML iconHTML  

    In this brief, the problems of delay-dependent stability analysis and strict (Q,S,ℜ)-α-dissipativity analysis are investigated for cellular neural networks (CNNs) with distributed delay. First, by introducing an integral partitioning technique, two new forms of Lyapunov-Krasovskii functionals are constructed, and improved distributed delay-dependent stability conditions are establish... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient Algorithm for Training Interpolation RBF Networks With Equally Spaced Nodes

    Publication Year: 2011 , Page(s): 982 - 988
    Cited by:  Papers (5)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (246 KB) |  | HTML iconHTML  

    This brief paper proposes a new algorithm to train interpolation Gaussian radial basis function (RBF) networks in order to solve the problem of interpolating multivariate functions with equally spaced nodes. Based on an efficient two-phase algorithm recently proposed by the authors, Euclidean norm associated to Gaussian RBF is now replaced by a conveniently chosen Mahalanobis norm, that allows for... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Embedded Feature Ranking for Ensemble MLP Classifiers

    Publication Year: 2011 , Page(s): 988 - 994
    Cited by:  Papers (5)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (274 KB) |  | HTML iconHTML  

    A feature ranking scheme for multilayer perceptron (MLP) ensembles is proposed, along with a stopping criterion based upon the out-of-bootstrap estimate. To solve multi-class problems feature ranking is combined with modified error-correcting output coding. Experimental results on benchmark data demonstrate the versatility of the MLP base classifier in removing irrelevant features. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Why we joined ... [advertisement]

    Publication Year: 2011 , Page(s): 995
    Request Permissions | PDF file iconPDF (205 KB)  
    Freely Available from IEEE
  • Leading the field since 1884 [advertisement]

    Publication Year: 2011 , Page(s): 996
    Request Permissions | PDF file iconPDF (223 KB)  
    Freely Available from IEEE
  • IEEE Computational Intelligence Society Information

    Publication Year: 2011 , Page(s): C3
    Request Permissions | PDF file iconPDF (37 KB)  
    Freely Available from IEEE
  • IEEE Transactions on Neural Networks Information for authors

    Publication Year: 2011 , Page(s): C4
    Request Permissions | PDF file iconPDF (37 KB)  
    Freely Available from IEEE

Aims & Scope

IEEE Transactions on Neural Networks is devoted to the science and technology of neural networks, which disclose significant technical knowledge, exploratory developments, and applications of neural networks from biology to software to hardware.

 

This Transactions ceased production in 2011. The current retitled publication is IEEE Transactions on Neural Networks and Learning Systems.

Full Aims & Scope