By Topic

IEEE Transactions on Neural Networks

Issue 6 • Nov. 2001

Filter Results

Displaying Results 1 - 25 of 36
  • Advances in independent component analysis [Book Review]

    Publication Year: 2001, Page(s): 1547
    Cited by:  Papers (2)
    Request permission for commercial reuse | PDF file iconPDF (10 KB) | HTML iconHTML
    Freely Available from IEEE
  • Author index

    Publication Year: 2001, Page(s):1548 - 1552
    Request permission for commercial reuse | PDF file iconPDF (52 KB)
    Freely Available from IEEE
  • Subject index

    Publication Year: 2001, Page(s):1552 - 1564
    Request permission for commercial reuse | PDF file iconPDF (97 KB)
    Freely Available from IEEE
  • Processing directed acyclic graphs with recursive neural networks

    Publication Year: 2001, Page(s):1464 - 1470
    Cited by:  Papers (13)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (157 KB) | HTML iconHTML

    Recursive neural networks are conceived for processing graphs and extend the well-known recurrent model for processing sequences. In Frasconi et al. (1998), recursive neural networks can deal only with directed ordered acyclic graphs (DOAGs), in which the children of any given node are ordered. While this assumption is reasonable in some applications, it introduces unnecessary constraints in other... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-organizing maps, vector quantization, and mixture modeling

    Publication Year: 2001, Page(s):1299 - 1305
    Cited by:  Papers (84)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (234 KB) | HTML iconHTML

    Self-organizing maps are popular algorithms for unsupervised learning and data visualization. Exploiting the link between vector quantization and mixture modeling, we derive expectation-maximization (EM) algorithms for self-organizing maps with and without missing values. We compare self-organizing maps with the elastic-net approach and explain why the former is better suited for the visualization... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neuromorphic VLSI device for implementing 2D selective attention systems

    Publication Year: 2001, Page(s):1455 - 1463
    Cited by:  Papers (33)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (247 KB) | HTML iconHTML

    Selective attention is a mechanism used to sequentially select and process salient subregions of the input space, while suppressing inputs arriving from nonsalient regions. By processing small amounts of sensory information in a serial fashion, rather than attempting to process all the sensory data in parallel, this mechanism overcomes the problem of flooding limited processing capacity systems wi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • RBF multiuser detector with channel estimation capability in a synchronous MC-CDMA system

    Publication Year: 2001, Page(s):1536 - 1539
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (144 KB) | HTML iconHTML

    The authors propose a multiuser detector with channel estimation capability using a radial basis function (RBF) network in a synchronous multicarrier-code division multiple access (MC-CDMA) system. The authors propose to connect an RBF network to the frequency domain to effectively utilize the frequency diversity. Simulations were performed over frequency-selective and multi-path fading channels. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new pruning heuristic based on variance analysis of sensitivity information

    Publication Year: 2001, Page(s):1386 - 1399
    Cited by:  Papers (97)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (255 KB) | HTML iconHTML

    Architecture selection is a very important aspect in the design of neural networks (NNs) to optimally tune performance and computational complexity. Sensitivity analysis has been used successfully to prune irrelevant parameters from feedforward NNs. This paper presents a new pruning algorithm that uses the sensitivity analysis to quantify the relevance of input and hidden units. A new statistical ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the convergence of the decomposition method for support vector machines

    Publication Year: 2001, Page(s):1288 - 1298
    Cited by:  Papers (97)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (253 KB) | HTML iconHTML

    The decomposition method is currently one of the major methods for solving support vector machines (SVM). Its convergence properties have not been fully understood. The general asymptotic convergence was first proposed by Chang et al. However, their working set selection does not coincide with existing implementation. A later breakthrough by Keerthi and Gilbert (2000, 2002) proved the convergence ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two regularizers for recursive least squared algorithms in feedforward multilayered neural networks

    Publication Year: 2001, Page(s):1314 - 1332
    Cited by:  Papers (32)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (440 KB) | HTML iconHTML

    Recursive least squares (RLS)-based algorithms are a class of fast online training algorithms for feedforward multilayered neural networks (FMNNs). Though the standard RLS algorithm has an implicit weight decay term in its energy function, the weight decay effect decreases linearly as the number of learning epochs increases, thus rendering a diminishing weight decay effect as training progresses. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An algorithmic approach to adaptive state filtering using recurrent neural networks

    Publication Year: 2001, Page(s):1411 - 1432
    Cited by:  Papers (51)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (500 KB) | HTML iconHTML

    Practical algorithms are presented for adaptive state filtering in nonlinear dynamic systems when the state equations are unknown. The state equations are constructively approximated using neural networks. The algorithms presented are based on the two-step prediction-update approach of the Kalman filter. The proposed algorithms make minimal assumptions regarding the underlying nonlinear dynamics a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A multilayer self-organizing model for convex-hull computation

    Publication Year: 2001, Page(s):1341 - 1347
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (119 KB) | HTML iconHTML

    A self-organizing neural-network model is proposed for computation of the convex-hull of a given set of planar points. The network evolves in such a manner that it adapts itself to the hull-vertices of the convex-hull. The proposed network consists of three layers of processors. The bottom layer computes some angles which are passed to the middle layer. The middle layer is used for computation of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • RBFNN-based hole identification system in conducting plates

    Publication Year: 2001, Page(s):1445 - 1454
    Cited by:  Papers (3)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (184 KB) | HTML iconHTML

    A neural-based signal processing system that exploits radial basis function neural network (RBFNN) is proposed to solve the problem of detecting and locating circular holes in conducting plates by means of nondestructive eddy currents testing. The capabilities of basic multilayer perceptron and radial basis function (RBF) schemes are first investigated. Since the achieved performance revealed insu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Global convergence of delayed dynamical systems

    Publication Year: 2001, Page(s):1532 - 1536
    Cited by:  Papers (30)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (165 KB) | HTML iconHTML

    We discuss some delayed dynamical systems, investigating their stability and convergence in a critical case. To ensure the stability, the coefficients of the dynamical system must satisfy some inequalities. In most existing literatures, the restrictions on the coefficients are strict inequalities. The tough question is what will happen in the case (critical case) the strict inequalities are replac... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Empirical measure of multiclass generalization performance: the K-winner machine case

    Publication Year: 2001, Page(s):1525 - 1529
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (164 KB) | HTML iconHTML

    Combining the K-winner machine (KWM) model with empirical measurements of a classifier's Vapnik-Chervonenkis (VC)-dimension gives two major results. First, analytical derivations refine the theory that characterizes the generalization performances of binary classifiers. Second, a straightforward extension of the theoretical framework yields bounds to the generalization error for multiclass problem... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A recurrent neural network for nonlinear continuously differentiable optimization over a compact convex subset

    Publication Year: 2001, Page(s):1487 - 1490
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (136 KB) | HTML iconHTML

    We propose a general recurrent neural-network (RNN) model for nonlinear optimization over a nonempty compact convex subset which includes the bound subset and spheroid subset as special cases. It is shown that the compact convex subset is a positive invariant and attractive set of the RNN system and that all the network trajectories starting from the compact convex subset converge to the equilibri... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A network of dynamically coupled chaotic maps for scene segmentation

    Publication Year: 2001, Page(s):1375 - 1385
    Cited by:  Papers (19)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (264 KB) | HTML iconHTML

    In this paper, a computational model for scene segmentation based on a network of dynamically coupled chaotic maps is proposed. Time evolutions of chaotic maps that correspond to an object in the given scene are synchronized with one another, while this synchronized evolution is desynchronized with respect to time evolution of chaotic maps corresponding to other objects in the scene. In this model... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Confidence estimation methods for neural networks: a practical comparison

    Publication Year: 2001, Page(s):1278 - 1287
    Cited by:  Papers (60)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (172 KB) | HTML iconHTML

    Feedforward neural networks, particularly multilayer perceptrons, are widely used in regression and classification tasks. A reliable and practical measure of prediction confidence is essential. In this work three alternative approaches to prediction confidence estimation are presented and compared. The three methods are the maximum likelihood, approximate Bayesian, and the bootstrap technique. We ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Training of a feedforward multiple-valued neural network by error backpropagation with a multilevel threshold function

    Publication Year: 2001, Page(s):1519 - 1521
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (92 KB) | HTML iconHTML

    A technique for the training of multiple-valued neural networks based on a backpropagation learning algorithm employing a multilevel threshold function is proposed. The optimum threshold width of the multilevel function and the range of the learning parameter to be chosen for convergence are derived. Trials performed on a benchmark problem demonstrate the convergence of the network within the spec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Blind source separation by nonstationarity of variance: a cumulant-based approach

    Publication Year: 2001, Page(s):1471 - 1474
    Cited by:  Papers (53)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (64 KB) | HTML iconHTML

    Blind separation of source signals usually relies either on the nonGaussianity of the signals or on their linear autocorrelations. A third approach was introduced by Matsuoka et al. (1995), who showed that source separation can be performed by using the nonstationarity of the signals, in particular the nonstationarity of their variances. In this paper, we show how to interpret the nonstationarity ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generalization properties of modular networks: implementing the parity function

    Publication Year: 2001, Page(s):1306 - 1313
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (156 KB) | HTML iconHTML

    The parity function is one of the most used Boolean function for testing learning algorithms because both of its simple definition and its great complexity. We construct a family of modular architectures that implement the parity function in which, every member of the family can be characterized by the fan-in max of the network, i.e., the maximum number of connections that a neuron can receive. We... View full abstract»

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

    Publication Year: 2001, Page(s):1539 - 1546
    Cited by:  Papers (32)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB) | HTML iconHTML

    Univariate decision trees at each decision node consider the value of only one feature leading to axis-aligned splits. In a linear multivariate decision tree, each decision node divides the input space into two with a hyperplane. In a nonlinear multivariate tree, a multilayer perceptron at each node divides the input space arbitrarily, at the expense of increased complexity and higher risk of over... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hopfield neural networks for affine invariant matching

    Publication Year: 2001, Page(s):1400 - 1410
    Cited by:  Papers (51)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (605 KB) | HTML iconHTML

    The affine transformation, which consists of rotation, translation, scaling, and shearing transformations, can be considered as an approximation to the perspective transformation. Therefore, it is very important to find an effective means for establishing point correspondences under affine transformation in many applications. In this paper, we consider the point correspondence problem as a subgrap... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • LSTM recurrent networks learn simple context-free and context-sensitive languages

    Publication Year: 2001, Page(s):1333 - 1340
    Cited by:  Papers (52)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (209 KB) | HTML iconHTML

    Previous work on learning regular languages from exemplary training sequences showed that long short-term memory (LSTM) outperforms traditional recurrent neural networks (RNNs). We demonstrate LSTMs superior performance on context-free language benchmarks for RNNs, and show that it works even better than previous hardwired or highly specialized architectures. To the best of our knowledge, LSTM var... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic re-optimization of a fed-batch fermentor using adaptive critic designs

    Publication Year: 2001, Page(s):1433 - 1444
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (470 KB) | HTML iconHTML

    Traditionally, fed-batch biochemical process optimization and control uses complicated off-line optimizers, with no online model adaptation or re-optimization. This study demonstrates the applicability of a class of adaptive critic designs for online re-optimization and control of an aerobic fed-batch fermentor. Specifically, the performance of an entire class of adaptive critic designs, viz., heu... View full abstract»

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

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