By Topic

IEEE Transactions on Neural Networks

Issue 3 • Date May 2006

Filter Results

Displaying Results 1 - 25 of 34
  • Table of contents

    Publication Year: 2006, Page(s):c1 - c4
    Request permission for commercial reuse | PDF file iconPDF (39 KB)
    Freely Available from IEEE
  • IEEE Transactions on Neural Networks publication information

    Publication Year: 2006, Page(s): c2
    Request permission for commercial reuse | PDF file iconPDF (36 KB)
    Freely Available from IEEE
  • Function approximation using generalized adalines

    Publication Year: 2006, Page(s):541 - 558
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1843 KB) | HTML iconHTML

    This paper proposes neural organization of generalized adalines (gadalines) for data driven function approximation. By generalizing the threshold function of adalines, we achieve the K-state transfer function of gadalines which responds a unitary vector of K binary values to the projection of a predictor on a receptive field. A generative component that uses the K-state activation of a gadaline to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Gray-scale morphological associative memories

    Publication Year: 2006, Page(s):559 - 570
    Cited by:  Papers (44)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1584 KB) | HTML iconHTML

    Neural models of associative memories are usually concerned with the storage and the retrieval of binary or bipolar patterns. Thus far, the emphasis in research on morphological associative memory systems has been on binary models, although a number of notable features of autoassociative morphological memories (AMMs) such as optimal absolute storage capacity and one-step convergence have been show... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Information criteria for support vector machines

    Publication Year: 2006, Page(s):571 - 577
    Cited by:  Papers (6)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (405 KB) | HTML iconHTML

    This paper presents kernel regularization information criterion (KRIC), which is a new criterion for tuning regularization parameters in kernel logistic regression (KLR) and support vector machines (SVMs). The main idea of the KRIC is based on the regularization information criterion (RIC). We derive an eigenvalue equation to calculate the KRIC and solve the problem. The computational cost for par... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The influence of oppositely classified examples on the generalization complexity of Boolean functions

    Publication Year: 2006, Page(s):578 - 590
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (530 KB) | HTML iconHTML

    In this paper, we analyze Boolean functions using a recently proposed measure of their complexity. This complexity measure, motivated by the aim of relating the complexity of the functions with the generalization ability that can be obtained when the functions are implemented in feed-forward neural networks, is the sum of a number of components. We concentrate on the case in which we use the first... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The evolving tree-analysis and applications

    Publication Year: 2006, Page(s):591 - 603
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (837 KB) | HTML iconHTML

    In this paper, we enhance and analyze the Evolving Tree (ETree) data analysis algorithm. The suggested improvements aim to make the system perform better while still maintaining the simple nature of the basic algorithm. We also examine the system's behavior with many different kinds of tests, measurements and visualizations. We compare the ETree's performance against classical data analysis method... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel radial basis function neural network for discriminant analysis

    Publication Year: 2006, Page(s):604 - 612
    Cited by:  Papers (21)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (387 KB) | HTML iconHTML

    A novel radial basis function neural network for discriminant analysis is presented in this paper. In contrast to many other researches, this work focuses on the exploitation of the weight structure of radial basis function neural networks using the Bayesian method. It is expected that the performance of a radial basis function neural network with a well-explored weight structure can be improved. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tikhonov training of the CMAC neural network

    Publication Year: 2006, Page(s):613 - 622
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (629 KB) | HTML iconHTML

    The architecture of the cerebellar model articulation controller (CMAC) presents a rigid compromise between learning and generalization. In the presence of a sparse training dataset, this limitation manifestly causes overfitting, a drawback that is not overcome by current training algorithms. This paper proposes a novel training framework founded on the Tikhonov regularization, which relates to th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improved conditions for global exponential stability of recurrent neural networks with time-varying delays

    Publication Year: 2006, Page(s):623 - 635
    Cited by:  Papers (74)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (520 KB) | HTML iconHTML

    This paper presents new theoretical results on global exponential stability of recurrent neural networks with bounded activation functions and time-varying delays. The stability conditions depend on external inputs, connection weights, and time delays of recurrent neural networks. Using these results, the global exponential stability of recurrent neural networks can be derived, and the estimated l... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • OR/AND neurons and the development of interpretable logic models

    Publication Year: 2006, Page(s):636 - 658
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2680 KB) | HTML iconHTML

    In this paper, we are concerned with the concept of fuzzy logic networks and logic-based data analysis realized within this framework. The networks under discussion are homogeneous architectures comprising of OR/AND neurons originally introduced by Hirota and Pedrycz. Being treated here as generic processing units, OR/AND neurons are neurofuzzy constructs that exhibit well-defined logic characteri... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An approximate internal model-based neural control for unknown nonlinear discrete processes

    Publication Year: 2006, Page(s):659 - 670
    Cited by:  Papers (32)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (488 KB) | HTML iconHTML

    An approximate internal model-based neural control (AIMNC) strategy is proposed for unknown nonaffine nonlinear discrete processes under disturbed environment. The proposed control strategy has some clear advantages in respect to existing neural internal model control methods. It can be used for open-loop unstable nonlinear processes or a class of systems with unstable zero dynamics. Based on a no... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A geometric approach to Support Vector Machine (SVM) classification

    Publication Year: 2006, Page(s):671 - 682
    Cited by:  Papers (57)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (776 KB) | HTML iconHTML

    The geometric framework for the support vector machine (SVM) classification problem provides an intuitive ground for the understanding and the application of geometric optimization algorithms, leading to practical solutions of real world classification problems. In this work, the notion of "reduced convex hull" is employed and supported by a set of new theoretical results. These results allow exis... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploiting discriminant information in nonnegative matrix factorization with application to frontal face verification

    Publication Year: 2006, Page(s):683 - 695
    Cited by:  Papers (79)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (950 KB) | HTML iconHTML

    In this paper, two supervised methods for enhancing the classification accuracy of the Nonnegative Matrix Factorization (NMF) algorithm are presented. The idea is to extend the NMF algorithm in order to extract features that enforce not only the spatial locality, but also the separability between classes in a discriminant manner. The first method employs discriminant analysis in the features deriv... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Binary tree of SVM: a new fast multiclass training and classification algorithm

    Publication Year: 2006, Page(s):696 - 704
    Cited by:  Papers (57)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (343 KB) | HTML iconHTML

    We present a new architecture named Binary Tree of support vector machine (SVM), or BTS, in order to achieve high classification efficiency for multiclass problems. BTS and its enhanced version, c-BTS, decrease the number of binary classifiers to the greatest extent without increasing the complexity of the original problem. In the training phase, BTS has N-1 binary classifiers in the best situatio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Collision detection in complex dynamic scenes using an LGMD-based visual neural network with feature enhancement

    Publication Year: 2006, Page(s):705 - 716
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3832 KB) | HTML iconHTML

    The lobula giant movement detector (LGMD) is an identified neuron in the locust brain that responds most strongly to the images of an approaching object such as a predator. Its computational model can cope with unpredictable environments without using specific object recognition algorithms. In this paper, an LGMD-based neural network is proposed with a new feature enhancement mechanism to enhance ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Lidar detection of underwater objects using a neuro-SVM-based architecture

    Publication Year: 2006, Page(s):717 - 731
    Cited by:  Papers (30)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1099 KB) | HTML iconHTML

    This paper presents a neural network architecture using a support vector machine (SVM) as an inference engine (IE) for classification of light detection and ranging (Lidar) data. Lidar data gives a sequence of laser backscatter intensities obtained from laser shots generated from an airborne object at various altitudes above the earth surface. Lidar data is pre-filtered to remove high frequency no... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A softmin-based neural model for causal reasoning

    Publication Year: 2006, Page(s):732 - 744
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (485 KB) | HTML iconHTML

    This paper extends a neural model for causal reasoning to mechanize the monotonic class. Hence, the resulting model is able to solve multiple, varied causal problems in the open, independent, incompatibility and monotonic classes. First, additivity between causes is formalized as a fuzzy AND-ing process. Second, an activation mechanism called the "softmin" is developed to solve additive interactio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploiting application locality to design low-complexity, highly performing, and power-aware embedded classifiers

    Publication Year: 2006, Page(s):745 - 754
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (517 KB) | HTML iconHTML

    Temporal and spatial locality of the inputs, i.e., the property allowing a classifier to receive the same samples over time-or samples belonging to a neighborhood-with high probability, can be translated into the design of embedded classifiers. The outcome is a computational complexity and power aware design particularly suitable for implementation. A classifier based on the gated-parallel family ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Continuous-valued probabilistic behavior in a VLSI generative model

    Publication Year: 2006, Page(s):755 - 770
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1174 KB) | HTML iconHTML

    This paper presents the VLSI implementation of the continuous restricted Boltzmann machine (CRBM), a probabilistic generative model that is able to model continuous-valued data with a simple and hardware-amenable training algorithm. The full CRBM system consists of stochastic neurons whose continuous-valued probabilistic behavior is mediated by injected noise. Integrating on-chip training circuits... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On algorithmic rate-coded AER generation

    Publication Year: 2006, Page(s):771 - 788
    Cited by:  Papers (22)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1687 KB) | HTML iconHTML

    This paper addresses the problem of converting a conventional video stream based on sequences of frames into the spike event-based representation known as the address-event-representation (AER). In this paper we concentrate on rate-coded AER. The problem is addressed as an algorithmic problem, in which different methods are proposed, implemented and tested through software algorithms. The proposed... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Links between PPCA and subspace methods for complete Gaussian density estimation

    Publication Year: 2006, Page(s):789 - 792
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (226 KB) | HTML iconHTML

    High-dimensional density estimation is a fundamental problem in pattern recognition and machine learning areas. In this letter, we show that, for complete high-dimensional Gaussian density estimation, two widely used methods, probabilistic principal component analysis and a typical subspace method using eigenspace decomposition, actually give the same results. Additionally, we present a unified vi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A bottom-up method for simplifying support vector solutions

    Publication Year: 2006, Page(s):792 - 796
    Cited by:  Papers (14)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (226 KB) | HTML iconHTML

    The high generalization ability of support vector machines (SVMs) has been shown in many practical applications, however, they are considerably slower in test phase than other learning approaches due to the possibly big number of support vectors comprised in their solution. In this letter, we describe a method to reduce such number of support vectors. The reduction process iteratively selects two ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonlinear signal separation for multinonlinearity constrained mixing model

    Publication Year: 2006, Page(s):796 - 802
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (626 KB) | HTML iconHTML

    In this letter, a new type of nonlinear mixture is derived and developed into a multinonlinearity constrained mixing model. The proposed signal separation solution integrates the Theory of Series Reversion with a polynomial neural network whereby the hidden neurons are spanned by a set of mutually reversed activation functions. Simulations have been undertaken to support the theory of the proposed... View full abstract»

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

    Publication Year: 2006, Page(s):803 - 807
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (760 KB) | HTML iconHTML

    A more plausible biological version of the traditional perceptron is presented here with a learning rule which enables training of the neuron on nonlinear tasks. Three different models are introduced with varying inhibitory and excitatory synaptic connections. Using the derived learning rule, a single neuron is trained to successfully classify the XOR problem 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