scispace - formally typeset
Search or ask a question

Showing papers in "Neurocomputing in 2006"


Journal ArticleDOI
TL;DR: A new learning algorithm called ELM is proposed for feedforward neural networks (SLFNs) which randomly chooses hidden nodes and analytically determines the output weights of SLFNs which tends to provide good generalization performance at extremely fast learning speed.

10,217 citations


Journal ArticleDOI
TL;DR: A hybrid training algorithm of particle swarm optimization with diversity learning and gradient descent method is introduced for training the local linear wavelet neural network (LLWNN).

333 citations


Journal ArticleDOI
TL;DR: A neural algorithm is proposed using a Newton-like approach to obtain an optimal solution to the constrained optimization problem and experiments with synthetic signals and real fMRI data demonstrate the efficacy and accuracy of the proposed algorithm.

216 citations


Journal ArticleDOI
TL;DR: This paper investigates bifurcations of invariant sets in a five-dimensional parameter space, and identifies an essential parameter of the half-activated potential of the potassium activation curve that contributes to the alternation of the membrane properties of the M-L neuron.

215 citations


Journal ArticleDOI
TL;DR: A novel and successful method for recognizing palmprint based on radial basis probabilistic neural network (RBPNN), which achieves higher recognition rate and better classification efficiency than other usual classifiers.

201 citations


Journal ArticleDOI
TL;DR: In this article, the authors investigate the use of support vector machines (SVM) for functional data analysis (FDA) and focus on the problem of curve discrimination and define simple kernels that take into account the functional nature of the data and lead to consistent classification.

198 citations


Journal ArticleDOI
TL;DR: A computational model is presented that describes dual mechanisms of cognitive control through interactions between the prefrontal cortex (PFC) and anterior cingulate cortex (ACC) that provided an excellent fit to both the behavioral and brain imaging data from a previous detailed empirical study on humans performing the color-word version of the Stroop task.

196 citations


Journal ArticleDOI
TL;DR: Employing linear matrix inequality and general Lyapunov-Krasovskii functional, the global exponential stability and the existence of periodic solutions are studied for fuzzy cellular neural networks with time-varying delays in this paper.

177 citations


Journal ArticleDOI
TL;DR: The experiments were carried out using a dataset of software projects from NASA and the results have shown that SVR significantly outperforms RBFNs and linear regression in this task.

164 citations


Journal ArticleDOI
TL;DR: The results indicate that the choice of basis function (and, where appropriate, basis width parameter) is data set dependent and evaluating all recognised basis functions suitable for RBF networks is advantageous.

154 citations


Journal ArticleDOI
TL;DR: This paper explicates on the intricacies of the proposed framework in addition to presenting detailed empirical results and comparisons with a wide range of algorithms in the machine learning literature.

Journal ArticleDOI
TL;DR: This letter proposes to perform natural colour rendition in a digital colour image that is enhanced by a homomorphic filter, and uses a novel neural network learning algorithm, named Ratio rule, to carry out thenatural colour rendition process.

Journal ArticleDOI
TL;DR: This paper introduces a new method for automatic kernel selection, with empirical results based on classification, and presents a rule-based method to select the most appropriate kernel for a classification problem.

Journal ArticleDOI
TL;DR: Experimental results on the wind prediction problem demonstrate that the proposed algorithms exhibit enhanced performance, in terms of convergence speed and the accuracy of the attained solutions, compared to conventional gradient-based methods.

Journal ArticleDOI
TL;DR: A wavelet multiscale decomposition-based autoregressive approach for the prediction of 1-h ahead load based on historical electricity load data, based on a multiple resolution decomposition of the signal using the non-decimated or redundant Haar a trous wavelet transform whose advantage is taking into account the asymmetric nature of the time-varying data.

Journal ArticleDOI
TL;DR: A powerful evolutional particle swarm optimization (PSO) learning algorithm is developed that self-generates radial basis function neural networks (RBFNs) to deal with three nonlinear problems.

Journal ArticleDOI
TL;DR: The main purpose of this paper is to establish easily verifiable conditions under which the delayed stochastic neural network is exponentially stable in the mean square in the presence of both the discrete and distributed delays.

Journal ArticleDOI
TL;DR: The proposed approach was applied for two real-world problems involving designing intrusion detection system (IDS) and for breast cancer classification and empirical results indicate that the proposed method is efficient for both input feature selection and improved classification rate.

Journal ArticleDOI
TL;DR: A class of improved extreme learning machines encoding a priori information is proposed to obtain better generalization performance and much faster convergence rate for function approximation.

Journal ArticleDOI
TL;DR: A novel approach to fuzzy clustering is described, which organizes the data in clusters on the basis of the input data and a 'prototype' regression function built, in the output space, as a summation of a number of linear local regression models.

Journal ArticleDOI
TL;DR: In this paper, a locally regularized orthogonal least squares (LROLS) algorithm is proposed for constructing parsimonious or sparse regression models that generalize well by associating each weight in the regression model with an individual regularization parameter.

Journal ArticleDOI
TL;DR: Simple and fast methods based on nearest neighbors that order objects from high-dimensional data sets from typical points to untypical points allow us to detect outliers with a performance comparable to or better than other often much more sophisticated methods.

Journal ArticleDOI
TL;DR: A new derivation of the novelty detection algorithm based on the one class SVM is proposed to illustrate the power of the exponential family model in an RKHS.

Journal ArticleDOI
TL;DR: A stochastic gain-tuning model is used to investigate interactions between aging-related increase of endogenous neuronal noise and external input noise in affecting SR to suggest that determining the optimal proportion of resonance-inducing external noise as a function of internal-system stochastically gain tuning properties promotes unified theorizing about sensory and cognitive aging at behavioral and neural levels of analysis.

Journal ArticleDOI
TL;DR: This paper presents a pruning technique, by means of a quantified sensitivity measure, to remove as many neurons as possible, those with the least relevance, from the hidden layer of a multilayer perceptron (MLP).

Journal ArticleDOI
TL;DR: The proposed approach to extract rules from multilayer perceptrons trained in classification problems is experimentally evaluated in four datasets that are benchmarks for data mining applications and in a real-world meteorological dataset, leading to interesting results.

Journal ArticleDOI
TL;DR: The lobula giant movement detector neuron of locusts is presented and the functional parameters of the model identified and the model evolved most rapidly using GAs with high clone rates into a form suitable for detecting collisions with cars and not producing false collision alerts to most non-collision scenes.

Journal ArticleDOI
TL;DR: A simple neuron-based adaptive controller for trajectory tracking is developed for nonholonomic mobile robots without velocity measurements that is robust not only to structured uncertainty such as mass variation but also to unstructured one such as disturbances.

Journal ArticleDOI
TL;DR: The software package NeuGen generates non-identical neurons of morphological classes of the cortex, e.g., pyramidal cells and stellate neurons, and synaptically connected neural networks in 3D through sets of descriptive and iterative rules based on axonal and dendritic geometry.

Journal ArticleDOI
TL;DR: The sequential floating forward selection technique is used to select the independent components of the DNA microarray data for classification and experimental results show that the method is efficient and feasible.