scispace - formally typeset
Search or ask a question

Showing papers in "Neurocomputing in 2008"


Journal ArticleDOI
TL;DR: The proposed enhanced I-ELM works for the widespread type of piecewise continuous hidden nodes and is proposed as a universal approximator for constructive feedforward networks.

867 citations


Journal ArticleDOI
TL;DR: It is shown that several well-known reinforcement learning methods such as the original Actor-Critic and Bradtke's Linear Quadratic Q-Learning are in fact Natural Actor- Critic algorithms.

659 citations


Journal ArticleDOI
TL;DR: It is shown that the original architecture of the NARX network can be easily and efficiently applied to long-term (multi-step-ahead) prediction of univariate time series and consistently outperforms standard neural network based predictors, such as the TDNN and Elman architectures.

381 citations


Journal ArticleDOI
TL;DR: A new fusion algorithm for multimodal medical images based on contourlet transform is proposed, which can provide a more satisfactory fusion outcome compared with conventional image fusion algorithms.

353 citations


Journal ArticleDOI
TL;DR: The proposed pruned- ELM (P-ELM) algorithm is described as a systematic and automated approach for designing ELM classifier network that leads to compact network classifiers that generate fast response and robust prediction accuracy on unseen data, comparing with traditional ELM and other popular machine learning approaches.

342 citations


Journal ArticleDOI
TL;DR: This review focuses on detectors and local descriptors, which are widely utilized in a large number of applications, e.g., object categorization, image retrieval, robust matching, and robot localization.

300 citations


Journal ArticleDOI
TL;DR: This paper presents a robust analysis approach to asymptotic stability of the delayed genetic regulatory networks (GRNs) with SUM regulatory logic in which each transcription factor acts additively to regulate a gene, i.e., the regulatory function sums over all the inputs.

280 citations


Journal ArticleDOI
TL;DR: It is shown that, as long as the hidden layer activation function is complex continuous discriminatory or complex bounded nonlinear piecewise continuous, I-ELM can still approximate any target functions in the complex domain.

247 citations


Journal ArticleDOI
TL;DR: It is clearly demonstrate that IP is able to make reservoir computing more robust: the internal dynamics can autonomously tune themselves-irrespective of initial weights or input scaling-to the dynamic regime which is optimal for a given task.

213 citations


Journal ArticleDOI
TL;DR: A new procedure to predict time series using paradigms such as: fuzzy systems, neural networks and evolutionary algorithms, so that the linear model can be identified automatically, without the need of human expert participation is presented.

203 citations


Journal ArticleDOI
TL;DR: An improved particle swarm optimization and discrete PSO (DPSO) with an enhancement operation by using a self-adaptive evolution strategies (ES) is proposed for joint optimization of three-layer feedforward artificial neural network structure and parameters (weights and bias), which is named ESPNet.

Journal ArticleDOI
Xiaoxin Guo1, Jinhui Yang1, C. G. Wu1, Chaoyong Wang1, Yanhua Liang1 
TL;DR: A novel hyper-parameter selection method for LS-SVMs is presented based on the particle swarm optimization (PSO), which does not need any priori knowledge on the analytic property of the generalization performance measure and can be used to determine multiplehyper-parameters at the same time.

Journal ArticleDOI
TL;DR: Experimental results reveal that the predictions using the proposed approach are consistently better than those obtained using the other methods presented in this study in terms of the same measurements.

Journal ArticleDOI
TL;DR: A novel semi-supervised feature selection algorithm, which makes use of both labeled and unlabeled data points, which is compared with Fisher score and Laplacian score on face recognition and demonstrates the efficiency and effectiveness of the algorithm.

Journal ArticleDOI
TL;DR: A review of the current state of research regarding the incorporation of two general types of prior knowledge into SVMs for classification and a discussion is conducted to regroup sample and optimization methods under a regularization framework.

Journal ArticleDOI
TL;DR: A combination of spatial ICA with spectral Bayesian positive source (BPSS) with a rough classification of pixels is proposed, which allows selection of small, but relevant, number of pixels for the component extraction and consequently the endmember classification.

Journal ArticleDOI
TL;DR: An online SVM model to predictAir pollutant levels in an advancing time-series based on the monitored air pollutant database in Hong Kong downtown area is developed and the experimental comparison between the online and conventional SVM models demonstrates the effectiveness and efficiency in predicting air quality parameters with different time series.

Journal ArticleDOI
TL;DR: This paper proposes a new algorithm based on a back-propagation (BP) network combined with an observation model that provides an effective method of obtaining the sub-pixel mapping result and can provide an approximation of the reference classification image.

Journal ArticleDOI
TL;DR: Experiments conducted on the real data sets CB513 and RS126 demonstrate that the proposed ELM based protein secondary structure prediction framework can achieve as good prediction accuracy as other popular methods; however, at very fast learning speed.

Journal ArticleDOI
TL;DR: This paper investigates the use of genetic algorithms (GAs) to tune the parameters of the binary SVMs in common multiclass decompositions.

Journal ArticleDOI
TL;DR: A delay-dependent condition guaranteeing the global exponential stability of the concerned neural network is obtained in terms of a linear matrix inequality, which is less conservative than some previous ones in the literature.

Journal ArticleDOI
TL;DR: Group method of data handling (GMDH) neural network, composed of self-organizing active neurons, was proven very effective in producing forecasts that were significantly more accurate and less labor-intensive than traditional time-series and regression-based models.

Journal ArticleDOI
TL;DR: Experiments performed on a corpus composed of Shakespeare's writings show its linguistic analysis and categorization abilities.

Journal ArticleDOI
TL;DR: Different from the commonly used matrix norm theories, a unified LMI approach is developed to establish sufficient conditions for the neural networks to be globally, robustly, exponentially stable.

Journal ArticleDOI
TL;DR: A new spiking neural network architecture and its corresponding learning procedure to perform fast and adaptive multi-view visual pattern recognition and the two main novelties of the network: structural adaptation and frame-by-frame accumulation of opinions are described.

Journal ArticleDOI
TL;DR: The results demonstrate that the approaches are useful in forecasting alternatives for interval-valued time series and indicate that the hybrid model is an effective way to improve the forecasting accuracy achieved by any one of the models separately.

Journal ArticleDOI
TL;DR: A multi-timescale learning rule for spiking neuron networks, in the line of the recently emerging field of reservoir computing, emphasizes that polychronization can be used as a tool for exploiting the computational power of synaptic delays and for monitoring the topology and activity of a spiking neurons network.

Journal ArticleDOI
TL;DR: The approach proposed in this paper has good classification accuracy compared with classic SVM while the training is significantly faster than several other SVM classifiers.

Journal ArticleDOI
TL;DR: By employing Lyapunov functional and the free-weighting matrix method, several sufficient conditions in linear matrix inequality form are obtained to ensure the existence, uniqueness and global exponential stability of equilibrium point for the neural networks.

Journal ArticleDOI
TL;DR: This paper shows how a kernel version of the batch self-organizing map can be used to achieve goals via kernels derived from the Laplacian matrix of the graph, especially when it is used in conjunction with more classical methods based on the spectral analysis of thegraph.