Showing papers in "Neural Networks in 2011"

TL;DR: Experimental results show that the FS-RBFNN can be used to design an RBF structure which has fewer hidden neurons; the training time is also much faster and the algorithm is applied for predicting water quality in the wastewater treatment process.

TL;DR: Global dissipativity and quasi-synchronization issues are investigated for the delayed neural networks with discontinuous activation functions and, when the proper approximate functions are selected, the complete synchronization can be discussed as a special case that two systems are identical.

TL;DR: Experimental evidences confirm the role of the Markovian factor and show that all the identified key architectural factors have a major role in determining ESN performances.

TL;DR: This paper focuses on a methodological framework for the development of an automated data imputation model based on artificial neural networks, and suggests this approach improves the quality of a database with missing values.

TL;DR: Some weak and strong convergence results for the learning methods are presented, indicating that the gradient of the error function goes to zero and the weight sequence goes to a fixed point, respectively.

TL;DR: The main feature of the results obtained in this paper is that they are dependent on not only the bound but also the distribution probability of the time delay, and the authors obtain a larger allowance variation range of the delay, hence the results are less conservative than the traditional delay-independent ones.

TL;DR: A remarkable role of the synaptic connectivities in the inhibitory thalamic cell populations on the alpha band power and frequency is shown and produces the slowing of alpha rhythms and a simultaneous decrease ofalpha band power in the brain as a result of AD.

TL;DR: This paper investigates multistability of discrete-time Hopfield-type neural networks with distributed delays and impulses by using Lyapunov functionals, stability theory and control by impulses.

TL;DR: This paper proposes a novel approach to learn highly scalable CPs of basis movement skills from multiple demonstrations that allow the synthesis of novel movements with novel motion styles by specifying the linear coefficients of the bases as parameter vectors without losing useful properties of the DMPs.

TL;DR: The proposed framework aims at improving the discriminative power of supervised tensor-based models while still exploiting the structural information embodied in the data through the use of kernels that exploit the algebraic structure of data tensors.

TL;DR: This paper proposes an extension to conventional regression neural networks for replacing the point predictions they produce with prediction intervals that satisfy a required level of confidence and evaluates the proposed method on four benchmark datasets.

TL;DR: The multivariate quantitative constructive approximation of real and complex valued continuous multivariate functions on a box or RN, N∈N, by the multivariate quasi-interpolation sigmoidal neural network operators is studied.

TL;DR: It is argued that CMs have yet to influence psychiatric practice, but that they help psychiatric research in two fundamental ways: to build better theories integrating psychiatry with neuroscience; and to enforce explicit, global and efficient testing of hypotheses through more powerful analytical methods.

TL;DR: A hybrid model consisting of an Artificial Neural Network (ANN) and a Genetic Algorithm procedure for diagnostic risk factors selection in Medicine is proposed, finding a number of diagnostic factors in a patient's data record can be omitted without loss of fidelity in the diagnosis procedure.

TL;DR: A rather simple WM model in which all of these performance modes are trained into a recurrent neural network (RNN) of the echo state network (ESN) type, which is demonstrated on a bracket level parsing task.

TL;DR: The paper unifies periodic discrete-time and continuous-time BAM neural networks under the same framework by constructing a Lyapunov functional and discussing the global exponential stability of the periodic solution for such neural networks on time scales.

TL;DR: An adaptive classification method for the Brain Computer Interfaces which uses Interaction Error Potentials (IErrPs) as a reinforcement signal and adapts the classifier parameters when an error is detected is proposed.

TL;DR: This paper presents results on a computational study of how multi-site stimulation of the subthalamic nucleus (STN), within the basal ganglia, can improve the fidelity of thalamocortical (TC) relay in a parkinsonian network model.

TL;DR: Experimental results show that the proposed adaptive classifier based on the intersection of confidence intervals rule is particularly effective in situations where the process is subject to abrupt changes.

TL;DR: A methodology for understanding the relationship of gene expression and neuroanatomy based on correlation between gene expression profiles across tissue samples is presented and a resulting tool, NeuroBlast, can identify networks of genes co-expressed within or across neuroanatomic structures.

TL;DR: The proposed method, D(3)-LHSS (Direct Density-ratio estimation with Dimensionality reduction via Least-squares Hetero-distributional Subspace Search), is shown to overcome the limitation of baseline methods.

TL;DR: By applying the existence result of an equilibrium point and constructing a Lyapunov functional, the existence and uniqueness of the equilibrium point of interval general BAM neural networks with reaction-diffusion terms and multiple time-varying delays are discussed.

TL;DR: Experimental results on multiple human cancer data sets show that BARTMAP can achieve clustering structures with higher qualities than those achieved with other commonly used biclustering or clustering algorithms, and with fast run times.

TL;DR: The potential power of GPGPU techniques in real-time simulation of realistic neural networks is suggested, using a model of the basal ganglia that has been developed according to electrophysiological and anatomical knowledge.

TL;DR: An extended model is described that includes simulation of the different functional role of D1 and D2 dopamine receptors in the basal ganglia and prefrontal cortex, a dissociation it is argued is essential for understanding the non-uniform effects of levodopa, dopamine agonists, and antipsychotics on cognition.

TL;DR: The recall phase of fuzzy morphological associative memories is characterized and several theorems concerning the storage capacity, noise tolerance, fixed points, and convergence of auto-associative FMAMs are proved.

TL;DR: A neural model is proposed to explain how spatial and object attention coordinate the ability of IT to learn invariant category representations of objects that are seen at multiple positions, sizes, and viewpoints, and how such invariant learning can be fooled when monkeys, or other primates, are presented with an object that is swapped with another object during eye movements to foveate the original object.

TL;DR: It is shown that a Multiple Timescale Recurrent Neural Network (MTRNN) can acquire the capabilities to recognize, generate, and correct sentences by self-organizing in a way that mirrors the hierarchical structure of sentences: characters grouped into words, and words into sentences.

TL;DR: A pipeline of tools that allow investigating information flow by simulating electrical signals that propagate through anatomically realistic models of average neural networks are described, and a simulation framework, NeuroDUNE, is introduced to investigate structure-function relationships within networks of full-compartmental neuron models at subcellular, cellular and network levels.

TL;DR: This paper addresses the issue of multiple kernel learning for LS-SVM by formulating it as semidefinite programming (SDP) and shows that the regularization parameter can be optimized in a unified framework with the kernel, which leads to an automatic process for model selection.