Showing papers in "Neural Networks in 2009"

TL;DR: A new Multi-Spiking Neural Network (MuSpiNN) model is presented in which information from one neuron is transmitted to the next in the form of multiple spikes via multiple synapses and the model and learning algorithm employ the heuristic rules and optimum parameter values presented by the authors in a recent paper that improved the efficiency of the original single-spiking SNN model by two orders of magnitude.

TL;DR: In this article, an online approach to direct adaptive optimal control with infinite horizon cost for nonlinear systems is presented, based on a reinforcement learning scheme, namely Policy Iterations, and makes use of neural networks, in an Actor/Critic structure, to parametrically represent the control policy and the performance of the control system.

TL;DR: In this paper, an advanced learning paradigm called Learning Using Hidden Information (LUHI) was introduced, where a teacher can provide students with hidden information that exists in explanations, comments, comparisons, and so on.

TL;DR: The PNN model presented in this paper complements the recurrent neural network model developed by the authors previously, where good results were reported for predicting earthquakes with magnitude greater than 6.0.

TL;DR: This paper introduces a feature called Time Domain Parameter that is defined by the generalization of the Hjorth parameters, and shows that Time Domain Parameters outperform all band power features tested with all spatial filters applied.

TL;DR: A novel technique for the automatic design of Artificial Neural Networks (ANNs) by evolving to the optimal network configuration(s) within an architecture space based on a multi-dimensional Particle Swarm Optimization technique.

TL;DR: This work uses a large database of EEG recordings from 45 subjects, who took part in movement imagination task experiments, to construct an ensemble of classifiers derived from subject-specific temporal and spatial filters.

TL;DR: This paper investigates cluster synchronization in an array of hybrid coupled neural networks with delay by constructing a special coupling matrix based on Lyapunov stability theory and the linear matrix inequality (LMI) technique.

TL;DR: An effective linear matrix inequality approach is developed to solve the neuron state estimation problem for a class of Markovian neural networks with discrete and distributed time-delays.

TL;DR: Results indicate significant potential for the use of vowel speech imagery as a speech prosthesis controller in brain-computer interfaces for individuals with severe communication impairments.

TL;DR: In this review, fundamental principles, recent developments, applications and future directions and challenges of NIRS-based and fMRI-based BCIs are considered.

TL;DR: In this article, a neural network is tuned online using novel tuning laws to learn the complete plant dynamics so that a local asymptotic stability of the identification error can be shown.

TL;DR: A linear feature selection and classification scheme is applied to identify P300 events and calculate gradual feedback features from a scalp electrode array to achieve classification rates of 0.65 on single-trials during the online operation of the system while providing gradual feedback to the player.

TL;DR: This paper attempts to address how the brain makes inferences by casting inference as an optimisation problem by focusing on a model whose hierarchical and dynamical structure enables simulated brains to recognise and predict sequences of sensory states.

TL;DR: In this article, the authors demonstrate an efficient, biologically realistic, large-scale SNN simulator that runs on a single GPU, which includes Izhikevich spiking neurons, detailed models of synaptic plasticity and variable axonal delay.

TL;DR: Local-circuit mechanisms involved in hippocampal CA3 gamma oscillations, one of the best understood locally generated network patterns in the mammalian brain, are discussed, suggesting that local gammascillations not only control when, but also how many and which pyramidal cells will fire during each gamma cycle.

TL;DR: By constructing a new Lyapnuov-Krasovskii functional, a linear matrix inequality (LMI) approach is developed to establish sufficient conditions for the discrete-time neural networks to be globally asymptotically stable.

TL;DR: It is found that, with realistic in vivo background input, small assemblies of synchronised MSNs spontaneously appear, consistent with experimental observations, and that the number of assemblies and the time-scale of synchronisation is strongly dependent on the simulated concentration of dopamine.

TL;DR: A framework for modeling the closed-loop performance of the PVA and the OLE is presented, which shows that the performance gain with certain decoders can be far less extreme than predicted by off-line results, that subjects are able to compensate for certain types of bias in decodering, and that care must be taken to ensure that estimation error does not degrade the performance of theoretically optimal decoder.

TL;DR: A multiple-input, multiple-output (MIMO) nonlinear dynamic model for the input-output transformation of spike trains is formulated and it is shown that this model is equivalent to a generalized linear model with a probit link function.

TL;DR: A model of co-operative competitive processing that is consistent with the observed connectivity in the superficial layers of the cortex is discussed, and also how the topology of the overall cortical circuit could be configured dynamically through average inhibition is considered.

TL;DR: It is formally shown that the resulting estimation bias is bounded and asymptotically vanishes, which allows the experience replay-augmented algorithm to preserve the convergence properties of the original algorithm.

TL;DR: Sufficient conditions are obtained to ensure the existence and stability of the unique periodic solution for the neural networks by using the differential inclusions theory, the Lyapunov-Krasovskii functional method and linear matrix inequality (LMI) technique.

TL;DR: Improved criteria for the passivity of neural networks with time delay are proposed by exploiting the finer relationships between the time-varying delay and its size bound which allow the use of more slack variables.

TL;DR: In this article, a quantum-inspired spiking neural network (QiSNN) is proposed to solve the problem of invasive species establishment prediction using a binary representation for optimizing feature subsets and a continuous representation for evolving appropriate real-valued configurations of the network.

TL;DR: The synchronization problem is studied in this paper for nonidentical chaotic neural networks with time delays, where the mismatched parameters are taken into account and an integral sliding mode control approach is proposed to address it.

TL;DR: This division in terms of the various distinctions that accompany it in the fields of reinforcement learning and cognitive architectures is reviewed, considering issues such as declarative and procedural control, the effect of prior distributions over environments, the neural substrates involved, and the differing views about the relative rationality of theVarious forms of control.

TL;DR: This study serves as a review of available spike train smoothers and a first quantitative comparison of their performance for brain-machine interfaces.

TL;DR: In this article, the authors considered conceptual and emotional mechanisms of language along with their role in the mind and cultural evolution and suggested neural mechanisms of these processes as well as their mathematical models: the knowledge instinct, the dual model connecting language and cognition, neural modeling fields.

TL;DR: The proposed model resolves some long-standing language-cognition issues: how the mind learns correct associations between words and objects among an astronomical number of possible associations; why kids can talk about almost everything, but cannot act like adults, what exactly are the brain-mind differences.