<![CDATA[ IEEE Transactions on Neural Networks and Learning Systems - new TOC ]]>
http://ieeexplore.ieee.org
TOC Alert for Publication# 5962385 2017September18<![CDATA[Table of contents]]>2810C12221117<![CDATA[IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS publication information]]>2810C2C268<![CDATA[LSTM: A Search Space Odyssey]]>$\approx 15$ years of CPU time), which makes our study the largest of its kind on LSTM networks. Our results show that none of the variants can improve upon the standard LSTM architecture significantly, and demonstrate the forget gate and the output activation function to be its most critical components. We further observe that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.]]>2810222222322761<![CDATA[A New Discriminative Sparse Representation Method for Robust Face Recognition via $l_{2}$ Regularization]]>$l_{2}$ regularization-based representation are comprehensively shown by extensive experiments and analysis. The code of the proposed method is available at http://www.yongxu.org/lunwen.html.]]>2810223322422501<![CDATA[Kinematic Control of Redundant Manipulators Using Neural Networks]]>2810224322542438<![CDATA[Improving Neural-Network Classifiers Using Nearest Neighbor Partitioning]]>2810225522673011<![CDATA[Mesh Convolutional Restricted Boltzmann Machines for Unsupervised Learning of Features With Structure Preservation on 3-D Meshes]]>2810226822813082<![CDATA[Resolution of Singularities Introduced by Hierarchical Structure in Deep Neural Networks]]>2810228222931120<![CDATA[Semisupervised Feature Analysis by Mining Correlations Among Multiple Tasks]]>2810229423055390<![CDATA[Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics]]>2810230623183316<![CDATA[Fractional Hopfield Neural Networks: Fractional Dynamic Associative Recurrent Neural Networks]]>2810231923333584<![CDATA[Synchronization of Switched Neural Networks With Communication Delays via the Event-Triggered Control]]>281023342343547<![CDATA[A Collective Neurodynamic Optimization Approach to Nonnegative Matrix Factorization]]>2810234423562526<![CDATA[A Biologically Inspired Appearance Model for Robust Visual Tracking]]>2810235723702113<![CDATA[Optimized Structure of the Traffic Flow Forecasting Model With a Deep Learning Approach]]>2810237123812285<![CDATA[Event-Based $H_\infty $ State Estimation for Time-Varying Stochastic Dynamical Networks With State- and Disturbance-Dependent Noises]]>$H_\infty $ state estimation problem is investigated for a class of discrete time-varying stochastic dynamical networks with state- and disturbance-dependent noises [also called $(x,v)$ -dependent noises]. An event-triggered scheme is proposed to decrease the frequency of the data transmission between the sensors and the estimator, where the signal is transmitted only when certain conditions are satisfied. The purpose of the problem addressed is to design a time-varying state estimator in order to estimate the network states through available output measurements. By employing the completing-the-square technique and the stochastic analysis approach, sufficient conditions are established to ensure that the error dynamics of the state estimation satisfies a prescribed $H_\infty $ performance constraint over a finite horizon. The desired estimator parameters can be designed via solving coupled backward recursive Riccati difference equations. Finally, a numerical example is exploited to demonstrate the effectiveness of the developed state estimation scheme.]]>2810238223941534<![CDATA[Hierarchical Address Event Routing for Reconfigurable Large-Scale Neuromorphic Systems]]>$3.6\times 10^{7}$ synaptic events per second per 16k-neuron node in the hierarchy.]]>2810240824223937<![CDATA[LMI Conditions for Global Stability of Fractional-Order Neural Networks]]>2810242324333938<![CDATA[Off-Policy Reinforcement Learning for Synchronization in Multiagent Graphical Games]]>2810243424451367<![CDATA[Observer-Based Discrete-Time Nonnegative Edge Synchronization of Networked Systems]]>281024462455967<![CDATA[Stability of Recurrent Neural Networks With Time-Varying Delay via Flexible Terminal Method]]>281024562463713<![CDATA[Call For Papers: IEEE World Congress on Computational Intelligence]]>2810246424641346<![CDATA[IEEE Computational Intelligence Society Information]]>2810C3C3102<![CDATA[IEEE Transactions on Neural Networks information for authors]]>2810C4C4122