# IEEE Transactions on Neural Networks and Learning Systems

## Volume 29 Issue 5 • May 2018

The purchase and pricing options for this item are unavailable. Select items are only available as part of a subscription package. You may try again later or contact us for more information.

## Filter Results

Displaying Results 1 - 25 of 55

Publication Year: 2018, Page(s):C1 - 1395
| PDF (125 KB)
• ### IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS publication information

Publication Year: 2018, Page(s): C2
| PDF (67 KB)
• ### Logistic Localized Modeling of the Sample Space for Feature Selection and Classification

Publication Year: 2018, Page(s):1396 - 1413
| | PDF (2931 KB) | HTML

Conventional feature selection algorithms assign a single common feature set to all regions of the sample space. In contrast, this paper proposes a novel algorithm for localized feature selection for which each region of the sample space is characterized by its individual distinct feature subset that may vary in size and membership. This approach can therefore select an optimal feature subset that... View full abstract»

• ### Manifold Warp Segmentation of Human Action

Publication Year: 2018, Page(s):1414 - 1426
Cited by:  Papers (1)
| | PDF (3614 KB) | HTML

Human action segmentation is important for human action analysis, which is a highly active research area. Most segmentation methods are based on clustering or numerical descriptors, which are only related to data, and consider no relationship between the data and physical characteristics of human actions. Physical characteristics of human motions are those that can be directly perceived by human b... View full abstract»

• ### Computational Model Based on Neural Network of Visual Cortex for Human Action Recognition

Publication Year: 2018, Page(s):1427 - 1440
| | PDF (4258 KB) | HTML

In this paper, we propose a bioinspired model for human action recognition through modeling neural mechanisms of information processing in two visual cortical areas: the primary visual cortex (V1) and the middle temporal cortex (MT) dedicated to motion. This model, named V1-MT, is composed of V1 and MT models (layers) corresponding to their cortical areas, which are built with layered spiking neur... View full abstract»

• ### DeepX: Deep Learning Accelerator for Restricted Boltzmann Machine Artificial Neural Networks

Publication Year: 2018, Page(s):1441 - 1453
| | PDF (1995 KB) | HTML

Although there have been many decades of research and commercial presence on high performance general purpose processors, there are still many applications that require fully customized hardware architectures for further computational acceleration. Recently, deep learning has been successfully used to learn in a wide variety of applications, but their heavy computation demand has considerably limi... View full abstract»

• ### Preconditioned Stochastic Gradient Descent

Publication Year: 2018, Page(s):1454 - 1466
| | PDF (1955 KB) | HTML

Stochastic gradient descent (SGD) still is the workhorse for many practical problems. However, it converges slow, and can be difficult to tune. It is possible to precondition SGD to accelerate its convergence remarkably. But many attempts in this direction either aim at solving specialized problems, or result in significantly more complicated methods than SGD. This paper proposes a new method to a... View full abstract»

• ### Global$H_\infty$Pinning Synchronization of Complex Networks With Sampled-Data Communications

Publication Year: 2018, Page(s):1467 - 1476
Cited by:  Papers (1)
| | PDF (4168 KB) | HTML

This paper investigates the global H∞pinning synchronization problem for a class of complex networks with aperiodic samplings. Combined with the Writinger-based integral inequality, a new less conservative criterion is presented to guarantee the global pinning synchronization of the complex network. Furthermore, a novel condition is proposed under which the complex network is globally p... View full abstract»

• ### Robust Finite-Time Stabilization of Fractional-Order Neural Networks With Discontinuous and Continuous Activation Functions Under Uncertainty

Publication Year: 2018, Page(s):1477 - 1490
| | PDF (1346 KB) | HTML

This paper is concerned with robust finite-time stabilization for a class of fractional-order neural networks (FNNs) with two types of activation functions (i.e., discontinuous and continuous activation function) under uncertainty. It is worth noting that there exist few results about FNNs with discontinuous activation functions, which is mainly because classical solutions and theories of differen... View full abstract»

• ### Stability Analysis and Application for Delayed Neural Networks Driven by Fractional Brownian Noise

Publication Year: 2018, Page(s):1491 - 1502
| | PDF (1349 KB) | HTML

This paper deals with two types of the stability problem for the delayed neural networks driven by fractional Brownian noise (FBN). The existence and the uniqueness of the solution to the main system with respect to FBN are proved via fixed point theory. Based on Hilbert-Schmidt operator theory and analytic semigroup principle, the mild solution of the stochastic neural networks is obtained. By ap... View full abstract»

• ### Discriminative Sparse Neighbor Approximation for Imbalanced Learning

Publication Year: 2018, Page(s):1503 - 1513
Cited by:  Papers (1)
| | PDF (2723 KB) | HTML

Data imbalance is common in many vision tasks where one or more classes are rare. Without addressing this issue, conventional methods tend to be biased toward the majority class with poor predictive accuracy for the minority class. These methods further deteriorate on small, imbalanced data that have a large degree of class overlap. In this paper, we propose a novel discriminative sparse neighbor ... View full abstract»

• ### Data-Driven Multiagent Systems Consensus Tracking Using Model Free Adaptive Control

Publication Year: 2018, Page(s):1514 - 1524
Cited by:  Papers (2)
| | PDF (1797 KB) | HTML

This paper investigates the data-driven consensus tracking problem for multiagent systems with both fixed communication topology and switching topology by utilizing a distributed model free adaptive control (MFAC) method. Here, agent's dynamics are described by unknown nonlinear systems and only a subset of followers can access the desired trajectory. The dynamical linearization technique is appli... View full abstract»

• ### Reinforced Robust Principal Component Pursuit

Publication Year: 2018, Page(s):1525 - 1538
| | PDF (2330 KB) | HTML

High-dimensional data present in the real world is often corrupted by noise and gross outliers. Principal component analysis (PCA) fails to learn the true low-dimensional subspace in such cases. This is the reason why robust versions of PCA, which put a penalty on arbitrarily large outlying entries, are preferred to perform dimension reduction. In this paper, we argue that it is necessary to study... View full abstract»

• ### Adaptive Boundary Iterative Learning Control for an Euler–Bernoulli Beam System With Input Constraint

Publication Year: 2018, Page(s):1539 - 1549
Cited by:  Papers (11)
| | PDF (1557 KB) | HTML

This paper addresses the vibration control and the input constraint for an Euler-Bernoulli beam system under aperiodic distributed disturbance and aperiodic boundary disturbance. Hyperbolic tangent functions and saturation functions are adopted to tackle the input constraint. A restrained adaptive boundary iterative learning control (ABILC) law is proposed based on a time-weighted Lyapunov-Krasovs... View full abstract»

• ### Synchronization of Coupled Reaction–Diffusion Neural Networks With Directed Topology via an Adaptive Approach

Publication Year: 2018, Page(s):1550 - 1561
Cited by:  Papers (2)
| | PDF (1051 KB) | HTML

This paper investigates the synchronization issue of coupled reaction-diffusion neural networks with directed topology via an adaptive approach. Due to the complexity of the network structure and the presence of space variables, it is difficult to design proper adaptive strategies on coupling weights to accomplish the synchronous goal. Under the assumptions of two kinds of special network structur... View full abstract»

• ### Solving Multiextremal Problems by Using Recurrent Neural Networks

Publication Year: 2018, Page(s):1562 - 1574
Cited by:  Papers (1)
| | PDF (2520 KB) | HTML

In this paper, a neural network model for solving a class of multiextremal smooth nonconvex constrained optimization problems is proposed. Neural network is designed in such a way that its equilibrium points coincide with the local and global optimal solutions of the corresponding optimization problem. Based on the suitable underestimators for the Lagrangian of the problem, one give geometric crit... View full abstract»

• ### Multitarget Sparse Latent Regression

Publication Year: 2018, Page(s):1575 - 1586
Cited by:  Papers (1)
| | PDF (1500 KB) | HTML

Multitarget regression has recently generated intensive popularity due to its ability to simultaneously solve multiple regression tasks with improved performance, while great challenges stem from jointly exploring inter-target correlations and input-output relationships. In this paper, we propose multitarget sparse latent regression (MSLR) to simultaneously model intrinsic intertarget correlations... View full abstract»

• ### Convolution in Convolution for Network in Network

Publication Year: 2018, Page(s):1587 - 1597
Cited by:  Papers (1)
| | PDF (2493 KB) | HTML

Network in network (NiN) is an effective instance and an important extension of deep convolutional neural network consisting of alternating convolutional layers and pooling layers. Instead of using a linear filter for convolution, NiN utilizes shallow multilayer perceptron (MLP), a nonlinear function, to replace the linear filter. Because of the powerfulness of MLP and 1 × 1 convolutions in spatia... View full abstract»

• ### Application of LMS-Based NN Structure for Power Quality Enhancement in a Distribution Network Under Abnormal Conditions

Publication Year: 2018, Page(s):1598 - 1607
Cited by:  Papers (3)
| | PDF (2642 KB) | HTML

This paper proposes an application of a least mean-square (LMS)-based neural network (NN) structure for the power quality improvement of a three-phase power distribution network under abnormal conditions. It uses a single-layer neuron structure for the control in a distribution static compensator (DSTATCOM) to attenuate the harmonics such as noise, bias, notches, dc offset, and distortion, injecte... View full abstract»

• ### A Confident Information First Principle for Parameter Reduction and Model Selection of Boltzmann Machines

Publication Year: 2018, Page(s):1608 - 1621
Cited by:  Papers (1)
| | PDF (1480 KB) | HTML Media

Typical dimensionality reduction (DR) methods are data-oriented, focusing on directly reducing the number of random variables (or features) while retaining the maximal variations in the high-dimensional data. Targeting unsupervised situations, this paper aims to address the problem from a novel perspective and considers model-oriented DR in parameter spaces of binary multivariate distributions. Sp... View full abstract»

• ### AnRAD: A Neuromorphic Anomaly Detection Framework for Massive Concurrent Data Streams

Publication Year: 2018, Page(s):1622 - 1636
| | PDF (2908 KB) | HTML

The evolution of high performance computing technologies has enabled the large-scale implementation of neuromorphic models and pushed the research in computational intelligence into a new era. Among the machine learning applications, unsupervised detection of anomalous streams is especially challenging due to the requirements of detection accuracy and real-time performance. Designing a computing f... View full abstract»

• ### Dynamic Uncertain Causality Graph for Knowledge Representation and Reasoning: Utilization of Statistical Data and Domain Knowledge in Complex Cases

Publication Year: 2018, Page(s):1637 - 1651
| | PDF (3285 KB) | HTML

The dynamic uncertain causality graph (DUCG) is a newly presented framework for uncertain causality representation and probabilistic reasoning. It has been successfully applied to online fault diagnoses of large, complex industrial systems, and decease diagnoses. This paper extends the DUCG to model more complex cases than what could be previously modeled, e.g., the case in which statistical data ... View full abstract»

• ### Recurrent Neural Networks With Auxiliary Memory Units

Publication Year: 2018, Page(s):1652 - 1661
| | PDF (1909 KB) | HTML

Memory is one of the most important mechanisms in recurrent neural networks (RNNs) learning. It plays a crucial role in practical applications, such as sequence learning. With a good memory mechanism, long term history can be fused with current information, and can thus improve RNNs learning. Developing a suitable memory mechanism is always desirable in the field of RNNs. This paper proposes a nov... View full abstract»

• ### Random Forest Classifier for Zero-Shot Learning Based on Relative Attribute

Publication Year: 2018, Page(s):1662 - 1674
| | PDF (4043 KB) | HTML

For the zero-shot image classification with relative attributes (RAs), the traditional method requires that not only all seen and unseen images obey Gaussian distribution, but also the classifications on testing samples are made by maximum likelihood estimation. We therefore propose a novel zero-shot image classifier called random forest based on relative attribute. First, based on the ordered and... View full abstract»

• ### Improving Crowdsourced Label Quality Using Noise Correction

Publication Year: 2018, Page(s):1675 - 1688
| | PDF (4266 KB) | HTML

Crowdsourcing systems provide a cost effective and convenient way to collect labels, but they often fail to guarantee the quality of the labels. This paper proposes a novel framework that introduces noise correction techniques to further improve the quality of integrated labels that are inferred from the multiple noisy labels of objects. In the proposed general framework, information about the qua... View full abstract»

## Aims & Scope

IEEE Transactions on Neural Networks and Learning Systems publishes technical articles that deal with the theory, design, and applications of neural networks and related learning systems.

Full Aims & Scope

## Meet Our Editors

Editor-in-Chief
Haibo He
Dept. of Electrical, Computer, and Biomedical Engineering
University of Rhode Island
Kingston, RI 02881, USA
ieeetnnls@gmail.com