# IEEE Transactions on Neural Networks and Learning Systems

## Volume 28 Issue 8 • Aug. 2017

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 25

Publication Year: 2017, Page(s):C1 - 1733
| PDF (116 KB)
• ### IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS publication information

Publication Year: 2017, Page(s): C2
| PDF (79 KB)
• ### A Survey of Memristive Threshold Logic Circuits

Publication Year: 2017, Page(s):1734 - 1746
Cited by:  Papers (1)
| | PDF (3721 KB) | HTML

In this paper, we review different memristive threshold logic (MTL) circuits that are inspired from the synaptic action of the flow of neurotransmitters in the biological brain. The brainlike generalization ability and the area minimization of these threshold logic circuits aim toward crossing Moore's law boundaries at device, circuits, and systems levels. Fast switching memory, signal processing,... View full abstract»

• ### A Collective Neurodynamic Approach to Distributed Constrained Optimization

Publication Year: 2017, Page(s):1747 - 1758
Cited by:  Papers (6)
| | PDF (5699 KB) | HTML

This paper presents a collective neurodynamic approach with multiple interconnected recurrent neural networks (RNNs) for distributed constrained optimization. The objective function of the distributed optimization problems to be solved is a sum of local convex objective functions, which may be nonsmooth. Subject to its local constraints, each local objective function is minimized individually by u... View full abstract»

• ### Spectrum-Diverse Neuroevolution With Unified Neural Models

Publication Year: 2017, Page(s):1759 - 1773
| | PDF (3699 KB) | HTML

Learning algorithms are being increasingly adopted in various applications. However, further expansion will require methods that work more automatically. To enable this level of automation, a more powerful solution representation is needed. However, by increasing the representation complexity, a second problem arises. The search space becomes huge, and therefore, an associated scalable and efficie... View full abstract»

• ### Designing and Implementation of Stable Sinusoidal Rough-Neural Identifier

Publication Year: 2017, Page(s):1774 - 1786
| | PDF (2522 KB) | HTML

A rough neuron is defined as a pair of conventional neurons that are called the upper and lower bound neurons. In this paper, the sinusoidal rough-neural networks (SR-NNs) are used to identify the discrete dynamic nonlinear systems (DDNSs) with or without noise in series-parallel configuration. In the identification of periodic nonlinear systems, sinusoidal activation functions provide more effici... View full abstract»

• ### MR-NTD: Manifold Regularization Nonnegative Tucker Decomposition for Tensor Data Dimension Reduction and Representation

Publication Year: 2017, Page(s):1787 - 1800
| | PDF (1675 KB) | HTML

With the advancement of data acquisition techniques, tensor (multidimensional data) objects are increasingly accumulated and generated, for example, multichannel electroencephalographies, multiview images, and videos. In these applications, the tensor objects are usually nonnegative, since the physical signals are recorded. As the dimensionality of tensor objects is often very high, a dimension re... View full abstract»

• ### Understanding Social Causalities Behind Human Action Sequences

Publication Year: 2017, Page(s):1801 - 1813
Cited by:  Papers (1)
| | PDF (1705 KB) | HTML

Social causality study on human action sequences is useful and important to improve our understandings to human behaviors on online social networks. The redundant indirect causalities and unobserved confounding factors, such as homophily and simultaneity phenomena, contribute to the huge challenges on accurate causal discovery on such human actions. A causal relationship exists between two persons... View full abstract»

• ### Bridging the Gap Between Imitation Learning and Inverse Reinforcement Learning

Publication Year: 2017, Page(s):1814 - 1826
| | PDF (1654 KB) | HTML

Learning from demonstrations is a paradigm by which an apprentice agent learns a control policy for a dynamic environment by observing demonstrations delivered by an expert agent. It is usually implemented as either imitation learning (IL) or inverse reinforcement learning (IRL) in the literature. On the one hand, IRL is a paradigm relying on the Markov decision processes, where the goal of the ap... View full abstract»

• ### Passivity of Directed and Undirected Complex Dynamical Networks With Adaptive Coupling Weights

Publication Year: 2017, Page(s):1827 - 1839
Cited by:  Papers (2)
| | PDF (2249 KB) | HTML

A complex dynamical network consisting of N identical neural networks with reaction-diffusion terms is considered in this paper. First, several passivity definitions for the systems with different dimensions of input and output are given. By utilizing some inequality techniques, several criteria are presented, ensuring the passivity of the complex dynamical network under the designed adaptive law.... View full abstract»

• ### Stability of Markovian Jump Generalized Neural Networks With Interval Time-Varying Delays

Publication Year: 2017, Page(s):1840 - 1850
Cited by:  Papers (1)
| | PDF (978 KB) | HTML

This paper examines the problem of asymptotic stability for Markovian jump generalized neural networks with interval time-varying delays. Markovian jump parameters are modeled as a continuous-time and finite-state Markov chain. By constructing a suitable Lyapunov-Krasovskii functional (LKF) and using the linear matrix inequality (LMI) formulation, new delay-dependent stability conditions are estab... View full abstract»

• ### Shrinkage Degree in $L_{2}$ -Rescale Boosting for Regression

Publication Year: 2017, Page(s):1851 - 1864
| | PDF (2590 KB) | HTML

L2-rescale boosting (L2-RBoosting) is a variant of L2-Boosting, which can essentially improve the generalization performance of L2-Boosting. The key feature of L2-RBoosting lies in introducing a shrinkage degree to rescale the ensemble estimate in each iteration. Thus, the shrinkage degree determines the performance of L2-RBoosting.... View full abstract»

• ### Extending the Peak Bandwidth of Parameters for Softmax Selection in Reinforcement Learning

Publication Year: 2017, Page(s):1865 - 1877
| | PDF (2102 KB) | HTML

Softmax selection is one of the most popular methods for action selection in reinforcement learning. Although various recently proposed methods may be more effective with full parameter tuning, implementing a complicated method that requires the tuning of many parameters can be difficult. Thus, softmax selection is still worth revisiting, considering the cost savings of its implementation and tuni... View full abstract»

• ### Exponential Synchronization of Memristive Neural Networks With Delays: Interval Matrix Method

Publication Year: 2017, Page(s):1878 - 1888
Cited by:  Papers (11)
| | PDF (1420 KB) | HTML

This paper considers the global exponential synchronization of drive-response memristive neural networks (MNNs) with heterogeneous time-varying delays. Because the parameters of MNNs are state-dependent, the MNNs may exhibit unexpected parameter mismatch when different initial conditions are chosen. Therefore, traditional robust control scheme cannot guarantee the synchronization of MNNs. Under th... View full abstract»

• ### A Memristive Multilayer Cellular Neural Network With Applications to Image Processing

Publication Year: 2017, Page(s):1889 - 1901
| | PDF (2838 KB) | HTML

The memristor has been extensively studied in electrical engineering and biological sciences as a means to compactly implement the synaptic function in neural networks. The cellular neural network (CNN) is one of the most implementable artificial neural network models and capable of massively parallel analog processing. In this paper, a novel memristive multilayer CNN (Mm-CNN) model is presented a... View full abstract»

• ### An Adaptive NN-Based Approach for Fault-Tolerant Control of Nonlinear Time-Varying Delay Systems With Unmodeled Dynamics

Publication Year: 2017, Page(s):1902 - 1913
Cited by:  Papers (9)
| | PDF (1357 KB) | HTML

This paper presents an adaptive neural network (NN)-based fault-tolerant control approach for the compensation of actuator failures in nonlinear systems with time-varying delay. The novelty of this paper lies in the fact that both the lock in place and loss of effectiveness faults, unmodeled dynamics, and dynamic disturbances are catered for simultaneously. Furthermore, this is achieved by the ada... View full abstract»

• ### Lazy-Learning-Based Data-Driven Model-Free Adaptive Predictive Control for a Class of Discrete-Time Nonlinear Systems

Publication Year: 2017, Page(s):1914 - 1928
Cited by:  Papers (1)
| | PDF (2349 KB) | HTML

In this paper, a novel data-driven model-free adaptive predictive control method based on lazy learning technique is proposed for a class of discrete-time single-input and single-output nonlinear systems. The feature of the proposed approach is that the controller is designed only using the input-output (I/O) measurement data of the system by means of a novel dynamic linearization technique with a... View full abstract»

• ### Hamiltonian-Driven Adaptive Dynamic Programming for Continuous Nonlinear Dynamical Systems

Publication Year: 2017, Page(s):1929 - 1940
Cited by:  Papers (1)
| | PDF (2017 KB) | HTML

This paper presents a Hamiltonian-driven framework of adaptive dynamic programming (ADP) for continuous time nonlinear systems, which consists of evaluation of an admissible control, comparison between two different admissible policies with respect to the corresponding the performance function, and the performance improvement of an admissible control. It is showed that the Hamiltonian can serve as... View full abstract»

• ### Event-Triggered Adaptive Dynamic Programming for Continuous-Time Systems With Control Constraints

Publication Year: 2017, Page(s):1941 - 1952
Cited by:  Papers (1)
| | PDF (2478 KB) | HTML

In this paper, an event-triggered near optimal control structure is developed for nonlinear continuous-time systems with control constraints. Due to the saturating actuators, a nonquadratic cost function is introduced and the Hamilton-Jacobi-Bellman (HJB) equation for constrained nonlinear continuous-time systems is formulated. In order to solve the HJB equation, an actor-critic framework is prese... View full abstract»

• ### Dynamical Analysis of the Hindmarsh–Rose Neuron With Time Delays

Publication Year: 2017, Page(s):1953 - 1958
| | PDF (4451 KB) | HTML

This brief is mainly concerned with a series of dynamical analyses of the Hindmarsh-Rose (HR) neuron with state-dependent time delays. The dynamical analyses focus on stability, Hopf bifurcation, as well as chaos and chaos control. Through the stability and bifurcation analysis, we determine that increasing the external current causes the excitable HR neuron to exhibit periodic or chaotic bursting... View full abstract»

• ### Adaptation to New Microphones Using Artificial Neural Networks With Trainable Activation Functions

Publication Year: 2017, Page(s):1959 - 1965
| | PDF (532 KB) | HTML

Model adaptation is a key technique that enables a modern automatic speech recognition (ASR) system to adjust its parameters, using a small amount of enrolment data, to the nuances in the speech spectrum due to microphone mismatch in the training and test data. In this brief, we investigate four different adaptation schemes for connectionist (also known as hybrid) ASR systems that learn microphone... View full abstract»

• ### Design of Probabilistic Boolean Networks Based on Network Structure and Steady-State Probabilities

Publication Year: 2017, Page(s):1966 - 1971
| | PDF (250 KB) | HTML

In this brief, we consider the problem of finding a probabilistic Boolean network (PBN) based on a network structure and desired steady-state properties. In systems biology and synthetic biology, such problems are important as an inverse problem. Using a matrix-based representation of PBNs, a solution method for this problem is proposed. The problem of finding a BN has been studied so far. In the ... View full abstract»

• ### Call For Papers: IEEE World Congress on Computational Intelligence

Publication Year: 2017, Page(s): 1972
| PDF (1346 KB)
• ### IEEE Computational Intelligence Society Information

Publication Year: 2017, Page(s): C3
| PDF (91 KB)
• ### IEEE Transactions on Neural Networks information for authors

Publication Year: 2017, Page(s): C4
| PDF (98 KB)

## 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