IEEE Transactions on Neural Networks and Learning Systems

Filter Results

Displaying Results 1 - 24 of 24

Publication Year: 2015, Page(s): C1
| PDF (121 KB)
• IEEE Transactions on Neural Networks and Learning Systems publication information

Publication Year: 2015, Page(s): C2
| PDF (137 KB)
• On Recursive Edit Distance Kernels With Application to Time Series Classification

Publication Year: 2015, Page(s):1121 - 1133
Cited by:  Papers (9)
| | PDF (2094 KB) | HTML

This paper proposes some extensions to the work on kernels dedicated to string or time series global alignment based on the aggregation of scores obtained by local alignments. The extensions that we propose allow us to construct, from classical recursive definition of elastic distances, recursive edit distance (or time-warp) kernels that are positive definite if some sufficient conditions are sati... View full abstract»

• Generalized Multiple Kernel Learning With Data-Dependent Priors

Publication Year: 2015, Page(s):1134 - 1148
Cited by:  Papers (5)
| | PDF (2923 KB) | HTML

Multiple kernel learning (MKL) and classifier ensemble are two mainstream methods for solving learning problems in which some sets of features/views are more informative than others, or the features/views within a given set are inconsistent. In this paper, we first present a novel probabilistic interpretation of MKL such that maximum entropy discrimination with a noninformative prior over multiple... View full abstract»

• A Two-Layer Recurrent Neural Network for Nonsmooth Convex Optimization Problems

Publication Year: 2015, Page(s):1149 - 1160
Cited by:  Papers (16)
| | PDF (1014 KB) | HTML

In this paper, a two-layer recurrent neural network is proposed to solve the nonsmooth convex optimization problem subject to convex inequality and linear equality constraints. Compared with existing neural network models, the proposed neural network has a low model complexity and avoids penalty parameters. It is proved that from any initial point, the state of the proposed neural network reaches ... View full abstract»

• Generalized Single-Hidden Layer Feedforward Networks for Regression Problems

Publication Year: 2015, Page(s):1161 - 1176
Cited by:  Papers (55)
| | PDF (5182 KB) | HTML

In this paper, traditional single-hidden layer feedforward network (SLFN) is extended to novel generalized SLFN (GSLFN) by employing polynomial functions of inputs as output weights connecting randomly generated hidden units with corresponding output nodes. The significant contributions of this paper are as follows: 1) a primal GSLFN (P-GSLFN) is implemented using randomly generated hidden nodes a... View full abstract»

• Optimization of a Multilayer Neural Network by Using Minimal Redundancy Maximal Relevance-Partial Mutual Information Clustering With Least Square Regression

Publication Year: 2015, Page(s):1177 - 1187
Cited by:  Papers (6)
| | PDF (2382 KB) | HTML

In this paper, an optimized multilayer feed-forward network (MLFN) is developed to construct a soft sensor for controlling naphtha dry point. To overcome the two main flaws in the structure and weight of MLFNs, which are trained by a back-propagation learning algorithm, minimal redundancy maximal relevance-partial mutual information clustering (mPMIc) integrated with least square regression (LSR) ... View full abstract»

• Output-Feedback Adaptive Neural Control for Stochastic Nonlinear Time-Varying Delay Systems With Unknown Control Directions

Publication Year: 2015, Page(s):1188 - 1201
Cited by:  Papers (48)
| | PDF (1956 KB) | HTML

This paper presents an adaptive output-feedback neural network (NN) control scheme for a class of stochastic nonlinear time-varying delay systems with unknown control directions. To make the controller design feasible, the unknown control coefficients are grouped together and the original system is transformed into a new system using a linear state transformation technique. Then, the Nussbaum func... View full abstract»

• Memristor-Based Cellular Nonlinear/Neural Network: Design, Analysis, and Applications

Publication Year: 2015, Page(s):1202 - 1213
Cited by:  Papers (54)
| | PDF (2764 KB) | HTML

Cellular nonlinear/neural network (CNN) has been recognized as a powerful massively parallel architecture capable of solving complex engineering problems by performing trillions of analog operations per second. The memristor was theoretically predicted in the late seventies, but it garnered nascent research interest due to the recent much-acclaimed discovery of nanocrossbar memories by engineers a... View full abstract»

• Synchronization of Chaotic Lur’e Systems With Time Delays Using Sampled-Data Control

Publication Year: 2015, Page(s):1214 - 1221
Cited by:  Papers (35)
| | PDF (1253 KB) | HTML

The asymptotical synchronization problem is investigated for two identical chaotic Lur'e systems with time delays. The sampled-data control method is employed for the system design. A new synchronization condition is proposed in the form of linear matrix inequalities. The error system is shown to be asymptotically stable with the constructed new piecewise differentiable Lyapunov-Krasovskii functio... View full abstract»

• Kernel Reconstruction ICA for Sparse Representation

Publication Year: 2015, Page(s):1222 - 1232
Cited by:  Papers (4)
| | PDF (3203 KB) | HTML

Independent component analysis with soft reconstruction cost (RICA) has been recently proposed to linearly learn sparse representation with an overcomplete basis, and this technique exhibits promising performance even on unwhitened data. However, linear RICA may not be effective for the majority of real-world data because nonlinearly separable data structure pervasively exists in original data spa... View full abstract»

• Partially Shared Latent Factor Learning With Multiview Data

Publication Year: 2015, Page(s):1233 - 1246
Cited by:  Papers (18)
| | PDF (2872 KB) | HTML

Multiview representations reveal the fundamental attributes of the studied instances from different perspectives. Some common perspectives are reviewed by multiple views simultaneously, while some specific ones are reflected by individual views. That is, there are two kinds of properties embedded in the multiview data: 1) consistency and 2) complementarity. Different from most multiview learning a... View full abstract»

• Learning From Adaptive Neural Dynamic Surface Control of Strict-Feedback Systems

Publication Year: 2015, Page(s):1247 - 1259
Cited by:  Papers (43)
| | PDF (2502 KB) | HTML

Learning plays an essential role in autonomous control systems. However, how to achieve learning in the nonstationary environment for nonlinear systems is a challenging problem. In this paper, we present learning method for a class of nth-order strict-feedback systems by adaptive dynamic surface control (DSC) technology, which achieves the human-like ability of learning by doing and doing with lea... View full abstract»

• Complex Support Vector Machines for Regression and Quaternary Classification

Publication Year: 2015, Page(s):1260 - 1274
Cited by:  Papers (7)
| | PDF (3032 KB) | HTML

The paper presents a new framework for complex support vector regression (SVR) as well as Support Vector Machines (SVM) for quaternary classification. The method exploits the notion of widely linear estimation to model the input-out relation for complex-valued data and considers two cases: 1) the complex data are split into their real and imaginary parts and a typical real kernel is employed to ma... View full abstract»

• Blind Image Quality Assessment via Deep Learning

Publication Year: 2015, Page(s):1275 - 1286
Cited by:  Papers (72)
| | PDF (5674 KB) | HTML

This paper investigates how to blindly evaluate the visual quality of an image by learning rules from linguistic descriptions. Extensive psychological evidence shows that humans prefer to conduct evaluations qualitatively rather than numerically. The qualitative evaluations are then converted into the numerical scores to fairly benchmark objective image quality assessment (IQA) metrics. Recently, ... View full abstract»

• Discriminative Embedded Clustering: A Framework for Grouping High-Dimensional Data

Publication Year: 2015, Page(s):1287 - 1299
Cited by:  Papers (15)
| | PDF (2157 KB) | HTML

In many real applications of machine learning and data mining, we are often confronted with high-dimensional data. How to cluster high-dimensional data is still a challenging problem due to the curse of dimensionality. In this paper, we try to address this problem using joint dimensionality reduction and clustering. Different from traditional approaches that conduct dimensionality reduction and cl... View full abstract»

• Global Exponential Synchronization of Multiple Memristive Neural Networks With Time Delay via Nonlinear Coupling

Publication Year: 2015, Page(s):1300 - 1311
Cited by:  Papers (39)
| | PDF (4252 KB) | HTML

This paper presents theoretical results on the global exponential synchronization of multiple memristive neural networks with time delays. A novel coupling scheme is introduced, in a general topological structure described by a directed or undirected graph, with a linear diffusive term and discontinuous sign term. Several criteria are derived based on the Lyapunov stability theory to ascertain the... View full abstract»

• A Direct Self-Constructing Neural Controller Design for a Class of Nonlinear Systems

Publication Year: 2015, Page(s):1312 - 1322
Cited by:  Papers (5)
| | PDF (3568 KB) | HTML

This paper is concerned with the problem of adaptive neural control for a class of uncertain or ill-defined nonaffine nonlinear systems. Using a self-organizing radial basis function neural network (RBFNN), a direct self-constructing neural controller (DSNC) is designed so that unknown nonlinearities can be approximated and the closed-loop system is stable. The key features of the proposed DSNC de... View full abstract»

• Error Bounds of Adaptive Dynamic Programming Algorithms for Solving Undiscounted Optimal Control Problems

Publication Year: 2015, Page(s):1323 - 1334
Cited by:  Papers (25)
| | PDF (1114 KB) | HTML

In this paper, we establish error bounds of adaptive dynamic programming algorithms for solving undiscounted infinite-horizon optimal control problems of discrete-time deterministic nonlinear systems. We consider approximation errors in the update equations of both value function and control policy. We utilize a new assumption instead of the contraction assumption in discounted optimal control pro... View full abstract»

• Further Result on Guaranteed$H_\infty$Performance State Estimation of Delayed Static Neural Networks

Publication Year: 2015, Page(s):1335 - 1341
Cited by:  Papers (36)
| | PDF (490 KB) | HTML

This brief considers the guaranteed H∞performance state estimation problem of delayed static neural networks. An Arcak-type state estimator, which is more general than the widely adopted Luenberger-type one, is chosen to tackle this issue. A delay-dependent criterion is derived under which the estimation error system is globally asymptotically stable with a prescribed H∞perfo... View full abstract»

• Randomized Gradient-Free Method for Multiagent Optimization Over Time-Varying Networks

Publication Year: 2015, Page(s):1342 - 1347
Cited by:  Papers (22)
| | PDF (389 KB) | HTML

In this brief, we consider the multiagent optimization over a network where multiple agents try to minimize a sum of nonsmooth but Lipschitz continuous functions, subject to a convex state constraint set. The underlying network topology is modeled as time varying. We propose a randomized derivative-free method, where in each update, the random gradient-free oracles are utilized instead of the subg... View full abstract»

• IEEE World Congress on Computational Intelligence

Publication Year: 2015, Page(s): 1348
| PDF (1587 KB)
• IEEE Computational Intelligence Society Information

Publication Year: 2015, Page(s): C3
| PDF (116 KB)
• IEEE Transactions on Neural Networks information for authors

Publication Year: 2015, Page(s): C4
| PDF (46 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