IEEE Transactions on Neural Networks and Learning Systems

Filter Results

Displaying Results 1 - 25 of 34

Publication Year: 2016, Page(s):C1 - 2457
| PDF (124 KB)
• IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS publication information

Publication Year: 2016, Page(s): C2
| PDF (199 KB)
• Training Radial Basis Function Neural Networks for Classification via Class-Specific Clustering

Publication Year: 2016, Page(s):2458 - 2471
| | PDF (4700 KB) | HTML

In training radial basis function neural networks (RBFNNs), the locations of Gaussian neurons are commonly determined by clustering. Training inputs can be clustered on a fully unsupervised manner (input clustering), or some supervision can be introduced, for example, by concatenating the input vectors with weighted output vectors (input-output clustering). In this paper, we propose to apply clust... View full abstract»

• Similarity Constraints-Based Structured Output Regression Machine: An Approach to Image Super-Resolution

Publication Year: 2016, Page(s):2472 - 2485
Cited by:  Papers (7)
| | PDF (5985 KB) | HTML

For regression-based single-image super-resolution (SR) problem, the key is to establish a mapping relation between high-resolution (HR) and low-resolution (LR) image patches for obtaining a visually pleasing quality image. Most existing approaches typically solve it by dividing the model into several single-output regression problems, which obviously ignores the circumstance that a pixel within a... View full abstract»

• Deep Learning of Part-Based Representation of Data Using Sparse Autoencoders With Nonnegativity Constraints

Publication Year: 2016, Page(s):2486 - 2498
Cited by:  Papers (18)
| | PDF (5185 KB) | HTML

We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (nonnegativity-constrained autoencoder), that learns features that show part-based representation of data. The learning algorithm is based on constraining negative weights. The performance of the algorithm is assessed based on decomposing data into parts and its prediction performance is tested ... View full abstract»

• A Unified Framework for Representation-Based Subspace Clustering of Out-of-Sample and Large-Scale Data

Publication Year: 2016, Page(s):2499 - 2512
Cited by:  Papers (22)
| | PDF (3331 KB) | HTML

Under the framework of spectral clustering, the key of subspace clustering is building a similarity graph, which describes the neighborhood relations among data points. Some recent works build the graph using sparse, low-rank, and ℓ2-norm-based representation, and have achieved the state-of-the-art performance. However, these methods have suffered from the following two limitatio... View full abstract»

• A Theoretical Foundation of Goal Representation Heuristic Dynamic Programming

Publication Year: 2016, Page(s):2513 - 2525
Cited by:  Papers (12)
| | PDF (2499 KB) | HTML

Goal representation heuristic dynamic programming (GrHDP) control design has been developed in recent years. The control performance of this design has been demonstrated in several case studies, and also showed applicable to industrial-scale complex control problems. In this paper, we develop the theoretical analysis for the GrHDP design under certain conditions. It has been shown that the interna... View full abstract»

• Sequential Compact Code Learning for Unsupervised Image Hashing

Publication Year: 2016, Page(s):2526 - 2536
Cited by:  Papers (14)
| | PDF (3409 KB) | HTML

Effective hashing for large-scale image databases is a popular research area, attracting much attention in computer vision and visual information retrieval. Several recent methods attempt to learn either graph embedding or semantic coding for fast and accurate applications. In this paper, a novel unsupervised framework, termed evolutionary compact embedding (ECE), is introduced to automatically le... View full abstract»

• Organizing Books and Authors by Multilayer SOM

Publication Year: 2016, Page(s):2537 - 2550
Cited by:  Papers (4)
| | PDF (4482 KB) | HTML

This paper introduces a new framework for the organization of electronic books (e-books) and their corresponding authors using a multilayer self-organizing map (MLSOM). An author is modeled by a rich tree-structured representation, and an MLSOM-based system is used as an efficient solution to the organizational problem of structured data. The tree-structured representation formulates author featur... View full abstract»

• Generalized Higher Order Orthogonal Iteration for Tensor Learning and Decomposition

Publication Year: 2016, Page(s):2551 - 2563
| | PDF (2530 KB) | HTML

Low-rank tensor completion (LRTC) has successfully been applied to a wide range of real-world problems. Despite the broad, successful applications, existing LRTC methods may become very slow or even not applicable for large-scale problems. To address this issue, a novel core tensor trace-norm minimization (CTNM) method is proposed for simultaneous tensor learning and decomposition, and has a much ... View full abstract»

• Dynamic Learning From Neural Control for Strict-Feedback Systems With Guaranteed Predefined Performance

Publication Year: 2016, Page(s):2564 - 2576
Cited by:  Papers (19)
| | PDF (2567 KB) | HTML

This paper focuses on dynamic learning from neural control for a class of nonlinear strict-feedback systems with predefined tracking performance attributes. To reduce the number of neural network (NN) approximators used and make the convergence of neural weights verified easily, state variables are introduced to transform the state-feedback control of the original strict-feedback systems into the ... View full abstract»

• Online Solution of Two-Player Zero-Sum Games for Continuous-Time Nonlinear Systems With Completely Unknown Dynamics

Publication Year: 2016, Page(s):2577 - 2587
Cited by:  Papers (2)
| | PDF (942 KB) | HTML

Regarding two-player zero-sum games of continuous-time nonlinear systems with completely unknown dynamics, this paper presents an online adaptive algorithm for learning the Nash equilibrium solution, i.e., the optimal policy pair. First, for known systems, the simultaneous policy updating algorithm (SPUA) is reviewed. A new analytical method to prove the convergence is presented. Then, based on th... View full abstract»

• Shortcomings/Limitations of Blockwise Granger Causality and Advances of Blockwise New Causality

Publication Year: 2016, Page(s):2588 - 2601
Cited by:  Papers (1)
| | PDF (2476 KB) | HTML

Multivariate blockwise Granger causality (BGC) is used to reflect causal interactions among blocks of multivariate time series. In particular, spectral BGC and conditional spectral BGC are used to disclose blockwise causal flow among different brain areas in various frequencies. In this paper, we demonstrate that: 1) BGC in time domain may not necessarily disclose true causality and 2) due to the ... View full abstract»

• Semisupervised Multiclass Classification Problems With Scarcity of Labeled Data: A Theoretical Study

Publication Year: 2016, Page(s):2602 - 2614
| | PDF (1649 KB) | HTML

In recent years, the performance of semisupervised learning (SSL) has been theoretically investigated. However, most of this theoretical development has focused on binary classification problems. In this paper, we take it a step further by extending the work of Castelli and Cover to the multiclass paradigm. In particular, we consider the key problem in SSL of classifying an unseen instance x into ... View full abstract»

• Integration-Enhanced Zhang Neural Network for Real-Time-Varying Matrix Inversion in the Presence of Various Kinds of Noises

Publication Year: 2016, Page(s):2615 - 2627
Cited by:  Papers (15)
| | PDF (2831 KB) | HTML

Matrix inversion often arises in the fields of science and engineering. Many models for matrix inversion usually assume that the solving process is free of noises or that the denoising has been conducted before the computation. However, time is precious for the real-time-varying matrix inversion in practice, and any preprocessing for noise reduction may consume extra time, possibly violating the r... View full abstract»

• Scalable Linear Visual Feature Learning via Online Parallel Nonnegative Matrix Factorization

Publication Year: 2016, Page(s):2628 - 2642
Cited by:  Papers (1)
| | PDF (3425 KB) | HTML

Visual feature learning, which aims to construct an effective feature representation for visual data, has a wide range of applications in computer vision. It is often posed as a problem of nonnegative matrix factorization (NMF), which constructs a linear representation for the data. Although NMF is typically parallelized for efficiency, traditional parallelization methods suffer from either an exp... View full abstract»

• Information Theoretic Subspace Clustering

Publication Year: 2016, Page(s):2643 - 2655
Cited by:  Papers (2)
| | PDF (2224 KB) | HTML

This paper addresses the problem of grouping the data points sampled from a union of multiple subspaces in the presence of outliers. Information theoretic objective functions are proposed to combine structured low-rank representations (LRRs) to capture the global structure of data and information theoretic measures to handle outliers. In theoretical part, we point out that group sparsity-induced m... View full abstract»

• Adaptive Scaling of Cluster Boundaries for Large-Scale Social Media Data Clustering

Publication Year: 2016, Page(s):2656 - 2669
Cited by:  Papers (3)
| | PDF (3053 KB) | HTML

The large scale and complex nature of social media data raises the need to scale clustering techniques to big data and make them capable of automatically identifying data clusters with few empirical settings. In this paper, we present our investigation and three algorithms based on the fuzzy adaptive resonance theory (Fuzzy ART) that have linear computational complexity, use a single parameter, i.... View full abstract»

• K-MEAP: Multiple Exemplars Affinity Propagation With Specified $K$ Clusters

Publication Year: 2016, Page(s):2670 - 2682
| | PDF (5576 KB) | HTML

Recently, an attractive clustering approach named multiexemplar affinity propagation (MEAP) has been proposed as an extension to the single exemplar-based AP. MEAP is able to automatically identify multiple exemplars for each cluster associated with a superexemplar. However, if the cluster number is a prior knowledge and can be specified by the user, MEAP is unable to make use of such knowledge di... View full abstract»

• Landslide Displacement Prediction With Uncertainty Based on Neural Networks With Random Hidden Weights

Publication Year: 2016, Page(s):2683 - 2695
Cited by:  Papers (4)
| | PDF (4298 KB) | HTML

In this paper, we propose a new approach to establish a landslide displacement forecasting model based on artificial neural networks (ANNs) with random hidden weights. To quantify the uncertainty associated with the predictions, a framework for probabilistic forecasting of landslide displacement is developed. The aim of this paper is to construct prediction intervals (PIs) instead of deterministic... View full abstract»

• Impulsive Synchronization of Reaction–Diffusion Neural Networks With Mixed Delays and Its Application to Image Encryption

Publication Year: 2016, Page(s):2696 - 2710
Cited by:  Papers (19)
| | PDF (7774 KB) | HTML

This paper presents a new impulsive synchronization criterion of two identical reaction-diffusion neural networks with discrete and unbounded distributed delays. The new criterion is established by applying an impulse-time-dependent Lyapunov functional combined with the use of a new type of integral inequality for treating the reaction-diffusion terms. The impulse-time-dependent feature of the pro... View full abstract»

• MSDLSR: Margin Scalable Discriminative Least Squares Regression for Multicategory Classification

Publication Year: 2016, Page(s):2711 - 2717
Cited by:  Papers (1)
| | PDF (1169 KB) | HTML

In this brief, we propose a new margin scalable discriminative least squares regression (MSDLSR) model for multicategory classification. The main motivation behind the MSDLSR is to explicitly control the margin of DLSR model. We first prove that the DLSR is a relaxation of the traditional L2-support vector machine. Based on this fact, we further provide a theorem on the margin of DLSR. ... View full abstract»

• Data-Driven Modeling for UGI Gasification Processes via an Enhanced Genetic BP Neural Network With Link Switches

Publication Year: 2016, Page(s):2718 - 2729
Cited by:  Papers (3)
| | PDF (2129 KB) | HTML

In this brief, an enhanced genetic back-propagation neural network with link switches (EGA-BPNN-LS) is proposed to address a data-driven modeling problem for gasification processes inside United Gas Improvement (UGI) gasifiers. The online-measured temperature of crude gas produced during the gasification processes plays a dominant role in the syngas industry; however, it is difficult to model temp... View full abstract»

Publication Year: 2016, Page(s):2730 - 2735
Cited by:  Papers (3)
| | PDF (1679 KB) | HTML

Complex gradient methods have been widely used in learning theory, and typically aim to optimize real-valued functions of complex variables. The stepsize of complex gradient learning methods (CGLMs) is a positive number, and little is known about how a complex stepsize would affect the learning process. To this end, we undertake a comprehensive analysis of CGLMs with a complex stepsize, including ... View full abstract»

• Enhanced Logical Stochastic Resonance in Synthetic Genetic Networks

Publication Year: 2016, Page(s):2736 - 2739
Cited by:  Papers (1)
| | PDF (2193 KB) | HTML

In this brief, the concept of logical stochastic resonance is applied to implement the Set-Reset latch in a synthetic gene network derived from a bacteriophage λ. Clear Set-Reset latch operation is obtained when the network is only subjected to periodic forcing. The correct probability of obtaining the desired logic operation first increases to unity and then decreases as the amplitude of t... 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