# IEEE Transactions on Neural Networks and Learning Systems

## Filter Results

Displaying Results 1 - 24 of 24

Publication Year: 2013, Page(s): C1
| PDF (142 KB)
• ### IEEE Transactions on Neural Networks and Learning Systems - publication information

Publication Year: 2013, Page(s): C2
| PDF (139 KB)
• ### Study of the Convergence Behavior of the Complex Kernel Least Mean Square Algorithm

Publication Year: 2013, Page(s):1349 - 1363
Cited by:  Papers (7)
| | PDF (768 KB) | HTML

The complex kernel least mean square (CKLMS) algorithm is recently derived and allows for online kernel adaptive learning for complex data. Kernel adaptive methods can be used in finding solutions for neural network and machine learning applications. The derivation of CKLMS involved the development of a modified Wirtinger calculus for Hilbert spaces to obtain the cost function gradient. We analyze... View full abstract»

• ### Transductive Face Sketch-Photo Synthesis

Publication Year: 2013, Page(s):1364 - 1376
Cited by:  Papers (45)
| | PDF (2307 KB) | HTML

Face sketch-photo synthesis plays a critical role in many applications, such as law enforcement and digital entertainment. Recently, many face sketch-photo synthesis methods have been proposed under the framework of inductive learning, and these have obtained promising performance. However, these inductive learning-based face sketch-photo synthesis methods may result in high losses for test sample... View full abstract»

• ### Learning Sparse Kernel Classifiers for Multi-Instance Classification

Publication Year: 2013, Page(s):1377 - 1389
Cited by:  Papers (5)
| | PDF (1789 KB) | HTML

We propose a direct approach to learning sparse kernel classifiers for multi-instance (MI) classification to improve efficiency while maintaining predictive accuracy. The proposed method builds on a convex formulation for MI classification by considering the average score of individual instances for bag-level prediction. In contrast, existing formulations used the maximum score of individual insta... View full abstract»

• ### FPGA-Based Distributed Computing Microarchitecture for Complex Physical Dynamics Investigation

Publication Year: 2013, Page(s):1390 - 1399
Cited by:  Papers (3)
| | PDF (1393 KB) | HTML

In this paper, we present a distributed computing system, called DCMARK, aimed at solving partial differential equations at the basis of many investigation fields, such as solid state physics, nuclear physics, and plasma physics. This distributed architecture is based on the cellular neural network paradigm, which allows us to divide the differential equation system solving into many parallel inte... View full abstract»

• ### Neural-Adaptive Control of Single-Master–Multiple-Slaves Teleoperation for Coordinated Multiple Mobile Manipulators With Time-Varying Communication Delays and Input Uncertainties

Publication Year: 2013, Page(s):1400 - 1413
Cited by:  Papers (67)
| | PDF (1459 KB) | HTML

In this paper, adaptive neural network control is investigated for single-master-multiple-slaves teleoperation in consideration of time delays and input dead-zone uncertainties for multiple mobile manipulators carrying a common object in a cooperative manner. Firstly, concise dynamics of teleoperation systems consisting of a single master robot, multiple coordinated slave robots, and the object ar... View full abstract»

• ### Cube Kohonen Self-Organizing Map (CKSOM) Model With New Equations in Organizing Unstructured Data

Publication Year: 2013, Page(s):1414 - 1424
Cited by:  Papers (2)
| | PDF (1944 KB) | HTML

Surface reconstruction by using 3-D data is used to represent the surface of an object and perform important tasks. The type of data used is important and can be described as either structured or unstructured. For unstructured data, there is no connectivity information between data points. As a result, incorrect shapes will be obtained during the imaging process. Therefore, the data should be reor... View full abstract»

• ### Real-Time Model Predictive Control Using a Self-Organizing Neural Network

Publication Year: 2013, Page(s):1425 - 1436
Cited by:  Papers (13)
| | PDF (619 KB) | HTML

In this paper, a real-time model predictive control (RT-MPC) based on self-organizing radial basis function neural network (SORBFNN) is proposed for nonlinear systems. This RT-MPC has its simplicity in parallelism to model predictive control design and efficiency to deal with computational complexity. First, a SORBFNN with concurrent structure and parameter learning is developed as the predictive ... View full abstract»

• ### Memory Models of Adaptive Behavior

Publication Year: 2013, Page(s):1437 - 1448
Cited by:  Papers (13)
| | PDF (1397 KB) | HTML

Adaptive response to varying environment is a common feature of biological organisms. Reproducing such features in electronic systems and circuits is of great importance for a variety of applications. We consider memory models inspired by an intriguing ability of slime molds to both memorize the period of temperature and humidity variations and anticipate the next variations to come, when appropri... View full abstract»

• ### Model of an Excitatory Synapse Based on Stochastic Processes

Publication Year: 2013, Page(s):1449 - 1458
Cited by:  Papers (1)
| | PDF (754 KB) | HTML

We present a mathematical model of a biological synapse based on stochastic processes to establish the temporal behavior of the postsynaptic potential following a quantal synaptic transmission. This potential form is the basis of the neural code. We suppose that the release of neurotransmitters in the synaptic cleft follows a Poisson process, and that they diffuse according to integrated Ornstein-... View full abstract»

• ### Combined Convex Technique on Delay-Dependent Stability for Delayed Neural Networks

Publication Year: 2013, Page(s):1459 - 1466
Cited by:  Papers (41)
| | PDF (244 KB) | HTML

In this brief, by employing an improved Lyapunov-Krasovskii functional (LKF) and combining the reciprocal convex technique with the convex one, a new sufficient condition is derived to guarantee a class of delayed neural networks (DNNs) to be globally asymptotically stable. Since some previously ignored terms can be considered during the estimation of the derivative of LKF, a less conservative sta... View full abstract»

• ### Low-Temperature Fabrication of Spiking Soma Circuits Using Nanocrystalline-Silicon TFTs

Publication Year: 2013, Page(s):1466 - 1472
Cited by:  Papers (2)
| | PDF (785 KB) | HTML

Spiking neuron circuits consisting of ambipolar nanocrystalline-silicon (nc-Si) thin-film transistors (TFTs) have been fabricated using low temperature processing conditions (maximum of 250 °C) that allow the use of flexible substrates. These circuits display behaviors commonly observed in biological neurons such as millisecond spike duration, nonlinear frequency-current relation... View full abstract»

• ### Effect of Input Noise and Output Node Stochastic on Wang's k WTA

Publication Year: 2013, Page(s):1472 - 1478
Cited by:  Papers (2)
| | PDF (317 KB) | HTML

Recently, an analog neural network model, namely Wang's kWTA, was proposed. In this model, the output nodes are defined as the Heaviside function. Subsequently, its finite time convergence property and the exact convergence time are analyzed. However, the discovered characteristics of this model are based on the assumption that there are no physical defects during the operation. In this brief, we ... View full abstract»

• ### Controllability and Observability of Boolean Control Networks With Time-Variant Delays in States

Publication Year: 2013, Page(s):1478 - 1484
Cited by:  Papers (62)
| | PDF (259 KB) | HTML

This brief investigates the controllability and observability of Boolean control networks with (not necessarily bounded) time-variant delays in states. After a brief introduction to converting a Boolean control network to an equivalent discrete-time bilinear dynamical system via the semi-tensor product of matrices, the system is split into a finite number of subsystems (constructed forest) with no... View full abstract»

• ### Quantized Kernel Recursive Least Squares Algorithm

Publication Year: 2013, Page(s):1484 - 1491
Cited by:  Papers (76)
| | PDF (596 KB) | HTML

In a recent paper, we developed a novel quantized kernel least mean square algorithm, in which the input space is quantized (partitioned into smaller regions) and the network size is upper bounded by the quantization codebook size (number of the regions). In this paper, we propose the quantized kernel least squares regression, and derive the optimal solution. By incorporating a simple online vecto... View full abstract»

• ### On the Optimal Class Representation in Linear Discriminant Analysis

Publication Year: 2013, Page(s):1491 - 1497
Cited by:  Papers (19)
| | PDF (1316 KB) | HTML

Linear discriminant analysis (LDA) is a widely used technique for supervised feature extraction and dimensionality reduction. LDA determines an optimal discriminant space for linear data projection based on certain assumptions, e.g., on using normal distributions for each class and employing class representation by the mean class vectors. However, there might be other vectors that can represent ea... View full abstract»

• ### $Linfty$ Analysis and State-Feedback Control of Hopfield Networks

Publication Year: 2013, Page(s):1497 - 1503
Cited by:  Papers (2)
| | PDF (3928 KB) | HTML

A nonsymmetric version of Hopfield networks subject to bounded disturbances is considered. Such networks arise in the context of visuo-motor control loops and may, therefore, be used to mimic their complex behavior. In this brief, we adopt the Lur'e-Postnikov systems approach to analyze the induced L∞ gain of generalized Hopfield networks. A state-feedback control is then designe... View full abstract»

• ### Sequential Blind Identification of Underdetermined Mixtures Using a Novel Deflation Scheme

Publication Year: 2013, Page(s):1503 - 1509
Cited by:  Papers (4)
| | PDF (499 KB) | HTML

In this brief, we consider the problem of blind identification in underdetermined instantaneous mixture cases, where there are more sources than sensors. A new blind identification algorithm, which estimates the mixing matrix in a sequential fashion, is proposed. By using the rank-1 detecting device, blind identification is reformulated as a constrained optimization problem. The identification of ... View full abstract»

• ### 2014 IEEE World Congress on Computational Intelligence

Publication Year: 2013, Page(s): 1510
| PDF (3430 KB)
• ### Do what you do better with What's New @ IEEE Xplore

Publication Year: 2013, Page(s): 1511
| PDF (425 KB)
• ### Together, we are advancing technology

Publication Year: 2013, Page(s): 1512
| PDF (399 KB)
• ### IEEE Computational Intelligence Society Information

Publication Year: 2013, Page(s): C3
| PDF (125 KB)
• ### IEEE Transactions on Neural Networks information for authors

Publication Year: 2013, Page(s): C4
| PDF (127 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