By Topic

# IEEE Transactions on Neural Networks and Learning Systems

## Filter Results

Displaying Results 1 - 18 of 18

Publication Year: 2012, Page(s): C1
| PDF (118 KB)
• ### IEEE Transactions on Neural Networks and Learning Systems publication information

Publication Year: 2012, Page(s): C2
| PDF (40 KB)
• ### Twenty Years of Mixture of Experts

Publication Year: 2012, Page(s):1177 - 1193
Cited by:  Papers (52)
| | PDF (1016 KB) | HTML

In this paper, we provide a comprehensive survey of the mixture of experts (ME). We discuss the fundamental models for regression and classification and also their training with the expectation-maximization algorithm. We follow the discussion with improvements to the ME model and focus particularly on the mixtures of Gaussian process experts. We provide a review of the literature for other trainin... View full abstract»

• ### Constrained Empirical Risk Minimization Framework for Distance Metric Learning

Publication Year: 2012, Page(s):1194 - 1205
Cited by:  Papers (24)
| | PDF (772 KB) | HTML

Distance metric learning (DML) has received increasing attention in recent years. In this paper, we propose a constrained empirical risk minimization framework for DML. This framework enriches the state-of-the-art studies on both theoretic and algorithmic aspects. Theoretically, we comprehensively analyze the generalization by bounding the sample and the approximation errors with respect to the be... View full abstract»

• ### Scale-Invariant Amplitude Spectrum Modulation for Visual Saliency Detection

Publication Year: 2012, Page(s):1206 - 1214
Cited by:  Papers (5)
| | PDF (1584 KB) | HTML

Saliency detection is one of the key issues in simulating visual attention selection. Most attention models adopt the competitive structure to simulate the human visual system. Although these models provide remarkable results and convincing biological plausibility, they are still confronted with many difficulties in practical applications because of their extreme time cost and parameter sensitivit... View full abstract»

• ### Relaxed Fault-Tolerant Hardware Implementation of Neural Networks in the Presence of Multiple Transient Errors

Publication Year: 2012, Page(s):1215 - 1228
Cited by:  Papers (8)
| | PDF (1242 KB) | HTML

Reliability should be identified as the most important challenge in future nano-scale very large scale integration (VLSI) implementation technologies for the development of complex integrated systems. Normally, fault tolerance (FT) in a conventional system is achieved by increasing its redundancy, which also implies higher implementation costs and lower performance that sometimes makes it even inf... View full abstract»

• ### Mapping Dynamic Bayesian Networks to $alpha$-Shapes: Application to Human Faces Identification Across Ages

Publication Year: 2012, Page(s):1229 - 1241
Cited by:  Papers (7)
| | PDF (1117 KB) | HTML

We propose to map a dynamic Bayesian network (DBN) to an ordered family of α -shapes to improve DBNs classification power. This mission is achieved by: 1) embedding a DBN into a topological manifold and 2) applying the α-shape geometric constructor to build hierarchical structures assigned to the DBN. This continuous representation of traditional DBNs as α-shapes allows more i... View full abstract»

• ### Predictive Approach for User Long-Term Needs in Content-Based Image Suggestion

Publication Year: 2012, Page(s):1242 - 1253
Cited by:  Papers (5)
| | PDF (743 KB) | HTML

In this paper, we formalize content-based image suggestion (CBIS) as a Bayesian prediction problem. In CBIS, users provide the rating of images according to both their long-term needs and the contextual situation, such as time and place, to which they belong. Therefore, a CBIS model is defined to fit the distribution of the data in order to predict relevant images for a given user. Generally, CBIS... View full abstract»

• ### SOMKE: Kernel Density Estimation Over Data Streams by Sequences of Self-Organizing Maps

Publication Year: 2012, Page(s):1254 - 1268
Cited by:  Papers (11)
| | PDF (1621 KB) | HTML

In this paper, we propose a novel method SOMKE, for kernel density estimation (KDE) over data streams based on sequences of self-organizing map (SOM). In many stream data mining applications, the traditional KDE methods are infeasible because of the high computational cost, processing time, and memory requirement. To reduce the time and space complexity, we propose a SOM structure in this paper to... View full abstract»

• ### Reinforced Two-Step-Ahead Weight Adjustment Technique for Online Training of Recurrent Neural Networks

Publication Year: 2012, Page(s):1269 - 1278
Cited by:  Papers (18)
| | PDF (606 KB) | HTML

A reliable forecast of future events possesses great value. The main purpose of this paper is to propose an innovative learning technique for reinforcing the accuracy of two-step-ahead (2SA) forecasts. The real-time recurrent learning (RTRL) algorithm for recurrent neural networks (RNNs) can effectively model the dynamics of complex processes and has been used successfully in one-step-ahead foreca... View full abstract»

• ### Spatial Gaussian Process Regression With Mobile Sensor Networks

Publication Year: 2012, Page(s):1279 - 1290
Cited by:  Papers (22)
| | PDF (1386 KB) | HTML

This paper presents a method of using Gaussian process regression to model spatial functions for mobile wireless sensor networks. A distributed Gaussian process regression (DGPR) approach is developed by using a sparse Gaussian process regression method and a compactly supported covariance function. The resultant formulation of the DGPR approach only requires neighbor-to-neighbor communication, wh... View full abstract»

• ### Adaptive Data Embedding Framework for Multiclass Classification

Publication Year: 2012, Page(s):1291 - 1303
Cited by:  Papers (11)
| | PDF (2706 KB) | HTML

The objective of this paper is the design of an engine for the automatic generation of supervised manifold embedding models. It proposes a modular and adaptive data embedding framework for classification, referred to as DEFC, which realizes in different stages including initial data preprocessing, relation feature generation and embedding computation. For the computation of embeddings, the concept... View full abstract»

• ### Study on the Impact of Partition-Induced Dataset Shift on $k$-Fold Cross-Validation

Publication Year: 2012, Page(s):1304 - 1312
Cited by:  Papers (43)
| | PDF (338 KB) | HTML

Cross-validation is a very commonly employed technique used to evaluate classifier performance. However, it can potentially introduce dataset shift, a harmful factor that is often not taken into account and can result in inaccurate performance estimation. This paper analyzes the prevalence and impact of partition-induced covariate shift on different k-fold cross-validation schemes. From the... View full abstract»

• ### Kernel Recursive Least-Squares Tracker for Time-Varying Regression

Publication Year: 2012, Page(s):1313 - 1326
Cited by:  Papers (54)
| | PDF (861 KB) | HTML

In this paper, we introduce a kernel recursive least-squares (KRLS) algorithm that is able to track nonlinear, time-varying relationships in data. To this purpose, we first derive the standard KRLS equations from a Bayesian perspective (including a sensible approach to pruning) and then take advantage of this framework to incorporate forgetting in a consistent way, thus enabling the algorithm to p... View full abstract»

• ### Discrete-Time Neural Inverse Optimal Control for Nonlinear Systems via Passivation

Publication Year: 2012, Page(s):1327 - 1339
Cited by:  Papers (14)
| | PDF (641 KB) | HTML

This paper presents a discrete-time inverse optimal neural controller, which is constituted by combination of two techniques: 1) inverse optimal control to avoid solving the Hamilton-Jacobi-Bellman equation associated with nonlinear system optimal control and 2) on-line neural identification, using a recurrent neural network trained with an extended Kalman filter, in order to build a model of the ... View full abstract»

• ### Equilibria of Perceptrons for Simple Contingency Problems

Publication Year: 2012, Page(s):1340 - 1344
Cited by:  Papers (2)
| | PDF (155 KB) | HTML

The contingency between cues and outcomes is fundamentally important to theories of causal reasoning and to theories of associative learning. Researchers have computed the equilibria of Rescorla-Wagner models for a variety of contingency problems, and have used these equilibria to identify situations in which the Rescorla-Wagner model is consistent, or inconsistent, with normative models of contin... View full abstract»

• ### IEEE Computational Intelligence Society Information

Publication Year: 2012, Page(s): C3
| PDF (38 KB)
• ### IEEE Transactions on Neural Networks information for authors

Publication Year: 2012, Page(s): C4
| PDF (38 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