# IEEE Transactions on Neural Networks

## Filter Results

Displaying Results 1 - 25 of 45

Publication Year: 2007, Page(s):C1 - C4
| PDF (44 KB)
• ### IEEE Transactions on Neural Networks publication information

Publication Year: 2007, Page(s): C2
| PDF (36 KB)
• ### Deterministic Learning and Rapid Dynamical Pattern Recognition

Publication Year: 2007, Page(s):617 - 630
Cited by:  Papers (64)
| | PDF (1433 KB) | HTML

Recognition of temporal/dynamical patterns is among the most difficult pattern recognition tasks. In this paper, based on a recent result on deterministic learning theory, a deterministic framework is proposed for rapid recognition of dynamical patterns. First, it is shown that a time-varying dynamical pattern can be effectively represented in a time-invariant and spatially distributed manner thro... View full abstract»

Publication Year: 2007, Page(s):631 - 647
Cited by:  Papers (57)  |  Patents (5)
| | PDF (1202 KB) | HTML

A continuous-time formulation of an adaptive critic design (ACD) is investigated. Connections to the discrete case are made, where backpropagation through time (BPTT) and real-time recurrent learning (RTRL) are prevalent. Practical benefits are that this framework fits in well with plant descriptions given by differential equations and that any standard integration routine with adaptive step-size ... View full abstract»

• ### Sparse Distributed Memory Using Rank-Order Neural Codes

Publication Year: 2007, Page(s):648 - 659
Cited by:  Papers (6)
| | PDF (1357 KB) | HTML

A variant of a sparse distributed memory (SDM) is shown to have the capability of storing and recalling patterns containing rank-order information. These are patterns where information is encoded not only in the subset of neuron outputs that fire, but also in the order in which that subset fires. This is an interesting companion to several recent works in the neuroscience literature, showing that ... View full abstract»

• ### Stability Analysis and the Stabilization of a Class of Discrete-Time Dynamic Neural Networks

Publication Year: 2007, Page(s):660 - 673
Cited by:  Papers (36)
| | PDF (874 KB) | HTML

This paper deals with problems of stability and the stabilization of discrete-time neural networks. Neural structures under consideration belong to the class of the so-called locally recurrent globally feedforward networks. The single processing unit possesses dynamic behavior. It is realized by introducing into the neuron structure a linear dynamic system in the form of an infinite impulse respon... View full abstract»

• ### Training Winner-Take-All Simultaneous Recurrent Neural Networks

Publication Year: 2007, Page(s):674 - 684
Cited by:  Papers (6)
| | PDF (818 KB) | HTML

The winner-take-all (WTA) network is useful in database management, very large scale integration (VLSI) design, and digital processing. The synthesis procedure of WTA on single-layer fully connected architecture with sigmoid transfer function is still not fully explored. We discuss the use of simultaneous recurrent networks (SRNs) trained by Kalman filter algorithms for the task of finding the max... View full abstract»

• ### Fast Sparse Approximation for Least Squares Support Vector Machine

Publication Year: 2007, Page(s):685 - 697
Cited by:  Papers (89)
| | PDF (752 KB) | HTML

In this paper, we present two fast sparse approximation schemes for least squares support vector machine (LS-SVM), named FSALS-SVM and PFSALS-SVM, to overcome the limitation of LS-SVM that it is not applicable to large data sets and to improve test speed. FSALS-SVM iteratively builds the decision function by adding one basis function from a kernel-based dictionary at one time. The process is termi... View full abstract»

• ### Boolean Factor Analysis by Attractor Neural Network

Publication Year: 2007, Page(s):698 - 707
Cited by:  Papers (33)
| | PDF (894 KB) | HTML

A common problem encountered in disciplines such as statistics, data analysis, signal processing, textual data representation, and neural network research, is finding a suitable representation of the data in the lower dimension space. One of the principles used for this reason is a factor analysis. In this paper, we show that Hebbian learning and a Hopfield-like neural network could be used for a ... View full abstract»

• ### RCMAC Hybrid Control for MIMO Uncertain Nonlinear Systems Using Sliding-Mode Technology

Publication Year: 2007, Page(s):708 - 720
Cited by:  Papers (47)
| | PDF (850 KB) | HTML

A hybrid control system, integrating principal and compensation controllers, is developed for multiple-input-multiple-output (MIMO) uncertain nonlinear systems. This hybrid control system is based on sliding-mode technique and uses a recurrent cerebellar model articulation controller (RCMAC) as an uncertainty observer. The principal controller containing an RCMAC uncertainty observer is the main c... View full abstract»

• ### An Approach to Estimating Product Design Time Based on Fuzzy $nu$-Support Vector Machine

Publication Year: 2007, Page(s):721 - 731
Cited by:  Papers (26)
| | PDF (1291 KB) | HTML

This paper presents a new version of fuzzy support vector machine (FSVM) developed for product design time estimation. As there exist problems of finite samples and uncertain data in the estimation, the input and output variables are described as fuzzy numbers, with the metric on fuzzy number space defined. Then, the fuzzy nu-support vector machine (Fnu-SVM) is proposed on the basis of combining t... View full abstract»

• ### Simultaneous Pattern Classification and Multidomain Association Using Self-Structuring Kernel Memory Networks

Publication Year: 2007, Page(s):732 - 744
Cited by:  Papers (4)
| | PDF (610 KB) | HTML

In this paper, a novel exemplar-based constructive approach using kernels is proposed for simultaneous pattern classification and multidomain pattern association tasks. The kernel networks are constructed on a modular basis by a simple one-shot self-structuring algorithm motivated from the traditional Hebbian principle and then, they act as the flexible memory capable of generalization for the res... View full abstract»

• ### Unsupervised Learning of Gaussian Mixtures Based on Variational Component Splitting

Publication Year: 2007, Page(s):745 - 755
Cited by:  Papers (48)
| | PDF (1240 KB) | HTML

In this paper, we present an incremental method for model selection and learning of Gaussian mixtures based on the recently proposed variational Bayes approach. The method adds components to the mixture using a Bayesian splitting test procedure: a component is split into two components and then variational update equations are applied only to the parameters of the two components. As a result, eith... View full abstract»

• ### A Weighted Voting Model of Associative Memory

Publication Year: 2007, Page(s):756 - 777
Cited by:  Papers (10)  |  Patents (2)
| | PDF (2263 KB) | HTML

This paper presents an analysis of a random access memory (RAM)-based associative memory which uses a weighted voting scheme for information retrieval. This weighted voting memory can operate in heteroassociative or autoassociative mode, can store both real-valued and binary-valued patterns and, unlike memory models, is equipped with a rejection mechanism. A theoretical analysis of the performance... View full abstract»

• ### A Class of Single-Class Minimax Probability Machines for Novelty Detection

Publication Year: 2007, Page(s):778 - 785
Cited by:  Papers (11)
| | PDF (970 KB) | HTML

Single-class minimax probability machines (MPMs) offer robust novelty detection with distribution-free worst case bounds on the probability that a pattern will fall inside the normal region. However, in practice, they are too cautious in labeling patterns as outlying and so have a high false negative rate (FNR). In this paper, we propose a more aggressive version of the single-class MPM that bound... View full abstract»

• ### Explicit Magnification Control of Self-Organizing Maps for “Forbidden” Data

Publication Year: 2007, Page(s):786 - 797
Cited by:  Papers (31)
| | PDF (1964 KB) | HTML

In this paper, we examine the scope of validity of the explicit self-organizing map (SOM) magnification control scheme of Bauer (1996) on data for which the theory does not guarantee success, namely data that are n-dimensional, nges2, and whose components in the different dimensions are not statistically independent. The Bauer algorithm is very attractive for the possibility of faithful representa... View full abstract»

• ### A Spatially Constrained Generative Model and an EM Algorithm for Image Segmentation

Publication Year: 2007, Page(s):798 - 808
Cited by:  Papers (55)
| | PDF (1270 KB) | HTML

In this paper, we present a novel spatially constrained generative model and an expectation-maximization (EM) algorithm for model-based image segmentation. The generative model assumes that the unobserved class labels of neighboring pixels in the image are generated by prior distributions with similar parameters, where similarity is defined by entropic quantities relating to the neighboring priors... View full abstract»

• ### A Minimum-Range Approach to Blind Extraction of Bounded Sources

Publication Year: 2007, Page(s):809 - 822
Cited by:  Papers (17)
| | PDF (1078 KB) | HTML

In spite of the numerous approaches that have been derived for solving the independent component analysis (ICA) problem, it is still interesting to develop new methods when, among other reasons, specific a priori knowledge may help to further improve the separation performances. In this paper, the minimum-range approach to blind extraction of bounded source is investigated. The relationship with o... View full abstract»

• ### Higher-Order-Statistics-Based Radial Basis Function Networks for Signal Enhancement

Publication Year: 2007, Page(s):823 - 832
Cited by:  Papers (21)
| | PDF (857 KB) | HTML

In this paper, a higher-order-statistics (HOS)-based radial basis function (RBF) network for signal enhancement is introduced. In the proposed scheme, higher order cumulants of the reference signal were used as the input of HOS-based RBF. An HOS-based supervised learning algorithm, with mean square error obtained from higher order cumulants of the desired input and the system output as the learnin... View full abstract»

• ### Hierarchical Singleton-Type Recurrent Neural Fuzzy Networks for Noisy Speech Recognition

Publication Year: 2007, Page(s):833 - 843
Cited by:  Papers (34)
| | PDF (1024 KB) | HTML

This paper proposes noisy speech recognition using hierarchical singleton-type recurrent neural fuzzy networks (HSRNFNs). The proposed HSRNFN is a hierarchical connection of two singleton-type recurrent neural fuzzy networks (SRNFNs), where one is used for noise filtering and the other for recognition. The SRNFN is constructed by recurrent fuzzy if-then rules with fuzzy singletons in the consequen... View full abstract»

• ### Iterative Least Squares Functional Networks Classifier

Publication Year: 2007, Page(s):844 - 850
Cited by:  Papers (13)
| | PDF (661 KB) | HTML

This paper proposes unconstrained functional networks as a new classifier to deal with the pattern recognition problems. Both methodology and learning algorithm for this kind of computational intelligence classifier using the iterative least squares optimization criterion are derived. The performance of this new intelligent systems scheme is demonstrated and examined using real-world applications.... View full abstract»

• ### A Hybrid Neurogenetic Approach for Stock Forecasting

Publication Year: 2007, Page(s):851 - 864
Cited by:  Papers (62)
| | PDF (1519 KB) | HTML

In this paper, we propose a hybrid neurogenetic system for stock trading. A recurrent neural network (NN) having one hidden layer is used for the prediction model. The input features are generated from a number of technical indicators being used by financial experts. The genetic algorithm (GA) optimizes the NN's weights under a 2-D encoding and crossover. We devised a context-based ensemble method... View full abstract»

• ### An Improved Dynamic Neurocontroller Based on Christoffel Symbols

Publication Year: 2007, Page(s):865 - 879
Cited by:  Papers (3)
| | PDF (565 KB) | HTML

In this paper, a dynamic neurocontroller for positioning of robots based on static and parametric neural networks (NNs) has been developed. This controller is based on Christoffel symbols of first kind in order to carry out coriolis/centripetal matrix. Structural properties of robots and Kronecker product has been taken into account to develop NNs to approximate nonlinearities. The weight updating... View full abstract»

• ### Feedforward Neural Network Implementation in FPGA Using Layer Multiplexing for Effective Resource Utilization

Publication Year: 2007, Page(s):880 - 888
Cited by:  Papers (72)
| | PDF (479 KB) | HTML

This paper presents a hardware implementation of multilayer feedforward neural networks (NN) using reconfigurable field-programmable gate arrays (FPGAs). Despite improvements in FPGA densities, the numerous multipliers in an NN limit the size of the network that can be implemented using a single FPGA, thus making NN applications not viable commercially. The proposed implementation is aimed at redu... View full abstract»

• ### Real-Time Neural Network Inversion on the SRC-6e Reconfigurable Computer

Publication Year: 2007, Page(s):889 - 901
Cited by:  Papers (14)
| | PDF (2269 KB) | HTML

Implementation of real-time neural network inversion on the SRC-6e, a computer that uses multiple field-programmable gate arrays (FPGAs) as reconfigurable computing elements, is examined using a sonar application as a specific case study. A feedforward multilayer perceptron neural network is used to estimate the performance of the sonar system (Jung , 2001). A particle swarm algorithm uses the tra... View full abstract»

## Aims & Scope

IEEE Transactions on Neural Networks is devoted to the science and technology of neural networks, which disclose significant technical knowledge, exploratory developments, and applications of neural networks from biology to software to hardware.

This Transactions ceased production in 2011. The current retitled publication is IEEE Transactions on Neural Networks and Learning Systems.

Full Aims & Scope