A Complex-Valued RTRL Algorithm for Recurrent Neural Networks

Authors:
Su Lee Goh;Danilo P. Mandic
Affiliations:
Department of Electrical and Electronic Engineering, Imperial College London, London SW7 2AZ, U.K.;Department of Electrical and Electronic Engineering, Imperial College London, London SW7 2AZ, U.K.
Venue:
Neural Computation
Year:
2004

Citing 7
Cited 10

Neural networks and nonlinear adaptive filtering: unifying concepts and new algorithms

Neural Computation
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Recurrent Neural Networks: Design and Applications

Recurrent Neural Networks: Design and Applications
Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM

Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM
Recurrent Neural Networks for Prediction: Learning Algorithms,Architectures and Stability

Recurrent Neural Networks for Prediction: Learning Algorithms,Architectures and Stability
Approximation by fully complex multilayer perceptrons

Neural Computation
Nonlinear adaptive prediction of nonstationary signals

IEEE Transactions on Signal Processing

An Augmented Extended Kalman Filter Algorithm for Complex-Valued Recurrent Neural Networks

Neural Computation
Sequential Data Fusion via Vector Spaces: Fusion of Heterogeneous Data in the Complex Domain

Journal of VLSI Signal Processing Systems
An augmented CRTRL for complex-valued recurrent neural networks

Neural Networks
Analysis of Two Neural Networks in the Intelligent Faults Diagnosis of Metallurgic Fan Machinery

ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part III
A class of discrete time recurrent neural networks with multivalued neurons

Neurocomputing
Discrete-time recurrent neural networks with complex-valued linear threshold neurons

IEEE Transactions on Circuits and Systems II: Express Briefs
A class of discrete-time recurrent neural networks with multivalued neurons

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Convergence analysis of three classes of split-complex gradient algorithms for complex-valued recurrent neural networks

Neural Computation
Metacognitive learning in a fully complex-valued radial basis function neural network

Neural Computation
Letters: A new adaptive momentum algorithm for split-complex recurrent neural networks

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A complex-valued real-time recurrent learning (CRTRL) algorithm for the class of nonlinear adaptive filters realized as fully connected recurrent neural networks is introduced. The proposed CRTRL is derived for a general complex activation function of a neuron, which makes it suitable for nonlinear adaptive filtering of complex-valued nonlinear and nonstationary signals and complex signals with strong component correlations. In addition, this algorithm is generic and represents a natural extension of the real-valued RTRL. Simulations on benchmark and real-world complex-valued signals support the approach.