Nonlinear adaptive prediction of complex-valued signals by complex-valued PRNN

Authors:
Su Goh;D.P. Mandic
Affiliations:
Dept. of Electr. & Electron. Eng., Imperial Coll. London, UK;-
Venue:
IEEE Transactions on Signal Processing
Year:
2005

Citing 0
Cited 9

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

Journal of VLSI Signal Processing Systems
Nonlinear dynamic system identification using pipelined functional link artificial recurrent neural network

Neurocomputing
A novel adaptive nonlinear filter-based pipelined feed-forward second-order Volterra architecture

IEEE Transactions on Signal Processing
A novel adaptive bilinear filter based on pipelined architecture

Digital Signal Processing
A novel nonlinear adaptive filter using a pipelined second-order Volterra recurrent neural network

Neural Networks
Complex-valued neural networks: the merits and their origins

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Complex valued recurrent neural networks for noncircular complex signals

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Pipelined Chebyshev functional link artificial recurrent neural network for nonlinear adaptive filter

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Recent progress in applications of complex-valued neural networks

ICAISC'10 Proceedings of the 10th international conference on Artifical intelligence and soft computing: Part II

Quantified Score

Hi-index	35.69

Visualization

Abstract

A complex-valued pipelined recurrent neural network (CPRNN) for nonlinear adaptive prediction of complex nonlinear and nonstationary signals is introduced. This architecture represents an extension of the recently proposed real-valued PRNN of Haykin and Li in 1995. To train the CPRNN, a complex-valued real time recurrent learning (CRTRL) algorithm is first derived for a single recurrent neural network (RNN). This algorithm is shown to be generic and applicable to general signals that have complex domain representations. The CRTRL is then extended to suit the modularity of the CPRNN architecture. Further, to cater to the possibly large dynamics of the input signals, a gradient adaptive amplitude of the nonlinearity within the neurons is introduced to give the adaptive amplitude CRTRL (AACRTRL). A comprehensive analysis of the architecture and associated learning algorithms is undertaken, including the role of the number of nested modules, number of neurons within the modules, and input memory of the CPRNN. Simulations on real-world and synthetic complex data support the proposed architecture and algorithms.