Decision feedback recurrent neural equalization with fast convergence rate

Real-time recurrent learning (RTRL), commonly employed for training a fully connected recurrent neural network (RNN), has a drawback of slow convergence rate. In the light of this deficiency, a decision feedback recurrent neural equalizer (DFRNE) using the RTRL requires long training sequences to achieve good performance. In this paper, extended Kalman filter (EKF) algorithms based on the RTRL for the DFRNE are presented in state-space formulation of the system, in particular for complex-valued signal processing. The main features of global EKF and decoupled EKF algorithms are fast convergence and good tracking performance. Through nonlinear channel equalization, performance of the DFRNE with the EKF algorithms is evaluated and compared with that of the DFRNE with the RTRL.

[1]  Raffaele Parisi,et al.  Performance comparison among neural decision feedback equalizers , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[2]  Pedro Henrique Gouvêa Coelho.  A new state space model for a complex RTRL neural network , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[3]  Bhaskar D. Rao,et al.  Fast adaptive digital equalization by recurrent neural networks , 1997, IEEE Trans. Signal Process..

[4]  Elias S. Manolakos,et al.  Using recurrent neural networks for adaptive communication channel equalization , 1994, IEEE Trans. Neural Networks.

[5]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[6]  Daesik Hong,et al.  A decision feedback recurrent neural equalizer as an infinite impulse response filter , 1997, IEEE Trans. Signal Process..

[7]  G. V. Puskorius,et al.  A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering, and classification , 1998, Proc. IEEE.

[8]  Mohamed Ibnkahla,et al.  Applications of neural networks to digital communications - a survey , 2000, Signal Process..

[9]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[10]  Tülay Adali,et al.  Fully Complex Multi-Layer Perceptron Network for Nonlinear Signal Processing , 2002, J. VLSI Signal Process..

[11]  C. F. N. Cowan,et al.  Time‐variant equalization using a novel non‐linear adaptive structure , 1998 .

[12]  Elias S. Manolakos,et al.  Training fully recurrent neural networks with complex weights , 1994 .

[13]  Sheng Chen,et al.  Adaptive Bayesian equalizer with decision feedback , 1993, IEEE Trans. Signal Process..

[14]  Sharad Singhal,et al.  Training Multilayer Perceptrons with the Extende Kalman Algorithm , 1988, NIPS.

[15]  Lee A. Feldkamp,et al.  Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks , 1994, IEEE Trans. Neural Networks.

[16]  Jesús Cid-Sueiro,et al.  A neuro-evolutionary framework for Bayesian blind equalization in digital communications , 2003, Signal Process..

[17]  Pedro Henrique Gouvêa Coelho.  A complex EKF-RTRL neural network , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[18]  C.F.N. Cowan,et al.  Adaptive equalization of finite nonlinear channels using multilayer perceptron , 1990 .

[19]  Kadri Hacioglu.  An improved recurrent neural network for M-PAM symbol detection , 1997, IEEE Trans. Neural Networks.

[20]  Jianming Lu,et al.  Combining Recurrent Neural Networks with Self-Organizing Map for Channel Equalization , 2002 .

[21]  Daesik Hong,et al.  A complex version of a decision feedback recurrent neural equalizer as an infinite impulse response filter , 1997, GLOBECOM 97. IEEE Global Telecommunications Conference. Conference Record.

[22]  Simon Haykin,et al.  A Signal Processing Framework Based on Dynamic Neural Networks with Application to Problems in Adaptation, Filtering and Classification , 2001 .

[23]  Raffaele Parisi,et al.  Complex discriminative learning Bayesian neural equalizer , 2001, Signal Process..

[24]  Kadri Hacio.  An Improved Recurrent Neural Network for M-PAM Symbol Detection , 1997 .

[25]  Kyung Sup Kwak,et al.  On Modified Complex Recurrent Neural Network Adaptive Equalizer , 2002, J. Circuits Syst. Comput..