Application of decision feedback recurrent neural network with real-time recurrent algorithm

The recurrent neural network is a kind of neural network with one or more feedback loops. We may have feedback from the output neurons of the multilayer to the input layer. Yet another possible form of feedback is from the hidden neurons of the network to the input layer. In this paper, we propose a channel equalization scheme using a decision feedback recurrent neural network, which has feedback loops from both the hidden layer and the decision part, with real-time recurrent network. Simulation results show that the proposed scheme outperforms the recurrent neural network that only has feedbacks loops from the hidden layer.

[1]  三瓶 政一,et al.  Applications of digital wireless technologies to global wireless communications , 1997 .

[2]  Sheng Chen,et al.  Reconstruction of binary signals using an adaptive radial-basis-function equalizer , 1991, Signal Process..

[3]  Saleem A. Kassam,et al.  Channel Equalization Using Adaptive Complex Radial Basis Function Networks , 1995, IEEE J. Sel. Areas Commun..

[4]  C.F.N. Cowan,et al.  The application of nonlinear structures to the reconstruction of binary signals , 1991, IEEE Trans. Signal Process..

[5]  Asrar U. H. Sheikh,et al.  Comparison of DFE and MLSE Receiver Performance on HF Channels , 1985, IEEE Trans. Commun..

[6]  Olli Simula,et al.  Neural detection of QAM signal with strongly nonlinear receiver , 1998, Neurocomputing.

[7]  Norman C. Beaulieu,et al.  Error-rate evaluation of linear equalization and decision feedback equalization with error propagation , 1998, IEEE Trans. Commun..

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

[9]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[10]  Sammy Siu,et al.  Multilayer perceptron structures applied to adaptive equalisers for data communications , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[11]  Bhaskar D. Rao,et al.  A generalized learning paradigm exploiting the structure of feedforward neural networks , 1996, IEEE Trans. Neural Networks.

[12]  John G. Proakis,et al.  Digital Communications , 1983 .