Name
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/TNN.2005.845142 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
state space formulation,state-space methods,good tracking performance,extended kalman filter,kalman filters,learning (artificial intelligence),extended kalman filter (ekf),long training sequence,decision feedback recurrent neural,real-time recurrent learning,time-varying channel,real time recurrent learning,convergence,recurrent neural network (rnn),telecommunication computing,fast convergence rate,channel equalization,good performance,decoupled ekf algorithm,recurrent neural nets,global ekf,recurrent neural network,ekf algorithm,decision feedback recurrent neural equalization,decision feedback equalisers,fast convergence,real-time recurrent learning (rtrl),nonlinear filters,computer simulation,learning artificial intelligence,convergence rate,recurrent neural networks,algorithms,neural networks,neurofeedback,state space,stochastic processes,feedback,signal processing,intersymbol interference,finite impulse response filter,nonlinear distortion | Convergence (routing),Signal processing,Extended Kalman filter,Equalization (audio),Computer science,Control theory,Recurrent neural network,Kalman filter,Artificial intelligence,Rate of convergence,Machine learning,Feed forward | Journal |
Volume | Issue | ISSN |
16 | 3 | 1045-9227 |
Citations | PageRank | References |
18 | 1.08 | 14 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jong-Soo Choi | 1 | 147 | 30.10 |
| M. Bouchard | 2 | 195 | 17.65 |
| tet hin yeap | 3 | 27 | 2.78 |