On-line learning in recurrent neural networks using nonlinear Kalman filters

@article{Todorovic2003OnlineLI,
  title={On-line learning in recurrent neural networks using nonlinear Kalman filters},
  author={Branimir Todorovic and Miomir Stankovic and Claudio Moraga},
  journal={Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat. No.03EX795)},
  year={2003},
  pages={802-805}
}
The extended Kalman filter has been successfully applied to the feedforward and the recurrent neural network training. Recently introduced derivative-free filters (unscented Kalman filter and divided difference filter) outperform the extended Kalman filter in nonlinear state estimation. In the parameter estimation of the feedforward neural networks UKF and DDF are comparable or slightly better than EKF, with a significant advantage that they do not demand calculation of the neural network… CONTINUE READING

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…