Training controllers for robustness: multi-stream DEKF
- 17 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 2377-2382 vol.4
- https://doi.org/10.1109/icnn.1994.374591
Abstract
Kalman-filter-based training has been shown to be advantageous in many training applications. By its nature, extended Kalman filter (EKF) training is realized with instance-by-instance updates, rather than by performing updates at the end of a batch of training instances or patterns. Motivated originally by the desire to be able to base an update an a collection of instances, rather than just one, we recognized that the simple construct of multiple streams of training examples allows a batch-like update to be performed without violating an underlying principle of Kalman training, vis. that the approximate error covariance matrix remain consistent with the updates that have actually been performed. In this paper, we present this construct and show how it may be used to train robust controllers, i.e. controllers that perform well for a range of plants.Keywords
This publication has 14 references indexed in Scilit:
- Model reference adaptive control with recurrent networks trained by the dynamic DEKF algorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Neural network control of an unstable processPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Truncated backpropagation through time and Kalman filter training for neurocontrolPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networksIEEE Transactions on Neural Networks, 1994
- Neural network modeling and control of an anti-lock brake systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Gradient methods for the optimization of dynamical systems containing neural networksIEEE Transactions on Neural Networks, 1991
- An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network TrajectoriesNeural Computation, 1990
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990
- Backpropagation through time: what it does and how to do itProceedings of the IEEE, 1990
- A Learning Algorithm for Continually Running Fully Recurrent Neural NetworksNeural Computation, 1989