Extensions and enhancements of decoupled extended Kalman filter training
- 22 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1879-1883
- https://doi.org/10.1109/icnn.1997.614185
Abstract
We describe here three useful and practical extensions and enhancements of the decoupled extended Kalman filter (DEKF) neural network weight update procedure, which has served as the backbone for much of our applications-oriented research for the last six years. First, we provide a mechanism that constrains weight values to a pre-specified range during training to allow for fixed-point deployment of trained networks. Second, we examine modifications of DEKF training for alternative cost functions; as an example, we show how to use DEKF training to minimize a measure of relative entropy, rather than mean squared error, for pattern classification problems. Third, we describe an approximation of DEKF training that allows a multiple-output training problem to be treated with single-output training complexity.Keywords
This publication has 4 references indexed in Scilit:
- Adaptation from fixed weight dynamic networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Decoupled extended Kalman filter training of feedforward layered networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Dynamic neural network methods applied to on-vehicle idle speed controlProceedings of the IEEE, 1996
- Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networksIEEE Transactions on Neural Networks, 1994