Multi-stream extended Kalman filter training of neural networks on a SIMD parallel machine

Shuhui Li, Donald C. Wunsch, Edgar O'Hair, Michael G. Giesselmann

Research output: Contribution to conferencePaperpeer-review

1 Scopus citations

Abstract

The extended Kalman filter (EKF) algorithm has been shown to be advantageous for neural network trainings. This paper presents a method to do the EFK training on a SIMD parallel machine. We use multi-stream decoupled extended Kalman filter (DEKF) training algorithm which can provide more improved trained network weights and efficient use of the parallel resource. The performance of the parallel DEKF training algorithm is studied and simulation results for the estimation of the wind power using neural networks are provided.

Original languageEnglish
Pages59-66
Number of pages8
StatePublished - 1999
EventProceedings of the 1999 Artificial Neural Networks in Engineering Conference (ANNIE '99) - St. Louis, MO, USA
Duration: Nov 7 1999Nov 10 1999

Conference

ConferenceProceedings of the 1999 Artificial Neural Networks in Engineering Conference (ANNIE '99)
CitySt. Louis, MO, USA
Period11/7/9911/10/99

Fingerprint Dive into the research topics of 'Multi-stream extended Kalman filter training of neural networks on a SIMD parallel machine'. Together they form a unique fingerprint.

Cite this