Extended Kalman filter training of neural networks on a SIMD parallel machine

Authors:
Shuhui Li;Donald C. Wunsch;Edgar O'Hair;Michael G. Giesselmann
Affiliations:
Department of Electrical Engineering and Computer Science, Texas A&M University--Kingsville, Kingsville, Texas 78363;Department of Electrical and Computer Engineering, University of Missouri--Rolla, Rolla, Missouri 65409;Department of Electrical Engineering, Texas Tech University, Lubbock, Texas 79409;Department of Electrical Engineering, Texas Tech University, Lubbock, Texas 79409
Venue:
Journal of Parallel and Distributed Computing
Year:
2002

Citing 5
Cited 3

Training multilayer perceptrons with the extended Kalman algorithm

Advances in neural information processing systems 1
Kalman filtering: theory and practice

Kalman filtering: theory and practice
Introduction to parallel computing: design and analysis of algorithms

Introduction to parallel computing: design and analysis of algorithms
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Parallel Implementations of Backpropagation Neural Networks on Transputers: A Study of Training Set Parallelism

Parallel Implementations of Backpropagation Neural Networks on Transputers: A Study of Training Set Parallelism

A recurrent fuzzy neural model of a gene regulatory network for knowledge extraction using differential evolution

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Memory-efficient fully coupled filtering approach for observational model building

IEEE Transactions on Neural Networks
Filling gaps in diameter measurements on standing tree boles in the urban forest of Thessaloniki, Greece

Environmental Modelling & Software

Quantified Score

Hi-index	0.00

Visualization

Abstract

The extended Kalman filter (EKF) algorithm has been shown to be advantageous for neural network trainings. However, unlike the backpropagation (BP), many matrix operations are needed for the EKF algorithm and therefore greatly increase the computational complexity. This paper presents a method to do the EKF training on a SIMD parallel machine. We use a multistream decoupled extended Kalman filter (DEKF) training algorithm which can provide efficient use of the parallel resource and more improved trained network weights. From the overall design consideration of the DEKF algorithm and the consideration of maximum usage of the parallel resource, the multistream DEKF training is realized on a MasPar SIMD parallel machine. The performance of the parallel DEKF training algorithm is studied. Comparisons are performed to investigate pattern and batch-form trainings for both EKF and BP training algorithms.