Comparative analysis of backpropagation and the extended Kalmanfilter for training multilayer perceptrons
Ruck, D.W.
Rogers, S.K.
Kabrisky, M.
Maybeck, P.S.
Oxley, M.E.
Sch. of Eng., Air Force Inst. of Technol., Wright-Patterson AFB, OH;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Jun 1992
Volume: 14,
Issue: 6
On page(s): 686-691
ISSN: 0162-8828
References Cited: 21
CODEN: ITPIDJ
INSPEC Accession Number: 4219586
Digital Object Identifier: 10.1109/34.141559
Current Version Published: 2002-08-06
Abstract
The relationship between backpropagation and extended Kalman
filtering for training multilayer perceptrons is examined. These two
techniques are compared theoretically and empirically using sensor
imagery. Backpropagation is a technique from neural networks for
assigning weights in a multilayer perceptron. An extended Kalman filter
can also be used for this purpose. A brief review of the multilayer
perceptron and these two training methods is provided. Then, it is shown
that backpropagation is a degenerate form of the extended Kalman filter.
The training rules are compared in two examples: an image classification
problem using laser radar Doppler imagery and a target detection problem
using absolute range images. In both examples, the backpropagation
training algorithm is shown to be three orders of magnitude less costly
than the extended Kalman filter algorithm in terms of a number of
floating-point operations
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
