Recurrent network training with the decoupled-extended-Kalman-filter algorithm

Gintaras V. Puskorius; Lee A. Feldkamp

doi:10.1117/12.140113

1 July 1992 Recurrent network training with the decoupled-extended-Kalman-filter algorithm

Gintaras V. Puskorius, Lee A. Feldkamp

Proceedings Volume 1710, Science of Artificial Neural Networks; (1992) https://doi.org/10.1117/12.140113
Event: Aerospace Sensing, 1992, Orlando, FL, United States

Abstract

In this paper we describe the extension of our decoupled extended Kalman filter (DEKF) training algorithm to networks with internal recurrent (or feedback) connections; we call the resulting algorithm dynamic DEKF (or DDEKF for short). Analysis of DDEKF's computational complexity and empirical evidence suggest significant computational and performance advantages in comparison to training algorithms based exclusively upon gradient descent. We demonstrate DDEKF's effectiveness by training networks with recurrent connections for four different classes of problems. First, DDEKF is used to train a recurrent network that produces as its output a delayed copy of its input. Second, recurrent networks are trained by DDEKF to recognize sequences of events with arbitrarily long time delays between the events. Third, DDEKF is applied to the training of identification networks to act as models of the input-output behavior for nonlinear dynamical systems. We conclude the paper with a brief discussion of the extension of DDEKF to the training of neural controllers with internal feedback connections.

Citation Download Citation

Gintaras V. Puskorius and Lee A. Feldkamp "Recurrent network training with the decoupled-extended-Kalman-filter algorithm", Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); https://doi.org/10.1117/12.140113

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available