Title :
Truncated backpropagation through time and Kalman filter training for neurocontrol
Author :
Puskorius, G.V. ; Feldkamp, L.A.
Author_Institution :
Res. Lab., Ford Motor Co., Dearborn, MI, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
We have recently established the feasibility of training recurrent neural networks by parameter-based decoupled extended Kalman filter (DEKF) algorithms for control of nonlinear dynamical systems. In this paper we investigate the use of truncated backpropagation through time (BPTT) for approximating the required dynamic derivatives that are used by the DEKF training algorithm. The use of this approximation allows the gradient calculations and weight updates by the DEKF algorithm to be performed asynchronously with application of control signals, thereby leading to a scalable, real-time, online training algorithm. We demonstrate in simulation the effectiveness of the BPTT-based DEKF algorithm for the problem of automotive engine idle speed control
Keywords :
Kalman filters; approximation theory; backpropagation; internal combustion engines; neurocontrollers; real-time systems; recurrent neural nets; Kalman filter training; approximation; automotive engine; dynamic derivatives; gradient calculations; idle speed control; neurocontrol; recurrent neural networks; scalable real-time online learning; truncated backpropagation through time; weight updates; Approximation algorithms; Automotive engineering; Backpropagation algorithms; Control systems; Engines; Nonlinear control systems; Nonlinear dynamical systems; Recurrent neural networks; Vehicle dynamics; Velocity control;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374611
