Simple and conditioned adaptive behavior from Kalman filter trained recurrent networks

Authors:
Lee A. Feldkamp;Danil V. Prokhorov;Timothy M. Feldkamp
Affiliations:
Research and Advanced Engineering, Ford Motor Company, Dearborn, MI;Research and Advanced Engineering, Ford Motor Company, Dearborn, MI;Research and Advanced Engineering, Ford Motor Company, Dearborn, MI
Venue:
Neural Networks - 2003 Special issue: Advances in neural networks research — IJCNN'03
Year:
2003

Citing 4
Cited 3

Adaptive state representation and estimation using recurrent connectionist networks

Neural networks for control
Adaptive behavior form fixed weight networks

Information Sciences: an International Journal
Kalman Filtering and Neural Networks

Kalman Filtering and Neural Networks
Fixed-weight on-line learning

IEEE Transactions on Neural Networks

Training ANFIS as an identifier with intelligent hybrid stable learning algorithm based on particle swarm optimization and extended Kalman filter

Fuzzy Sets and Systems
Decentralized discrete-time neural control for a Quanser 2-DOF helicopter

Applied Soft Computing
Discrete-time inverse optimal neural control for synchronous generators

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We illustrate the ability of a fixed-weight neural network, trained with Kalman filter methods, to perform tasks that are usually entrusted to an explicitly adaptive system. Following a simple example, we demonstrate that such a network can be trained to exhibit input-output behavior that depends on which of two conditioning tasks was performed a substantial number of time steps in the past. This behavior can also be made to survive an intervening interference task.