Robust control in closed loops realised by fast signal transmission of infinite gain neurons

We show that using recurrent networks with finite time constants is not contradictory to arbitrary fast signal transmission in a closed loop with appropriate feedbacks. This surprising result is due to the occurrence of infinitely amplifying subloops, which we formally describe by differential inclu...

Full description

Saved in:
Bibliographic Details
Main Author: Steil, J.J.
Format: Conference Proceeding
Language:English
Subjects:
Appropriate technology
Biological system modeling
Feedback loop
Fires
Integral equations
Intelligent networks
Neurofeedback
Neurons
Robust control
Transfer functions
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We show that using recurrent networks with finite time constants is not contradictory to arbitrary fast signal transmission in a closed loop with appropriate feedbacks. This surprising result is due to the occurrence of infinitely amplifying subloops, which we formally describe by differential inclusions. The theory then shows that the transmission speed depends crucially on the gain of the transfer function. Generalising the theoretical framework we demonstrate how to build efficient, fast and robust neuro-controllers with pre-specified performance by application to the benchmark problem of balancing the inverted pendulum.
ISSN:1098-7576
1558-3902
DOI:10.1109/IJCNN.2000.857846