TITLE:   Recurrent Neural Networks in Systems Identification
	 
AUTHORS: Chris M. Jubien and Nikitas J. Dimopoulos
	 
IN:      1993 IEEE International Symposium on 
	 Circuits and Systems, May, 1993, 
	 pp. 2458-2461 
	 

ABSTRACT 

A training procedure for a class of neural networks 
that are asymptotically stable is presented. The 
training procedure is gradient method which adapts 
the interconnection weights as well as the relaxation 
constants and the slopes of the activation function 
used so as the error between the expected and obtained 
responses is minimized. A method for assuring that 
stability is maintained throughout the training procedure
is also given. Such a network was used to identify the 
dynamic behavior of a boat based on collected 
rudder/heading data.