Mohamed Oubbati, Paul Levi, and Michael Schanz
A FIXED-WEIGHT RNN DYNAMIC CONTROLLER FOR MULTIPLE MOBILE ROBOTS
==================================================================================================
Abstract: "...... The controller is properly trained to exhibit adaptive behaviour after its weights have been fixed. ..." => true?

--------------------------------------------------------------------------------------------------
"The adaptive behaviour of RNNs with fixed weights is named differently. It is termed �gmeta-learning�h in [6], and �gaccommodative�h in [7]."

     [6] Prokhorov, D., Feldkamp, L., and I. Tyukin, 
Adaptive Behavior with Fixed Weights in Recurrent Neural Networks: An Overview, 
Int. Joint Conference on Neural Networks, Honolulu, Hawaii, May 2002. => done

     [7] J. Lo, 
Adaptive vs. Accommodative Neural networks for Adaptive System Identification, 
Int. Joint Conf. on Neural Networks, 2001, 2001-2006. => done


--------------------------------------------------------------------------------------------------
"Adaptation here is [sic] ... to adjust its behaviour to these changes, without changing any synaptic weight.

--------------------------------------------------------------------------------------------------
the ESN controller is asked to exhibit a characteristic, normally ascribed to adaptive controllers, whose parameters change in response to an environmental change. �gAdaptation�h in this work is defined as the ability of the controller to recognize change only through the robot output and its own state, without changing any synaptic weight."