This paper studies controllability properties of recurrent neural networks.
The new contributions are: (I) an extension of a previous result to a slig
htly different model, (2) a formulation and proof of a necessary and suffic
ient condition, and (3) an analysis of a low-dimensional case for which the
hypotheses made in previous work do not apply. (C) 1999 Elsevier Science B
.V. All rights reserved.