Title :
Remarks on controllability of recurrent neural networks
Author :
Sontag, E.D. ; Qiao, Y.
Author_Institution :
Dept. of Math., Rutgers Univ., Piscataway, NJ, USA
Abstract :
For recurrent neural networks, this paper extends results on controllability to a slightly different model, formulates a necessary and sufficient condition, and completely characterizes the two-dimensional case
Keywords :
controllability; recurrent neural nets; 2D system; controllability; necessary and sufficient condition; recurrent neural networks; Computer networks; Controllability; Equations; Force control; Mathematical model; Mathematics; Neural networks; Recurrent neural networks; State-space methods; Sufficient conditions;
Conference_Titel :
Decision and Control, 1998. Proceedings of the 37th IEEE Conference on
Conference_Location :
Tampa, FL
Print_ISBN :
0-7803-4394-8
DOI :
10.1109/CDC.1998.760727
