Further results on controllability of recurrent neural networks
Abstract
Description
This paper studies controllability properties of recurrent neural networks. The new contributions are:
(1) an extension of the result in the previous paper "Complete controllability of continuous-time recurrent neural networks" (Sontag and Sussmann) to a slightly different model, where inputs appear in an affine form,
(2) a formulation and proof of a necessary and sufficient condition, in terms of local-local controllability, and
(3) a complete analysis of the 2-dimensional case for which the hypotheses made in previous work do not apply
12 pages
12 pages