Publication View

Further results on controllability of recurrent neural networks (1999)

Abstract
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. Comment: 12 pages

Publication details
Download http://arxiv.org/abs/math/9902023
Repository arXiv (United States)
Keywords Mathematics - Optimization and Control, 93B05
Type text