Further results on controllability of recurrent neural networks

E. D. Sontag, Y. Qiao

Research output: Contribution to journalArticle

21 Scopus citations

Abstract

This paper studies controllability properties of recurrent neural networks. The new contributions are: (1) an extension of a previous result to a slightly different model, (2) a formulation and proof of a necessary and sufficient condition, and (3) an analysis of a low-dimensional case for which the hypotheses made in previous work do not apply.

Original languageEnglish (US)
Pages (from-to)121-129
Number of pages9
JournalSystems and Control Letters
Volume36
Issue number2
DOIs
StatePublished - Feb 15 1999

All Science Journal Classification (ASJC) codes

  • Mechanical Engineering
  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science(all)

Keywords

  • Backstepping of controllability
  • Controllability
  • Local controllability
  • Neural networks
  • Recurrent networks

Fingerprint Dive into the research topics of 'Further results on controllability of recurrent neural networks'. Together they form a unique fingerprint.

  • Cite this