Remarks on controllability of recurrent neural networks

E. D. Sontag, Y. Qiao

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

The controllability properties of recurrent neural networks are studied. A sufficient condition for complete controllability is obtained and this condition is discussed. Obtaining controllability results for input-affine nets is not completely trivial. A complete characterization of controllability for two-dimensional recurrent nets is provided.

Original languageEnglish (US)
Pages (from-to)501-506
Number of pages6
JournalProceedings of the IEEE Conference on Decision and Control
Volume1
StatePublished - 1998
EventProceedings of the 1998 37th IEEE Conference on Decision and Control (CDC) - Tampa, FL, USA
Duration: Dec 16 1998Dec 18 1998

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization

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

Cite this