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 language | English (US) |
|---|---|
| Pages (from-to) | 121-129 |
| Number of pages | 9 |
| Journal | Systems and Control Letters |
| Volume | 36 |
| Issue number | 2 |
| DOIs | |
| State | Published - Feb 15 1999 |
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Computer Science(all)
- Mechanical Engineering
- Electrical and Electronic Engineering
Keywords
- Backstepping of controllability
- Controllability
- Local controllability
- Neural networks
- Recurrent networks