Abstract
![CDATA[This paper addresses the problem of asymptotic stability for discrete-time recurrent neural networks with time-varying delay. The analysis starts with a general assumption that the time-varying delay may be expressed as the lower bound plus the length of an interval over which the delay varies. Then the delay partitioning technique is used to establish a new delay-dependent sufficient condition under which the asymptotic stability of recurrent neural networks with time-varying delay can be guaranteed. The new stability criterion takes the form of linear matrix inequalities, thus lending itself to being readily checkable by the available software package. The obtained theoretical result is further illustrated by numerical results, including their superiority over the existing results on asymptotic stability of delayed recurrent neural networks.]]
| Original language | English |
|---|---|
| Title of host publication | 2009 IEEE International Symposium on Circuits and Systems : Circuits and Systems for Human Centric Smart Living Technologies, Conference Program, Taipei International Convention Center, Taipei, Taiwan, May 24-May 27, 2009 |
| Publisher | I.E.E.E. Press |
| Pages | 2125-2128 |
| Number of pages | 4 |
| ISBN (Print) | 9781424438273 |
| Publication status | Published - 2009 |
| Event | IEEE International Symposium on Circuits and Systems - Duration: 20 May 2012 → … |
Conference
| Conference | IEEE International Symposium on Circuits and Systems |
|---|---|
| Period | 20/05/12 → … |
Keywords
- asymptotic stability
- neural networks (computer science)