cqu_389+DS3+DS3.2.pdf (193.44 kB)

On stability of recurrent neural networks : an approach from volterra integro-differential equations

Download (193.44 kB)
journal contribution
posted on 06.12.2017, 00:00 by P Liu, Qing-Long Han
The uniform asymptotic stability of recurrent neural networks (RNNs) with distributed delay is analyzed by comparing RNNs to linear Volterra integro-differential systems under Lipschitz continuity of activation functions. The stability criteria obtained have unified and extended many existing results on RNNs.

Funding

Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)

History

Volume

17

Issue

1

Start Page

264

End Page

267

Number of Pages

4

eISSN

1941-0093

ISSN

1045-9227

Location

New York (NY)

Publisher

Institute of Electrical and Electronics Engineers

Language

en-aus

Peer Reviewed

Yes

Open Access

No

External Author Affiliations

Faculty of Business and Informatics; Flinders University; TBA Research Institute;

Era Eligible

Yes

Journal

IEEE Transactions on Neural Networks

Exports