posted on 2017-12-06, 00:00authored byP 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)