Improved Stability Analysis for Delayed Neural Networks.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 29990171.
- Also identified by DOI 10.1109/TNNLS.2017.2743262.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
In this brief, by constructing an augmented Lyapunov-Krasovskii functional in a triple integral form, the stability analysis of delayed neural networks is investigated. In order to exploit more accurate bounds for the derivatives of triple integrals, new double integral inequalities are developed, which include some recently introduced estimation techniques as special cases. The information on the activation function is taken into full consideration. Taking advantages of the proposed inequalities, the stability criteria with less conservatism are derived. The improvement of the obtained approaches is verified by numerical examples.