Global dissipativity analysis for delayed quaternion-valued neural networks.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 28223007.
- Also identified by DOI 10.1016/j.neunet.2017.01.006.
- 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
The problem of global dissipativity analysis for quaternion-valued neural networks (QVNNs) with time-varying delays is firstly investigated in this paper. The QVNN is studied as a single entirety without any decomposition. Several algebraic conditions ensuring the global dissipativity and globally exponential dissipativity for QVNNs are derived by employing Lyapunov theory and some analytic techniques. Furthermore, the positive invariant sets, globally attractive sets and globally exponentially attractive sets are figured out as well. Finally, the effectiveness is notarized by deducing two simulation examples.
Medical subject headings
- Neural Networks, Computer