Abstract
The aim of this paper is to study the predefined-time synchronization of coupled competitive neural networks (NNs) as well as the impacts of time-varying delays on the predefined-time synchronization performance. First, the models for drive and response systems of coupled competitive NNs with and without coupling delays are established for the first time in this work. After that, the predefined-time synchronization of the proposed network models is investigated, and some new predefined-time synchronization conditions for the considered drive and response systems are derived by designing novel bilayer controllers and using some inequality techniques. It is worth mentioning that the desired convergence time can be adjusted by presetting the parameters in the controllers in advance. Moreover, the synchronization is achieved in the predefined time regardless of the initial value of the coupled competitive NNs. At last, the proposed synchronization conditions are validated through two examples.
| Original language | English |
|---|---|
| Pages (from-to) | 609-621 |
| Number of pages | 13 |
| Journal | International Journal of Adaptive Control and Signal Processing |
| Volume | 39 |
| Issue number | 3 |
| Early online date | 9 Jan 2025 |
| DOIs | |
| Publication status | Published - 1 Mar 2025 |
Funding
This work was supported by the National Natural Science Foundation of China under Grants 62173244 and 62173016.
Keywords
- competitive neural networks
- coupled neural networks
- redefined-time synchronization