Abstract
In this paper, a discrete-time projection neural network with an adaptive step size (DPNN) is proposed for distributed global optimization. The DPNN is proven to be convergent to a Karush-Kuhn-Tucker point. Several DPNNs are utilized in a collaborative neurodynamic framework for solving distributed global optimization problem. The efficacy of the collaborative neurodynamic approach with DPNNs is demonstrated through simulation results. © 2025 IEEE.
| Original language | English |
|---|---|
| Title of host publication | 13th International Conference on Intelligent Control and Information Processing (ICICIP 2025) |
| Publisher | IEEE |
| Pages | 196-204 |
| ISBN (Electronic) | 979-8-3315-1614-7 |
| DOIs | |
| Publication status | Published - 2025 |
| Event | 13th International Conference on Intelligent Control and Information Processing (ICICIP 2025) - Hybrid, Muscat, Oman Duration: 6 Feb 2025 → 11 Feb 2025 https://conference.cs.cityu.edu.hk/icicip/ICICIP2025/index.html |
Publication series
| Name | International Conference on Intelligent Control and Information Processing, ICICIP |
|---|
Conference
| Conference | 13th International Conference on Intelligent Control and Information Processing (ICICIP 2025) |
|---|---|
| Abbreviated title | ICICIP2025 |
| Country/Territory | Oman |
| City | Muscat |
| Period | 6/02/25 → 11/02/25 |
| Internet address |
Funding
The work was supported by the National Key R&D Program of China under Grant 2021ZD0201300, the National Natural Science Foundation of China under Grant 623B2040, the Innovation Group Project of the National Natural Science Foundation of China under Grant 61821003, the 111 Project on Computational Intelligence and Intelligent Control under Grant B18024, the Fundamental Research Funds for the Central Universities under Grand YCJJ20242109.
Research Keywords
- Distributed global optimization
- neurodynamic model
- projection neural networks