Abstract
This paper presents a two-time-scale neurodynamic approach to constrained minimax optimization using two coupled neural networks. One of the recurrent neural networks is used for minimizing the objective function and another is used for maximization. It is shown that the coupled neurodynamic systems operating in two different time scales work well for minimax optimization. The effectiveness and characteristics of the proposed approach are illustrated using several examples. Furthermore, the proposed approach is applied for H∞ model predictive control.
| Original language | English |
|---|---|
| Pages (from-to) | 620-629 |
| Journal | IEEE Transactions on Neural Networks and Learning Systems |
| Volume | 28 |
| Issue number | 3 |
| Online published | 27 Apr 2016 |
| DOIs | |
| Publication status | Published - Mar 2017 |
Research Keywords
- Minimax problem
- neurodynamic optimization
- recurrent neural networks (RNNs)
- two-time-scale systems
Fingerprint
Dive into the research topics of 'A Two-Time-Scale Neurodynamic Approach to Constrained Minimax Optimization'. Together they form a unique fingerprint.Projects
- 2 Finished
-
GRF: Intelligent Motion Control and Planning of Autonomous Underwater Vehicles
WANG, J. (Principal Investigator / Project Coordinator) & Liu, Y. H. (Co-Investigator)
1/01/15 → 11/06/19
Project: Research
-
GRF: Neurodynamic Approaches to Constrained Optimization with Generalized-Convex and Multiple-Objective Functions
WANG, J. (Principal Investigator / Project Coordinator) & LI, D. (Co-Investigator)
1/01/13 → 15/06/17
Project: Research
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver