A collaborative neurodynamic approach with two-timescale projection neural networks designed via majorization-minimization for global optimization and distributed global optimization

• DOI: 10.1016/j.neunet.2024.106525
• Publication Date: 2024-07-11T22:25:08Z
• Authors: Yangxia Li; Zicong Xia; Yang Liu; Jun Wang
• Keywords: Minification; Deep Neural Networks; Global Optimization; Majorization

In this paper, two two-timescale projection neural networks are proposed based on the majorization-minimization principle for nonconvex optimization and distributed nonconvex optimization. They are proved to be globally convergent to Karush-Kuhn-Tucker points. A collaborative neurodynamic approach leverages multiple two-timescale projection neural networks repeatedly re-initialized using a meta-heuristic rule for global optimization and distributed global optimization. Two numerical examples are elaborated to demonstrate the efficacy of the proposed approaches.