Two-timescale projection neural networks in collaborative neurodynamic approaches to global optimization and distributed optimization. Huang, B., Liu, Y., Jiang, Y., & Wang, J. Neural Networks, 169:83–91, January, 2024.
Two-timescale projection neural networks in collaborative neurodynamic approaches to global optimization and distributed optimization [link]Paper  doi  abstract   bibtex   
In this paper, we propose a two-timescale projection neural network (PNN) for solving optimization problems with nonconvex functions. We prove the convergence of the PNN with sufficiently different timescales to a local optimal solution. We develop a collaborative neurodynamic approach with multiple such PNNs to search for global optimal solutions. In addition, we develop a collaborative neurodynamic approach with multiple PNNs connected via a directed graph for distributed global optimization. We elaborate on four numerical examples to illustrate the characteristics of the approaches.
@article{huang_two-timescale_2024,
	title = {Two-timescale projection neural networks in collaborative neurodynamic approaches to global optimization and distributed optimization},
	volume = {169},
	issn = {08936080},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0893608023005671},
	doi = {10.1016/j.neunet.2023.10.011},
	abstract = {In this paper, we propose a two-timescale projection neural network (PNN) for solving optimization problems with nonconvex functions. We prove the convergence of the PNN with sufficiently different timescales to a local optimal solution. We develop a collaborative neurodynamic approach with multiple such PNNs to search for global optimal solutions. In addition, we develop a collaborative neurodynamic approach with multiple PNNs connected via a directed graph for distributed global optimization. We elaborate on four numerical examples to illustrate the characteristics of the approaches.},
	language = {en},
	urldate = {2023-10-22},
	journal = {Neural Networks},
	author = {Huang, Banghua and Liu, Yang and Jiang, Yun-Liang and Wang, Jun},
	month = jan,
	year = {2024},
	pages = {83--91},
}

Downloads: 0