Distributed Inertial k -Winners-Take-All Neural Network Based on Quadratic Optimization Problems
- 20 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP (2162237X) , 1-13
Abstract
The $k$ -winners-take-all ( $k$ -WTA) problem is to find the $k$ largest inputs from $n$ inputs. Based on the existing quadratic programming model, this article proposes a new $k$ -WTA network with an inertia term. The inertial term is designed to modulate the instantaneous behavior of the trajectory and use historical information to accelerate convergence. Traditional Lyapunov methods are inapplicable due to the inertia term. To overcome this, a cocoercive operator is used to prove asymptotic and exponential convergence to the $k$ -WTA solution from any initial state. Additionally, the article investigates distributed $k$ -WTA networks with restrictive equality constraints. Finally, simulations are used to confirm the efficacy of the suggested $k$ -WTA network.Keywords
Funding Information
- Key Program of the National Natural Science Foundation of China (62333016)
- National Natural Science Foundation of China (62173177)
- National Natural Science Foundation of China (62276119)
- National Natural Science Foundation of China (62373358)
This publication has 42 references indexed in Scilit:
- Event-triggered explorized IRL-based decentralized fault-tolerant guaranteed cost control for interconnected systems against actuator failuresNeurocomputing, 2024
- Velocity-free distributed coordinated optimal control for second-order multi-agent systemsAutomatica, 2023
- Distributed -winners-take-all via multiple neural networks with inertiaNeural Networks, 2022
- A second-order accelerated neurodynamic approach for distributed convex optimizationNeural Networks, 2022
- Analysis and design of a distributed -winners-take-all modelAutomatica, 2020
- Convex Analysis and Monotone Operator Theory in Hilbert Spaces2017
- A class of finite-time dual neural networks for solving quadratic programming problems and its -winners-take-all applicationNeural Networks, 2013
- A novel neural dynamical approach to convex quadratic program and its efficient applicationsNeural Networks, 2009
- Two k-winners-take-all networks with discontinuous activation functionsNeural Networks, 2008
- Convex Analysis2006