IEEE Trans Cybern. 2022 Aug;52(8):8515-8527. doi: 10.1109/TCYB.2021.3079457. Epub 2022 Jul 19.
In this article, a robust k -winner-take-all ( k -WTA) neural network employing the saturation-allowed activation functions is designed and investigated to perform a k -WTA operation, and is shown to possess enhanced robustness to disturbance compared to existing k -WTA neural networks. Global convergence and robustness of the proposed k -WTA neural network are demonstrated through analysis and simulations. An application studied in detail is competitive multiagent coordination and dynamic task allocation, in which k active agents [among ] are allocated to execute a tracking task with the static m-k ones. This is implemented by adopting a distributed k -WTA network with limited communication, aided with a consensus filter. Simulation results demonstrating the system's efficacy and feasibility are presented.
在本文中，设计并研究了一种采用允许饱和激活函数的稳健 k-胜者通吃（k-WTA）神经网络，以执行 k-WTA 操作，并显示出比现有 k-WTA 神经网络具有更强的抗扰性。通过分析和仿真证明了所提出的 k-WTA 神经网络的全局收敛性和鲁棒性。详细研究的应用是竞争多智能体协调和动态任务分配，其中 k 个活动智能体[在]中被分配执行具有静态 m-k 的跟踪任务。这是通过采用具有有限通信的分布式 k-WTA 网络并辅助一致性滤波器来实现的。本文提出了一个仿真结果，展示了该系统的有效性和可行性。
