摘要
Dear editor,This letter identifies two weaknesses of state-of-the-art k-winnerstake-all(k-WTA)models based on recurrent neural networks(RNNs)when considering time-dependent inputs,i.e.,the lagging error and the infeasibility in finite-time convergence based on the Lipschitz continuity.
基金
supported by the National Natural Science Foundation of China(62072429)
the Key Cooperation Project of Chongqing Municipal Education Commission(HZ2021017,HZ2021008)。
作者简介
Mei Liu,e-mail:liumeisysu@qq.com;Corresponding author:Mingsheng Shang,e-mail:msshang@cigit.ac.cn.
