期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 34, 期 9, 页码 6677-6678出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2021.3123540
关键词
Convergence analysis; gradient descent; in-parameter-linear nonlinear learning system; weight-update stability
This article provides comments on the derivation of weight-update stability in an in-parameter-linear nonlinear learning system with the gradient descent learning rule as described in the mentioned article. The purpose of the comments is not to discredit the overall contribution of the mentioned article, but to point out the issues that need to be addressed to prevent their proliferation.
This article is to comment on the derivation of the weight-update stability of in-parameter-linear nonlinear learning system with the gradient descent learning rule in the above article. Our comments are not to disqualify the commented article's whole contribution; however, the issues should be pointed out to avoid their proliferation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据