期刊
PLOS ONE
卷 13, 期 6, 页码 -出版社
PUBLIC LIBRARY SCIENCE
DOI: 10.1371/journal.pone.0199196
关键词
-
资金
- Canadian Institutes of Health Research [3531979]
- Natural Science and Engineering Research Council of Canada
- Canada Research Chairs Program
First-order tactile neurons have spatially complex receptive fields. Here we use machine-learning tools to show that such complexity arises for a wide range of training sets and network architectures. Moreover, we demonstrate that this complexity benefits network performance, especially on more difficult tasks and in the presence of noise. Our work suggests that spatially complex receptive fields are normatively good given the biological constraints of the tactile periphery.
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