期刊
NEURAL NETWORK WORLD
卷 22, 期 4, 页码 387-393出版社
ACAD SCIENCES CZECH REPUBLIC, INST COMPUTER SCIENCE
DOI: 10.14311/NNW.2012.22.023
关键词
Sigmoid function; Chebyshev polynomials; recursive algorithms
资金
- Grant Agency of the Czech Republic [GAP102/11/1795]
An alternative polynomial approximation for the activation sigmoid function is developed here. It can considerably simplify the input/output operations of a neural network. The recursive algorithm is found for Chebyshev expansion of all constituting polynomials.
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