神经网络结构搜索方法综述 刘建伟.pdf

文档介绍：: .
控制理论与应 ²ä(§÷vØÓI¦. ´§<óO ²ä(I‡;’•£§?1
Œþ¢. Ïd§ ²ä(|¢Ž{ïÄw4••‡. ²ä(|¢(NAS)´gÄÝÆ
S(AutoDL)L§¥˜‡ÄÚ½§éÝÆSuІA^kX•‡K•. @ϧ˜
²ä(|¢Ž
{•,|¢
5U` ²ä(§´I‡ŒþOŽ]
!|¢Ç$e. Ïd§ïÄ<
&¢
õ
«O ²ä(Ž{§•JÑ
Nõ~OŽ]
!Jp|¢Ç•{. ©Äk{‡0
²ä
(|¢˜m§Ùgé ²ä(|¢Ž{?1
¡©a®o!©Û§Ì‡•)‘Å|¢Ž{!?zŽ
{!rzÆS!ÄuFÝeü•{!Äu^S.`zŽ{§2Ùg&¢¿o(
Jp ²ä(|¢
Ç•{§•
&?
8c ²ä(|¢óŠ¥•3¯K±9™5ïÄ••.
'…c: ²ä(|¢; |¢˜m; |¢üÑ; 5UµüÑ
Ú^‚ª: 4ï•, #". ²ä(|¢•{nã. ››n؆A^, 2022, 39: 1 – 10
DOI: .10568
A Review of Neural Network Structure Search Method
LIU Jian-wei1†,WANG Xin-tan1
(1. Department of Automation,China University of Petroleum,Beijing 102249,China)
Abstract: Nowadays, deep learning is widely used in all aspects of life and work, which brings us great convenience.
In this context, we need to design neural network structure for different tasks to meet different needs. However, manually
design of neural network structure needs professional knowledge and a lot of experiments. Therefore, the research of
neural network structure search algorithm is very important. Neural network structure search (NAS) is a basic step in the
process of automatic deep learning (AutoDL), which has an important impact on the development and application of deep