暂无图片
暂无图片
暂无图片
暂无图片
暂无图片
深度神经架构搜索综述 - 孟子尧, 谷雪, 梁艳春, 许东, 吴春国.pdf
324
12页
1次
2021-11-22
免费下载
DOI
:
issn
JournalofCom
p
uterResearchandDevelo
p
ment
(
):
,
 
稿
:
;
:
 
:
(
,
,
);
(
GX
,
GX
);
(
JC
);
广
(
A
);
广
(
KZDXM
);
广
(
GDYSZDXK
)
Thiswork wassu
pp
ortedb
y
the NationalNaturalScienceFoundationofChina
(
,
,
),
the Ke
y
ResearchandDevelo
p
mentPro
j
ectofJilinProvince
(
GX
,
GX
),
theNaturalScienceFoundationofJilin
Province
(
JC
),
theScienceand Technolo
gy
Plannin
g
Pro
j
ectof Guan
g
don
g
Province
(
A
),
the
Guan
g
don
g
Ke
y
Pro
j
ectfor A
pp
lied Fundamental Research
(
KZDXM
),
andthe Guan
g
don
g
Premier Ke
y
Disci
p
line
EnhancementScheme
(
GDYSZDXK
)
 
:
(
wuc
g
j
lueducn
)
,
 
 
,
 
,
 
 
 
(
(
)
 
 
)
(
(
)
 
广
 
)
(
 
 MO
)
(
z
y
men
g
outlookcom
)
Dee
p
NeuralArchitectureSearch
:
ASurve
y
Men
g
Zi
y
ao
,
,
GuXue
,
,
Lian
g
Yanchun
,
,
XuDon
g
,
and WuChun
g
uo
(
Ke
y
Laborator
y
o
f
S
y
mbol Com
p
utation and Knowled
g
e En
g
ineerin
g
(
Jilin Universit
y
),
Ministr
y
o
f
Education
,
Chan
g
chun
)
(
ZhuhaiLaborator
y
o
f
Ke
y
Laborator
y
o
f
S
y
mbolCom
p
utationand Knowled
g
eEn
g
ineerin
g
(
ZhuhaiColle
g
eo
f
Jilin
Universit
y
),
Ministr
y
o
f
Education
,
Zhuhai
,
Guan
g
don
g
)
(
De
p
artmento
f
ElectricalEn
g
ineerin
g
and Com
p
uterScience
,
Universit
y
o
f
MissouriColumbia
,
Columbia
,
Missouri
,
USA MO
)
Abstract Dee
p
learnin
g
hasachievedexcellentresultsondatataskswith multi
p
lemodalitiessuchas
ima
g
es
,
s
p
eech
,
and text.However
,
desi
g
nin
g
networks manuall
y
for s
p
ecific tasksis time
consumin
g
andre
q
uiresacertainlevelofex
p
ertiseanddesi
g
nex
p
eriencefromthedesi
g
nerIntheface
oftoda
y
􀆳sincreasin
g
l
y
com
p
lexnetworkarchitectures
,
rel
y
in
g
on manualdesi
g
naloneincreasin
g
l
y
becomescom
p
lexForthisreason
,
automaticarchitecturesearchofneuralnetworkswiththehel
p
of
al
g
orithmshasbecomeahotresearchto
p
icThea
pp
roachofneuralarchitecturesearchinvolvesthree
as
p
ects
:
searchs
p
ace
,
searchstrate
gy
,
and
p
erformanceevaluationstrate
gy
Thesearchstrate
gy
sam
p
lesa network architecturein the search s
p
ace
,
evaluates the network architecture b
y
a
p
erformanceevaluationstrate
gy
,
andfeedbacktheresultstothesearchstrate
gy
to
g
uideittoselecta
betternetwork architecture
,
and obtainsthe o
p
timal network architecture throu
g
h continuous
iterationsInordertobettersortoutthe methodsofneuralarchitecturesearch
,
wesummarizethe
common methodsinrecent
y
earsfrom searchs
p
ace
,
searchstrate
gy
and
p
erformanceevaluation
strate
gy
,
andanal
y
zetheirstren
g
thsandweaknesses
Ke
y
words dee
p
learnin
g
;
neuralarchitecturesearch
(
NAS
);
searchs
p
ace
;
searchstrate
gy
;
p
erfor
manceevaluation
 
 
,
,
,
,
,
:
,
,
,
,
,
,
 
;
;
;
;
 TP
  
,
,
LeCun
[
]
LeNet
,
,
GPU
CPU
,
使
Krizhevsk
y
[
]
AlexNet
,
ILSVRC
(
Ima
g
eNetlar
g
escalevisualreco
g
nition
challen
g
e
)
AlexNet
,
Sze
g
ed
y
[
]
,
Goo
g
LeNet
He
[
]
,
ResNet
,
ILSVRC
,
,
,
[
]
,
,
,
,
,
(
neuralarchitecturesearch
,
NAS
)
[
]
[
]
,
Liu
[
]
,
,
,
:
,
,
,
Fi
g
 The
p
rocessofneuralarchitecturesearch
[
]
 
[
]
,
,
,
,
 
,
使
,
Liu
[
]
,
,
使 使
,
,
[
]
,
,
Cell
:
of 12
免费下载
【版权声明】本文为墨天轮用户原创内容,转载时必须标注文档的来源(墨天轮),文档链接,文档作者等基本信息,否则作者和墨天轮有权追究责任。如果您发现墨天轮中有涉嫌抄袭或者侵权的内容,欢迎发送邮件至:contact@modb.pro进行举报,并提供相关证据,一经查实,墨天轮将立刻删除相关内容。

评论

关注
最新上传
暂无内容,敬请期待...
下载排行榜
Top250 周榜 月榜