IEEE Computational Intelligence Magazine - August 2021 - 26

B. Evolution
The evolutionary strategy is summarized in Alg. 1. Unlike AmoebaNet
[36], which evaluates the performance of the sub-networks
sampled from the search space in a population, our method evolves
the operation in each block in a trial-and-test manner. We first
mutate the operation based on its mutation probability, followed
by an evaluation step to make sure the mutation is ultimately used.
Mutation: An initial structure 0a is manually designed (e.g.,
ResNet-50)3 or searched by another NAS (e.g., ProxylessNAS
[4]) on a different dataset using supervised learning. The initial
subnetwork
f ,si
which is generated by searching over-parameterized
network based on a0 , is then trained using (6) for k steps to
obtain the evaluation metric
lo .k
^hi
then constructed from the old architecture n 1a -
A new architecture ()o ,
()o ,kn 1an
kn
transformation or a mutation. The mutation probability pmt
defined as
3 No weight parameters.
is
by a
is
po h =
mt ^
where sak
i
kn
i
,
The operation ok
i
Z
[
\
]]
]
1 - e,oo 1,, -
K 1 f1
kn
i
1
-
-
=
kn
i
sa
k
i
/sa l
kl
k
i
p
e , otherwise
(1)
represents the sampling times of the operation .ok
i
represents the kth operation in the ith block
and n represents current number of evolutions or the index of
epoch. In general, the operation in each block is kept constant
with a probability 1 ein
the beginning. For the mutation,
younger (less sample time) operations are more likely to be
selected, with a probability of ,e Intuitively, keeping the operation
constant can be thought of as providing exploitation,
while mutations provide exploration [36]. We use two main
mutations that we call the depth mutation and the op mutation,
as in AmoebaNet [36], to modify the structure generated
by the search space described above.
The operation mutation pays attention to the selection of
operations in each block. Once the operation in a block is
Performance Evaluation
InfoNCE Loss
t = fθt
(xt)
Teacher
s0, s1, s2...
Reduce
Student
Teacher
Search Space
FaUNAE
(a)
EMA
TS Contrastive Learning
Student
t = fθt
(xt)
s0, s1, s2...
Conv
1×1
Conv
1×1
Conv
3×3
Conv
1×1
Conv
3×3
Conv
5×5
Conv
1×1
SAConv
3×3
SAConv
5×5
fmap in Memory
fmap not in Memory
1) Bottleneck
2) Search Block
(b)
FIGURE 2 (a) The main framework of the Teacher-Student model, which focuses on both the unsupervised neural architecture evolution (left)
and contrastive learning (right). (b) Compared with the original bottleneck (1) in ResNet, a new search block is designed for FaUNAE (2). " fmap
in memory " means that we select the operation to participate in the feature map calculation.
26 IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE | AUGUST 2021

IEEE Computational Intelligence Magazine - August 2021

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - August 2021

Contents
IEEE Computational Intelligence Magazine - August 2021 - Cover1
IEEE Computational Intelligence Magazine - August 2021 - Cover2
IEEE Computational Intelligence Magazine - August 2021 - Contents
IEEE Computational Intelligence Magazine - August 2021 - 2
IEEE Computational Intelligence Magazine - August 2021 - 3
IEEE Computational Intelligence Magazine - August 2021 - 4
IEEE Computational Intelligence Magazine - August 2021 - 5
IEEE Computational Intelligence Magazine - August 2021 - 6
IEEE Computational Intelligence Magazine - August 2021 - 7
IEEE Computational Intelligence Magazine - August 2021 - 8
IEEE Computational Intelligence Magazine - August 2021 - 9
IEEE Computational Intelligence Magazine - August 2021 - 10
IEEE Computational Intelligence Magazine - August 2021 - 11
IEEE Computational Intelligence Magazine - August 2021 - 12
IEEE Computational Intelligence Magazine - August 2021 - 13
IEEE Computational Intelligence Magazine - August 2021 - 14
IEEE Computational Intelligence Magazine - August 2021 - 15
IEEE Computational Intelligence Magazine - August 2021 - 16
IEEE Computational Intelligence Magazine - August 2021 - 17
IEEE Computational Intelligence Magazine - August 2021 - 18
IEEE Computational Intelligence Magazine - August 2021 - 19
IEEE Computational Intelligence Magazine - August 2021 - 20
IEEE Computational Intelligence Magazine - August 2021 - 21
IEEE Computational Intelligence Magazine - August 2021 - 22
IEEE Computational Intelligence Magazine - August 2021 - 23
IEEE Computational Intelligence Magazine - August 2021 - 24
IEEE Computational Intelligence Magazine - August 2021 - 25
IEEE Computational Intelligence Magazine - August 2021 - 26
IEEE Computational Intelligence Magazine - August 2021 - 27
IEEE Computational Intelligence Magazine - August 2021 - 28
IEEE Computational Intelligence Magazine - August 2021 - 29
IEEE Computational Intelligence Magazine - August 2021 - 30
IEEE Computational Intelligence Magazine - August 2021 - 31
IEEE Computational Intelligence Magazine - August 2021 - 32
IEEE Computational Intelligence Magazine - August 2021 - 33
IEEE Computational Intelligence Magazine - August 2021 - 34
IEEE Computational Intelligence Magazine - August 2021 - 35
IEEE Computational Intelligence Magazine - August 2021 - 36
IEEE Computational Intelligence Magazine - August 2021 - 37
IEEE Computational Intelligence Magazine - August 2021 - 38
IEEE Computational Intelligence Magazine - August 2021 - 39
IEEE Computational Intelligence Magazine - August 2021 - 40
IEEE Computational Intelligence Magazine - August 2021 - 41
IEEE Computational Intelligence Magazine - August 2021 - 42
IEEE Computational Intelligence Magazine - August 2021 - 43
IEEE Computational Intelligence Magazine - August 2021 - 44
IEEE Computational Intelligence Magazine - August 2021 - 45
IEEE Computational Intelligence Magazine - August 2021 - 46
IEEE Computational Intelligence Magazine - August 2021 - 47
IEEE Computational Intelligence Magazine - August 2021 - 48
IEEE Computational Intelligence Magazine - August 2021 - 49
IEEE Computational Intelligence Magazine - August 2021 - 50
IEEE Computational Intelligence Magazine - August 2021 - 51
IEEE Computational Intelligence Magazine - August 2021 - 52
IEEE Computational Intelligence Magazine - August 2021 - 53
IEEE Computational Intelligence Magazine - August 2021 - 54
IEEE Computational Intelligence Magazine - August 2021 - 55
IEEE Computational Intelligence Magazine - August 2021 - 56
IEEE Computational Intelligence Magazine - August 2021 - 57
IEEE Computational Intelligence Magazine - August 2021 - 58
IEEE Computational Intelligence Magazine - August 2021 - 59
IEEE Computational Intelligence Magazine - August 2021 - 60
IEEE Computational Intelligence Magazine - August 2021 - 61
IEEE Computational Intelligence Magazine - August 2021 - 62
IEEE Computational Intelligence Magazine - August 2021 - 63
IEEE Computational Intelligence Magazine - August 2021 - 64
IEEE Computational Intelligence Magazine - August 2021 - 65
IEEE Computational Intelligence Magazine - August 2021 - 66
IEEE Computational Intelligence Magazine - August 2021 - 67
IEEE Computational Intelligence Magazine - August 2021 - 68
IEEE Computational Intelligence Magazine - August 2021 - 69
IEEE Computational Intelligence Magazine - August 2021 - 70
IEEE Computational Intelligence Magazine - August 2021 - 71
IEEE Computational Intelligence Magazine - August 2021 - 72
IEEE Computational Intelligence Magazine - August 2021 - 73
IEEE Computational Intelligence Magazine - August 2021 - 74
IEEE Computational Intelligence Magazine - August 2021 - 75
IEEE Computational Intelligence Magazine - August 2021 - 76
IEEE Computational Intelligence Magazine - August 2021 - 77
IEEE Computational Intelligence Magazine - August 2021 - 78
IEEE Computational Intelligence Magazine - August 2021 - 79
IEEE Computational Intelligence Magazine - August 2021 - 80
IEEE Computational Intelligence Magazine - August 2021 - 81
IEEE Computational Intelligence Magazine - August 2021 - 82
IEEE Computational Intelligence Magazine - August 2021 - 83
IEEE Computational Intelligence Magazine - August 2021 - 84
IEEE Computational Intelligence Magazine - August 2021 - 85
IEEE Computational Intelligence Magazine - August 2021 - 86
IEEE Computational Intelligence Magazine - August 2021 - 87
IEEE Computational Intelligence Magazine - August 2021 - 88
IEEE Computational Intelligence Magazine - August 2021 - 89
IEEE Computational Intelligence Magazine - August 2021 - 90
IEEE Computational Intelligence Magazine - August 2021 - 91
IEEE Computational Intelligence Magazine - August 2021 - 92
IEEE Computational Intelligence Magazine - August 2021 - 93
IEEE Computational Intelligence Magazine - August 2021 - 94
IEEE Computational Intelligence Magazine - August 2021 - 95
IEEE Computational Intelligence Magazine - August 2021 - 96
IEEE Computational Intelligence Magazine - August 2021 - Cover3
IEEE Computational Intelligence Magazine - August 2021 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202311
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202308
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202305
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202302
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202211
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202208
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202205
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202202
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202111
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202108
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202105
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202102
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202011
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202008
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202005
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202002
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201911
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201908
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201905
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201902
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201811
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201808
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201805
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201802
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter12
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall12
https://www.nxtbookmedia.com