際際滷

際際滷Share a Scribd company logo
Learning how to explain neural networks
PatternNet and PatternAttribution
PJ Kindermans et al. 2017
蠏觜

螻る蟲 一蟆曙螻牛螻

Data Science & Business Analytics 郁規
/ 29
覈谿
1. 螻手碓 覦覯襦れ 覦 覓語
2. 螻手碓 覦覯襦 覿
1) DeConvNet
2) Guided BackProp
3. Linear model 蟲
1) Deterministic distractor
2) Additive isotropic Gaussian noise
4. Approaches
5. Quality criterion for signal estimator
6. Learning to estimate signal
1) Existing estimators
2) PatternNet & PatternAttribution
7. Experiments
2
/ 29
0. 
Data 譴 覩碁ゼ 願  Signal螻 碁 覿覿 Distractor襦 蟲焔.
螳襯 る Signal 覿覿 譴 伎 .
Model weight Distractor レ 襷 覦蠍 覓語
螳襯   weight襷 譟危覃 譬讌  蟆郁骸襯 碁.
output y distractor correlation朱 signal 讌 , 螳  .
豢覿 給 覈語 { weight, input, output } 螳朱 linear, non-linear
 覦朱 signal 蟲  螻,  蠏碁襦 螳.
3
/ 29
1. 螻手碓 覦覯襦れ 覓語
Deep learning る蠍  れ れ 伎
DeConvNet, Guided BackProp, LRP(Layer-wise Relevance Propagation)
 覈碁れ 譯殊 螳 譴 覲願 豢 Output る Backpropagation 
覃 input 譴 覲企れ 企至 豢伎讌   る 蟆
4
/ 29
1. 螻手碓 覦覯襦れ 覓語(Contd)
讌襷 螻手碓 覦覯襦れ 豢豢 saliency mapれ 蟆朱 蠏碁伎誤企慨,
企朱 覯渚蟆 input data 譴 覿覿れ 豢豢讌 覈詩
Data Signal螻 Distractor  螳讌襦 蟲覿  
Relevant signal: Data襯 企 譴 覿覿, 旧 伎
Distracting component: Data 蟯螻 noise
Signal  Distractor 蟆 譬讌一 Weight vector襦 覈語 る
朱朱 Deep learning model  殊 Data Distractor襯 蟇壱 蟆
∬係 weight vector襯 filter手 覿襯碁
5
- Distractor direction
磯 weight vector
direction 襷蟲 覲
蟆 覲  
- Weight vector 
distractor 蟇一企襦
轟壱
/ 29
2.1 螻手碓 覦覯襦 - DeConvNet by Zeiler & Fergus
DeconvNet 伎蟾讌
input layer 覦襦 襷酔 豌 覯讌 layer 螻殊 伎襷 る蟇磯 -> る 覿譟
Hessian matrix襯 伎伎 るジ layer 螻朱 る
-> layer襯 願襦 覲旧″伎蠍 覓語 quadratic approximation朱 螻螳 
譯殊 貉
Gradient descent襯  轟 neuron 燕る input space  谿剰鍵
∬ 襷ル曙 觜訣 郁規 譟伎
Simonyan et al. -> fully connected layer saliency map 谿城 郁規
Girchick et al. -> image 企 patch螳 filter襯 activation る讌 谿剰鍵
6
(1) Adaptive Deconvolutional Networks for Mid and High Level Feature Learning - Matthew D. Zeiler and Rob Fergus, 2011

(2) Visualizing and Understanding Convolutioinal Networks - Matthew D. Zeiler and Rob Fergus, 2014
/ 29
2.1 螻手碓 覦覯襦 - DeConvNet by Zeiler & Fergus (Contd)
 ろ語 蟲譟(AlexNet)
1. 螳 layerれ Convolution layer襦 蟲焔 
2. Convolution layer れ  ReLU 覿
3. (Optionally) Max pooling layer 
DeConvNet 谿
1. image襯 蠍一ヾ 給 ConvNet model(一検) 糾骸
2. 危エ覲 feature map 螻,
るジ 覈 feature mapれ 0朱 襷 れ,
DeConvNet layer(譬豸) 糾骸
(i) Unpool
(ii) Rectify
(iii)Reconstruction
7
(1) Adaptive Deconvolutional Networks for Mid and High Level Feature Learning - Matthew D. Zeiler and Rob Fergus, 2011

(2) Visualizing and Understanding Convolutioinal Networks - Matthew D. Zeiler and Rob Fergus, 2014
/ 29
2.1 螻手碓 覦覯襦 - DeConvNet by Zeiler & Fergus (Contd)
Unpooling
Max pooling non-invertible -> Approximation
∬係 pooling  襷 企 layer 豕螳
豺襯 record企螻, DeConvNet Switch
覦 .
Rectification
ReLU襯 蠍 覓語 feature map  0 伎
DeConvNet  螳 襷り鍵  ReLU 糾骸
Convolutional Filtering(Reconstruction)
∬鍵譟 learned conv filter襯 vertically, horizontally
flip貅 (transposed)
 螳 activation襷 BackPropる 蟆螻 螳 覩
8
(1) Adaptive Deconvolutional Networks for Mid and High Level Feature Learning - Matthew D. Zeiler and Rob Fergus, 2011

(2) Visualizing and Understanding Convolutioinal Networks - Matthew D. Zeiler and Rob Fergus, 2014
< 朱(1) figure >
< from towardsdatascience.com >
/ 29
2.1 螻手碓 覦覯襦 - DeConvNet by Zeiler & Fergus (Contd)
Occlusion Sensitivity test
轟 覿覿  襦 螳襴
企 覿覿 螳れ 
(b) total activation 覲
(d) probability score 覲
(e) most probable class 覲
(c) projection 蟆郁骸
∬ 襴 企 企語
るジ 3螳 るジ 企語 

伎: Convolution filter螳
企語 轟 覿覿(螳豌)
 ′願 . 9
/ 29
2.2 螻手碓 覦覯襦 - Guided BackProp by Springenberg
企 朱語 覈
襦 覈語 螳覦  れ 覯伎る 狩 蠑 覲旧″伎瑚螻 .
ろ語襯 蟲燕  譴 豕螻 焔レ 企  螳 譴 覿覿 覓伎殊 谿場覲伎
覈 螳 覦覯 deconvolution approach(Guided BackProp)
朱語 蟆磯
Convolution layer襷朱 覈 ろ語襯 蟲
max-pooling layer襯 一 襷螻 -> Strided convolution layer (stride 2, 3x3 filter)
10(3) Striving for Simplicity: The All Convolutional Net - Jost Tobias Springenberg et al. 2014
/ 29
2.2 螻手碓 覦覯襦 - Guided BackProp by Springenberg(Contd)
Max-pooling Strided Convolution layer襦 豌危   伎
Pooling equation
Convolution equation
=> pooling, convolution  覈 螳 input 覦朱謂
pooling activation function p-norm  蟆螻 螳.
11(3) Striving for Simplicity: The All Convolutional Net - Jost Tobias Springenberg et al. 2014
si,j,u(f ) = (
k/2

h=k/2
k/2

w=k/2
| fg(h,w,i,j,u) |p
)1/p
Notation
 f : feature map
 W,H : width, height
 N : Number of channels
 k : pooling size
 r : stride
 g(h,w,i,j,u) = (r*i + h,
r*j + w, u)
 p : order of p-norm,
p螳 覓危朱 螳 
max-pooling螻 螳 覩
 theta : convolutional
weight
 sigma : activation function
 o : # of output channel
ci,j,o(f ) = (
k/2

h=k/2
k/2

w=k/2
N

u=1
慮h,w,u,o  fg(h,w,i,j,u))
/ 29
2.2 螻手碓 覦覯襦 - Guided BackProp by Springenberg(Contd)
ろ 觜蟲 ろ語 譬襯
A, B, C : Convolutional filter size螳 る
C 3螳讌 襦 譬  れ: 麹 一検 觜螳   覈 觜蟲
12(3) Striving for Simplicity: The All Convolutional Net - Jost Tobias Springenberg et al. 2014
螳 一
/ 29
2.2 螻手碓 覦覯襦 - Guided BackProp by Springenberg(Contd)
All-CNN-C 覈語 Deconvolution 覦朱 螳
讌 螳 Zeiler & Fergus(2014) Deconvolution 覦覯
企 覈語 Max-Pooling layer螳 伎 焔レ 譬讌 蟆 
Guided BackProp
Convolution layer襷 蠍 覓語 switch 
Activation 螳 0 伎願, Gradient 0 伎 蟆襷 
a) Zeiler&Fergus(2014)
13
/ 29
2.3 螻手碓 覦覯襦 - Weight vector襷 讌譴
DeConvNet, Guided BackProp 覦覯 覈
Weight(Conv filter) 一 蟆郁骸 蟯
Weight螳 Data Signal 磯手讌 朱襦 企 覦覯れ
Data 譴 覿覿 ′伎 覈詩  
14
/ 29
3.1  Linear Model 蟲 - Deterministic distractor
 Linear model 牛 signal螻 distractor 讌 蟯谿
15
Notation
 w : filter or weight
 x : data
 y : condensed output
 s : relevant signal
 d : distracting component.
 output  覓企
覲企 螳讌螻 讌  覿覿
 a_s : direction of signal.
 output 殊 覈
 a_d : direction of distractor
s = asyx = s + d
d = ad狼
as = (1,0)T
ad = (1,1)T
y  [1,1]
狼  (亮, 2
)
Data x  signal s distractor d 
   襷譟燕蠍 伎
 願, 伎伎 蠍 覓
wT
x = y w = [1,  1]T
wT
asy = y wT
ad狼 = 0
/ 29
3.1  Linear Model 蟲 - Deterministic distractor
16
,   覈襯 豢譟煙貅 
weight distractor襯 蟇壱伎狩蠍 覓語 distractor direction螻 orthogonal り 
讀 w signal direction螻 align讌 .
weight distractor orthogonal  讌覃伎,
蠍 譟一 牛  讌 .
Weight vector distractor  蟆 譬讌一 
weight vector襷朱 企 input pattern output レ 殊讌   
wT
asy = y wT
ad狼 = 0
- signal direction 蠏碁襦 讌
- distractor direction 覦
weight direction  覦
wT
as = 1
/ 29
3.2  Linear Model 蟲 - No distractor, Additive isotropic Gaussian noise
17
Isotropic Gaussian noise襯  伎
zero mean: noise mean bias襯 牛 朱
讌   朱襦  0朱 .
correlation企 structure螳 蠍 覓語
weight vector襯  牛り 伎
noise螳 蟇磯讌 .
Gaussian noise襯 豢螳 蟆
L2 regularization螻 螳 螻朱ゼ 碁.
讀 weight襯 shirink .
 譟郁唄 覓語  襷譟燕
螳  weight vector
 螳 覦レ vector
< Gaussian pattern >
yn = 硫xn + 狼
N

n=1
(yn |硫xn, 2
)
N

n=1
(yn |硫xn, 2
)(硫|0,了1
)
N

n=1

1
2
(yn  硫xn)2
 了硫2
+ const
< Gaussian noise & L2 regularization >
> likelihood,
皙 Logarithm
wT
as = 1
as
as
w
w霞
w
1
/ 29
4. Approaches
18
Functions
data x output y襯 觸  磯 覦覯. ex) gradients, saliency map
y襯 x襦 覩碁伎 input 覲螳 企至 output 覲蟆讌 危エ覲碁.
企 model gradient襯 磯 蟆願 蟆郁記  gradient weight.
Signal
Signal: 覈語 neuron activate る 一危一 蟲 
Output input space蟾讌 gradient襯 backprop貅 覲 蟯谿
DeConvNet, Guded BackProp  蟆 signal企 覲伎 覈詩.
Attribution
轟 Signal 朱 output 蠍一讌 企 讌
Linear model signal螻 weight vector element-wise 螻煙朱 伎伎
Deep taylor decomposition 朱語 activation 螳 input 
contribution朱 覿危螻, LRP relevance 豺.
y = wT
x
y/x = w
PatternNet
PatternAttribution
/ 29
5. Quality criterion for signal estimator
19
伎  
wT
x = y
wT
s + wT
d = y
(x = s + d)wT
(s + d) = y
wT
s = y (wT
d = 0)
(wT
)1
wT
s = (wT
)1
y
s = uu1
(wT
)1
y
s = u(wT
u)1
y
u = random vector
(wT
u  0)
Quality measure 
S(x) = s
(S) = 1  maxvcorr(wT
x, vT
(x  S(x)))
d = x  S(x) y = wT
x, ,
= 1  maxv
vT
cov[y, d]
2
vT d
2
y
譬 signal estimator correlation 0朱 -> 
w 企  給 覈語 weight 螳
correlation scale invariant 蠍 覓語
 覿一  覿郁骸 螳 蟆企 曙^蟇 豢螳
S(x)襯 螻り optimal 襯 谿城謂
 覦 d y  Least-squares regression

vT d y
v
illposed problem.
企襦 襴讌 .
るジ 覦
/ 29
6.1 蠍一ヾ Signal estimator 覦
20
The identity estimator
data distractor , signal襷 譟伎 螳
data螳 企語  signal 企語 蠏碁襦企.
 linear model  attribution 蟲 .
(distractor螳 譟伎朱, attribution )
れ 一危一 distractor螳   螻,
forward pass 蟇磯讌襷
backward pass element wise 螻煙  讌
螳 noise螳 襷 覲伎碁(LRP)
Sx(x) = x
r = w  x = w  s + w  d
The filter based estimator
∬豸° signal weight direction  螳
ex) DeConvNet, Guided BackProp
weight normalize 伎 
linear model  attribution 螻旧 れ螻 螳螻
signal  襦 蟲燕讌 覈詩
Sw(x) =
w
wTw
wT
x
r =
w  w
wTw
y
/ 29
6.2 PatternNet & PatternAttribution
21
 覦 覦 螳
 criterion 豕 給逢
覈 螳ロ 覯″  y d correlation 0 
signal estimator S螳 optimal企   .
Linear model  y d covariance 0企
cov[y, x]  cov[y, S(x)] = 0

v
cov[y, x] = cov[y, S(x)]
cov[y, d] = 0
(S) = 1  maxvcorr(wT
x, vT
(x  S(x)))
= 1  maxv
vT
cov[y, d]
2
vT d
2
y
Quality measure
/ 29
6.2 PatternNet & PatternAttribution
22
The linear estimator
linear neuron data x linear signal襷 豢豢 螳
 豌 y linear 一一   signal 
linear model  y, d covariance 0企襦
Sa(x) = awT
x = ay
cov[x, y]
= cov[S(x), y]
= cov[awT
x, y]
= a  cov[y, y]
 a =
cov[x, y]
2
y
襷 d s螳 orthogonal る
DeConvNet螻 螳 filter-based 覦
螻 殊.
Convolution layer 襷れ  
FC layer ReLU螳 郁屋伎 覿覿
 correlation  蟇壱  
朱襦  豌 criterion 豺 
VGG16

criterion 觜蟲

襷蠏碁 襦

random, S_w,
S_a, S_a+-
/ 29
6.2 PatternNet & PatternAttribution
23
The two-component(Non-linear) estimator
 linear estimator 螳 trick 一襷
y 螳 覿語 磯 螳螳 るゴ蟆 豌襴.
企一 燕伎讌 覿  覲企
distractor 譟伎 y螳  覿覿 螻 
ReLU 覓語 れ positive domain襷
locally 一危 蠍 覓語 企ゼ 覲伎
covariance 螻旧 れ螻 螳螻
覿語 磯 磯 螻, 螳譴豺襦 .
Sa+(x) =
{
a+w
x if油w
x > 0
aw
x otherwise
x =
{
s+ + d+ if油y > 0
s + d otherwise
cov(x, y) = [xy]  [x][y]
cov(x, y) = +(+[xy]  +[x][y])
+(1  +)(錫[xy]  錫[x][y])
cov(s, y) = +(+[sy]  +[s][y])
+(1  +)(錫[sy]  錫[s][y])
cov(x,y), cov(s,y)螳 殊 ,  覿語  覃
a+ =
+[xy]  +[x][y]
w +[xy]  w +[x][y]
/ 29
6.2 PatternNet & PatternAttribution
24
PatternNet and PatternAttribution
/ 29
6.2 PatternNet & PatternAttribution
25
PatternNet and PatternAttribution
PatternNet, Linear
cov[x,y], cov[s,y]螳 螳
a襯 螻壱  x, y襦襷 螻 螳
PatternNet, Non-linear
ReLU activation 轟 螻
/  a 螳 螻
Non-linear 覈語 焔 譬
PatternAttribution
a 螳 w襯 element-wise 螻燕 蟆郁骸襦
伎蠍  譬  蟾
heat map 燕  . r = w  a+
a =
cov[x, y]
2
y
a+ =
+[xy]  +[x][y]
w +[xy]  w +[x][y]
/ 29
7. Experiments
26
螳 觜蟲, VGG16 on ImageNet(S)
Convolution layer
覲 朱語  linear estimator螳 覃伎 譬 焔レ 覲伎願 
覲 朱語 non-linear estimator  るジ filter-based, random 覲企 燕 焔
FC layer with ReLU
覲 朱語 linear estimator 焔 蠍蟆 伎
non-linear estimator 焔 讌
/ 29
7. Experiments
27
Qualitative evaluation
轟 企語  レ  觜蟲 伎
Methods 蟲覿
Sx : Identity estimator
Sw : DeConvNet, Guided BackProp
Sa : Linear
Sa+- : Non-linear
一検朱 螳 襦 譬  structure襯錫
誤螻 碁蟆 ′碁.
/ 29
7. Experiments
28
/ 2929
螳.
PatternNet & PatternAttribution

More Related Content

What's hot (20)

neural network 蠍一
neural network 蠍一neural network 蠍一
neural network 蠍一
Dea-hwan Ki
[貉危磯螻 瑚概讌] 5. 蟆暑
[貉危磯螻 瑚概讌] 5. 蟆暑[貉危磯螻 瑚概讌] 5. 蟆暑
[貉危磯螻 瑚概讌] 5. 蟆暑
jdo
Coursera Machine Learning (by Andrew Ng)_螳襴
Coursera Machine Learning (by Andrew Ng)_螳襴Coursera Machine Learning (by Andrew Ng)_螳襴
Coursera Machine Learning (by Andrew Ng)_螳襴
SANG WON PARK
堝朱-蠏覿覲仰
堝朱-蠏覿覲仰堝朱-蠏覿覲仰
堝朱-蠏覿覲仰
jdo
[貉危磯螻 瑚概讌] 6. 2
[貉危磯螻 瑚概讌] 6.  2[貉危磯螻 瑚概讌] 6.  2
[貉危磯螻 瑚概讌] 6. 2
jdo
[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 5 - Others
 [貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 5 - Others [貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 5 - Others
[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 5 - Others
jdo
Lecture 4: Neural Networks I
Lecture 4: Neural Networks ILecture 4: Neural Networks I
Lecture 4: Neural Networks I
Sang Jun Lee
From maching learning to deep learning episode2
From maching learning to deep learning episode2 From maching learning to deep learning episode2
From maching learning to deep learning episode2
Yongdae Kim
Energy based models and boltzmann machines
Energy based models and boltzmann machinesEnergy based models and boltzmann machines
Energy based models and boltzmann machines
Soowan Lee
Lecture 3: Unsupervised Learning
Lecture 3: Unsupervised LearningLecture 3: Unsupervised Learning
Lecture 3: Unsupervised Learning
Sang Jun Lee
-覓朱Μろ 覈碁
-覓朱Μろ 覈碁-覓朱Μろ 覈碁
-覓朱Μろ 覈碁
jdo
Deep neural networks cnn rnn_ae_some practical techniques
Deep neural networks cnn rnn_ae_some practical techniquesDeep neural networks cnn rnn_ae_some practical techniques
Deep neural networks cnn rnn_ae_some practical techniques
Kang Pilsung
Recurrent Neural Net 企螻 る
Recurrent Neural Net 企螻 るRecurrent Neural Net 企螻 る
Recurrent Neural Net 企螻 る
覦 蟾
願 危危 SVM(, 企至襯 譴朱)
願 危危 SVM(, 企至襯 譴朱)願 危危 SVM(, 企至襯 譴朱)
願 危危 SVM(, 企至襯 譴朱)
SANG WON PARK
Visualizing data using t-SNE
Visualizing data using t-SNEVisualizing data using t-SNE
Visualizing data using t-SNE
覦 蟾
[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 1 - る
[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 1 - る[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 1 - る
[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 1 - る
jdo
ル 蠍磯蓋 襴 危
ル 蠍磯蓋 襴 危ル 蠍磯蓋 襴 危
ル 蠍磯蓋 襴 危
Hee Won Park
HistoryOfCNN
HistoryOfCNNHistoryOfCNN
HistoryOfCNN
Tae Young Lee
Chapter 7 Regularization for deep learning - 3
Chapter 7 Regularization for deep learning - 3Chapter 7 Regularization for deep learning - 3
Chapter 7 Regularization for deep learning - 3
KyeongUkJang
襾誤殊 襾語 : Gaussian Processes
襾誤殊 襾語 : Gaussian Processes襾誤殊 襾語 : Gaussian Processes
襾誤殊 襾語 : Gaussian Processes
Jungkyu Lee
neural network 蠍一
neural network 蠍一neural network 蠍一
neural network 蠍一
Dea-hwan Ki
[貉危磯螻 瑚概讌] 5. 蟆暑
[貉危磯螻 瑚概讌] 5. 蟆暑[貉危磯螻 瑚概讌] 5. 蟆暑
[貉危磯螻 瑚概讌] 5. 蟆暑
jdo
Coursera Machine Learning (by Andrew Ng)_螳襴
Coursera Machine Learning (by Andrew Ng)_螳襴Coursera Machine Learning (by Andrew Ng)_螳襴
Coursera Machine Learning (by Andrew Ng)_螳襴
SANG WON PARK
堝朱-蠏覿覲仰
堝朱-蠏覿覲仰堝朱-蠏覿覲仰
堝朱-蠏覿覲仰
jdo
[貉危磯螻 瑚概讌] 6. 2
[貉危磯螻 瑚概讌] 6.  2[貉危磯螻 瑚概讌] 6.  2
[貉危磯螻 瑚概讌] 6. 2
jdo
[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 5 - Others
 [貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 5 - Others [貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 5 - Others
[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 5 - Others
jdo
Lecture 4: Neural Networks I
Lecture 4: Neural Networks ILecture 4: Neural Networks I
Lecture 4: Neural Networks I
Sang Jun Lee
From maching learning to deep learning episode2
From maching learning to deep learning episode2 From maching learning to deep learning episode2
From maching learning to deep learning episode2
Yongdae Kim
Energy based models and boltzmann machines
Energy based models and boltzmann machinesEnergy based models and boltzmann machines
Energy based models and boltzmann machines
Soowan Lee
Lecture 3: Unsupervised Learning
Lecture 3: Unsupervised LearningLecture 3: Unsupervised Learning
Lecture 3: Unsupervised Learning
Sang Jun Lee
-覓朱Μろ 覈碁
-覓朱Μろ 覈碁-覓朱Μろ 覈碁
-覓朱Μろ 覈碁
jdo
Deep neural networks cnn rnn_ae_some practical techniques
Deep neural networks cnn rnn_ae_some practical techniquesDeep neural networks cnn rnn_ae_some practical techniques
Deep neural networks cnn rnn_ae_some practical techniques
Kang Pilsung
Recurrent Neural Net 企螻 る
Recurrent Neural Net 企螻 るRecurrent Neural Net 企螻 る
Recurrent Neural Net 企螻 る
覦 蟾
願 危危 SVM(, 企至襯 譴朱)
願 危危 SVM(, 企至襯 譴朱)願 危危 SVM(, 企至襯 譴朱)
願 危危 SVM(, 企至襯 譴朱)
SANG WON PARK
Visualizing data using t-SNE
Visualizing data using t-SNEVisualizing data using t-SNE
Visualizing data using t-SNE
覦 蟾
[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 1 - る
[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 1 - る[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 1 - る
[貉危磯螻 瑚概讌] 8. 炎咳 蟆暑 ろ豌 1 - る
jdo
ル 蠍磯蓋 襴 危
ル 蠍磯蓋 襴 危ル 蠍磯蓋 襴 危
ル 蠍磯蓋 襴 危
Hee Won Park
Chapter 7 Regularization for deep learning - 3
Chapter 7 Regularization for deep learning - 3Chapter 7 Regularization for deep learning - 3
Chapter 7 Regularization for deep learning - 3
KyeongUkJang
襾誤殊 襾語 : Gaussian Processes
襾誤殊 襾語 : Gaussian Processes襾誤殊 襾語 : Gaussian Processes
襾誤殊 襾語 : Gaussian Processes
Jungkyu Lee

Similar to Learning how to explain neural networks: PatternNet and PatternAttribution (20)

SAGAN_2024seminar announce_seoultech.pptx
SAGAN_2024seminar announce_seoultech.pptxSAGAN_2024seminar announce_seoultech.pptx
SAGAN_2024seminar announce_seoultech.pptx
ssuser4b2fe7
Guided policy search
Guided policy searchGuided policy search
Guided policy search
Jaehyeon Park
PR12 Season3 Weight Agnostic Neural Networks
PR12 Season3 Weight Agnostic Neural NetworksPR12 Season3 Weight Agnostic Neural Networks
PR12 Season3 Weight Agnostic Neural Networks
Kyunghoon Jung
The fastalgorithmfordeepbeliefnets
The fastalgorithmfordeepbeliefnetsThe fastalgorithmfordeepbeliefnets
The fastalgorithmfordeepbeliefnets
Lee Gyeong Hoon
Denoising auto encoders(d a)
Denoising auto encoders(d a)Denoising auto encoders(d a)
Denoising auto encoders(d a)
Tae Young Lee
Convolutional neural networks
Convolutional neural networksConvolutional neural networks
Convolutional neural networks
HyunjinBae3
History of Vision AI
History of Vision AIHistory of Vision AI
History of Vision AI
Tae Young Lee
Densely Connected Convolutional Networks
Densely Connected Convolutional NetworksDensely Connected Convolutional Networks
Densely Connected Convolutional Networks
Oh Yoojin
[paper review] 蠏觜 - Eye in the sky & 3D human pose estimation in video with ...
[paper review] 蠏觜 - Eye in the sky & 3D human pose estimation in video with ...[paper review] 蠏觜 - Eye in the sky & 3D human pose estimation in video with ...
[paper review] 蠏觜 - Eye in the sky & 3D human pose estimation in video with ...
Gyubin Son
Survey on Monocular Depth Estimation
Survey on Monocular Depth EstimationSurvey on Monocular Depth Estimation
Survey on Monocular Depth Estimation
覯譴 蟾
Progressive Growing of GANs for Improved Quality, Stability, and Variation Re...
Progressive Growing of GANs for Improved Quality, Stability, and Variation Re...Progressive Growing of GANs for Improved Quality, Stability, and Variation Re...
Progressive Growing of GANs for Improved Quality, Stability, and Variation Re...
Chapter 8 - optimization for training deep models
Chapter 8 - optimization for training deep modelsChapter 8 - optimization for training deep models
Chapter 8 - optimization for training deep models
KyeongUkJang
Deep learning overview
Deep learning overviewDeep learning overview
Deep learning overview
螳覩手記 螳覩手記
3.unsupervised learing(epoch#2)
3.unsupervised learing(epoch#2)3.unsupervised learing(epoch#2)
3.unsupervised learing(epoch#2)
Haesun Park
[蟆暑蠍一] 豸旧蟆暑螳
[蟆暑蠍一] 豸旧蟆暑螳[蟆暑蠍一] 豸旧蟆暑螳
[蟆暑蠍一] 豸旧蟆暑螳
jaypi Ko
[ 襾語 ろ磯 - 語 襾語] 5. 覯″ 襾語
[ 襾語 ろ磯 - 語 襾語] 5.  覯″ 襾語[ 襾語 ろ磯 - 語 襾語] 5.  覯″ 襾語
[ 襾語 ろ磯 - 語 襾語] 5. 覯″ 襾語
Haesun Park
Chapter 6 Deep feedforward networks - 2
Chapter 6 Deep feedforward networks - 2Chapter 6 Deep feedforward networks - 2
Chapter 6 Deep feedforward networks - 2
KyeongUkJang
"simple does it weakly supervised instance and semantic segmentation" Paper r...
"simple does it weakly supervised instance and semantic segmentation" Paper r..."simple does it weakly supervised instance and semantic segmentation" Paper r...
"simple does it weakly supervised instance and semantic segmentation" Paper r...
LEE HOSEONG
瑚概讌, 蠍郁 蠏碁Μ螻 ル
瑚概讌, 蠍郁 蠏碁Μ螻 ル瑚概讌, 蠍郁 蠏碁Μ螻 ル
瑚概讌, 蠍郁 蠏碁Μ螻 ル
Jinwon Lee
Dense sparse-dense training for dnn and Other Models
Dense sparse-dense training for dnn and Other ModelsDense sparse-dense training for dnn and Other Models
Dense sparse-dense training for dnn and Other Models
Dong Heon Cho
SAGAN_2024seminar announce_seoultech.pptx
SAGAN_2024seminar announce_seoultech.pptxSAGAN_2024seminar announce_seoultech.pptx
SAGAN_2024seminar announce_seoultech.pptx
ssuser4b2fe7
Guided policy search
Guided policy searchGuided policy search
Guided policy search
Jaehyeon Park
PR12 Season3 Weight Agnostic Neural Networks
PR12 Season3 Weight Agnostic Neural NetworksPR12 Season3 Weight Agnostic Neural Networks
PR12 Season3 Weight Agnostic Neural Networks
Kyunghoon Jung
The fastalgorithmfordeepbeliefnets
The fastalgorithmfordeepbeliefnetsThe fastalgorithmfordeepbeliefnets
The fastalgorithmfordeepbeliefnets
Lee Gyeong Hoon
Denoising auto encoders(d a)
Denoising auto encoders(d a)Denoising auto encoders(d a)
Denoising auto encoders(d a)
Tae Young Lee
Convolutional neural networks
Convolutional neural networksConvolutional neural networks
Convolutional neural networks
HyunjinBae3
History of Vision AI
History of Vision AIHistory of Vision AI
History of Vision AI
Tae Young Lee
Densely Connected Convolutional Networks
Densely Connected Convolutional NetworksDensely Connected Convolutional Networks
Densely Connected Convolutional Networks
Oh Yoojin
[paper review] 蠏觜 - Eye in the sky & 3D human pose estimation in video with ...
[paper review] 蠏觜 - Eye in the sky & 3D human pose estimation in video with ...[paper review] 蠏觜 - Eye in the sky & 3D human pose estimation in video with ...
[paper review] 蠏觜 - Eye in the sky & 3D human pose estimation in video with ...
Gyubin Son
Survey on Monocular Depth Estimation
Survey on Monocular Depth EstimationSurvey on Monocular Depth Estimation
Survey on Monocular Depth Estimation
覯譴 蟾
Progressive Growing of GANs for Improved Quality, Stability, and Variation Re...
Progressive Growing of GANs for Improved Quality, Stability, and Variation Re...Progressive Growing of GANs for Improved Quality, Stability, and Variation Re...
Progressive Growing of GANs for Improved Quality, Stability, and Variation Re...
Chapter 8 - optimization for training deep models
Chapter 8 - optimization for training deep modelsChapter 8 - optimization for training deep models
Chapter 8 - optimization for training deep models
KyeongUkJang
3.unsupervised learing(epoch#2)
3.unsupervised learing(epoch#2)3.unsupervised learing(epoch#2)
3.unsupervised learing(epoch#2)
Haesun Park
[蟆暑蠍一] 豸旧蟆暑螳
[蟆暑蠍一] 豸旧蟆暑螳[蟆暑蠍一] 豸旧蟆暑螳
[蟆暑蠍一] 豸旧蟆暑螳
jaypi Ko
[ 襾語 ろ磯 - 語 襾語] 5. 覯″ 襾語
[ 襾語 ろ磯 - 語 襾語] 5.  覯″ 襾語[ 襾語 ろ磯 - 語 襾語] 5.  覯″ 襾語
[ 襾語 ろ磯 - 語 襾語] 5. 覯″ 襾語
Haesun Park
Chapter 6 Deep feedforward networks - 2
Chapter 6 Deep feedforward networks - 2Chapter 6 Deep feedforward networks - 2
Chapter 6 Deep feedforward networks - 2
KyeongUkJang
"simple does it weakly supervised instance and semantic segmentation" Paper r...
"simple does it weakly supervised instance and semantic segmentation" Paper r..."simple does it weakly supervised instance and semantic segmentation" Paper r...
"simple does it weakly supervised instance and semantic segmentation" Paper r...
LEE HOSEONG
瑚概讌, 蠍郁 蠏碁Μ螻 ル
瑚概讌, 蠍郁 蠏碁Μ螻 ル瑚概讌, 蠍郁 蠏碁Μ螻 ル
瑚概讌, 蠍郁 蠏碁Μ螻 ル
Jinwon Lee
Dense sparse-dense training for dnn and Other Models
Dense sparse-dense training for dnn and Other ModelsDense sparse-dense training for dnn and Other Models
Dense sparse-dense training for dnn and Other Models
Dong Heon Cho

Learning how to explain neural networks: PatternNet and PatternAttribution

  • 1. Learning how to explain neural networks PatternNet and PatternAttribution PJ Kindermans et al. 2017 蠏觜 螻る蟲 一蟆曙螻牛螻 Data Science & Business Analytics 郁規
  • 2. / 29 覈谿 1. 螻手碓 覦覯襦れ 覦 覓語 2. 螻手碓 覦覯襦 覿 1) DeConvNet 2) Guided BackProp 3. Linear model 蟲 1) Deterministic distractor 2) Additive isotropic Gaussian noise 4. Approaches 5. Quality criterion for signal estimator 6. Learning to estimate signal 1) Existing estimators 2) PatternNet & PatternAttribution 7. Experiments 2
  • 3. / 29 0. Data 譴 覩碁ゼ 願 Signal螻 碁 覿覿 Distractor襦 蟲焔. 螳襯 る Signal 覿覿 譴 伎 . Model weight Distractor レ 襷 覦蠍 覓語 螳襯 weight襷 譟危覃 譬讌 蟆郁骸襯 碁. output y distractor correlation朱 signal 讌 , 螳 . 豢覿 給 覈語 { weight, input, output } 螳朱 linear, non-linear 覦朱 signal 蟲 螻, 蠏碁襦 螳. 3
  • 4. / 29 1. 螻手碓 覦覯襦れ 覓語 Deep learning る蠍 れ れ 伎 DeConvNet, Guided BackProp, LRP(Layer-wise Relevance Propagation) 覈碁れ 譯殊 螳 譴 覲願 豢 Output る Backpropagation 覃 input 譴 覲企れ 企至 豢伎讌 る 蟆 4
  • 5. / 29 1. 螻手碓 覦覯襦れ 覓語(Contd) 讌襷 螻手碓 覦覯襦れ 豢豢 saliency mapれ 蟆朱 蠏碁伎誤企慨, 企朱 覯渚蟆 input data 譴 覿覿れ 豢豢讌 覈詩 Data Signal螻 Distractor 螳讌襦 蟲覿 Relevant signal: Data襯 企 譴 覿覿, 旧 伎 Distracting component: Data 蟯螻 noise Signal Distractor 蟆 譬讌一 Weight vector襦 覈語 る 朱朱 Deep learning model 殊 Data Distractor襯 蟇壱 蟆 ∬係 weight vector襯 filter手 覿襯碁 5 - Distractor direction 磯 weight vector direction 襷蟲 覲 蟆 覲 - Weight vector distractor 蟇一企襦 轟壱
  • 6. / 29 2.1 螻手碓 覦覯襦 - DeConvNet by Zeiler & Fergus DeconvNet 伎蟾讌 input layer 覦襦 襷酔 豌 覯讌 layer 螻殊 伎襷 る蟇磯 -> る 覿譟 Hessian matrix襯 伎伎 るジ layer 螻朱 る -> layer襯 願襦 覲旧″伎蠍 覓語 quadratic approximation朱 螻螳 譯殊 貉 Gradient descent襯 轟 neuron 燕る input space 谿剰鍵 ∬ 襷ル曙 觜訣 郁規 譟伎 Simonyan et al. -> fully connected layer saliency map 谿城 郁規 Girchick et al. -> image 企 patch螳 filter襯 activation る讌 谿剰鍵 6 (1) Adaptive Deconvolutional Networks for Mid and High Level Feature Learning - Matthew D. Zeiler and Rob Fergus, 2011 (2) Visualizing and Understanding Convolutioinal Networks - Matthew D. Zeiler and Rob Fergus, 2014
  • 7. / 29 2.1 螻手碓 覦覯襦 - DeConvNet by Zeiler & Fergus (Contd) ろ語 蟲譟(AlexNet) 1. 螳 layerれ Convolution layer襦 蟲焔 2. Convolution layer れ ReLU 覿 3. (Optionally) Max pooling layer DeConvNet 谿 1. image襯 蠍一ヾ 給 ConvNet model(一検) 糾骸 2. 危エ覲 feature map 螻, るジ 覈 feature mapれ 0朱 襷 れ, DeConvNet layer(譬豸) 糾骸 (i) Unpool (ii) Rectify (iii)Reconstruction 7 (1) Adaptive Deconvolutional Networks for Mid and High Level Feature Learning - Matthew D. Zeiler and Rob Fergus, 2011 (2) Visualizing and Understanding Convolutioinal Networks - Matthew D. Zeiler and Rob Fergus, 2014
  • 8. / 29 2.1 螻手碓 覦覯襦 - DeConvNet by Zeiler & Fergus (Contd) Unpooling Max pooling non-invertible -> Approximation ∬係 pooling 襷 企 layer 豕螳 豺襯 record企螻, DeConvNet Switch 覦 . Rectification ReLU襯 蠍 覓語 feature map 0 伎 DeConvNet 螳 襷り鍵 ReLU 糾骸 Convolutional Filtering(Reconstruction) ∬鍵譟 learned conv filter襯 vertically, horizontally flip貅 (transposed) 螳 activation襷 BackPropる 蟆螻 螳 覩 8 (1) Adaptive Deconvolutional Networks for Mid and High Level Feature Learning - Matthew D. Zeiler and Rob Fergus, 2011 (2) Visualizing and Understanding Convolutioinal Networks - Matthew D. Zeiler and Rob Fergus, 2014 < 朱(1) figure > < from towardsdatascience.com >
  • 9. / 29 2.1 螻手碓 覦覯襦 - DeConvNet by Zeiler & Fergus (Contd) Occlusion Sensitivity test 轟 覿覿 襦 螳襴 企 覿覿 螳れ (b) total activation 覲 (d) probability score 覲 (e) most probable class 覲 (c) projection 蟆郁骸 ∬ 襴 企 企語 るジ 3螳 るジ 企語 伎: Convolution filter螳 企語 轟 覿覿(螳豌) ′願 . 9
  • 10. / 29 2.2 螻手碓 覦覯襦 - Guided BackProp by Springenberg 企 朱語 覈 襦 覈語 螳覦 れ 覯伎る 狩 蠑 覲旧″伎瑚螻 . ろ語襯 蟲燕 譴 豕螻 焔レ 企 螳 譴 覿覿 覓伎殊 谿場覲伎 覈 螳 覦覯 deconvolution approach(Guided BackProp) 朱語 蟆磯 Convolution layer襷朱 覈 ろ語襯 蟲 max-pooling layer襯 一 襷螻 -> Strided convolution layer (stride 2, 3x3 filter) 10(3) Striving for Simplicity: The All Convolutional Net - Jost Tobias Springenberg et al. 2014
  • 11. / 29 2.2 螻手碓 覦覯襦 - Guided BackProp by Springenberg(Contd) Max-pooling Strided Convolution layer襦 豌危 伎 Pooling equation Convolution equation => pooling, convolution 覈 螳 input 覦朱謂 pooling activation function p-norm 蟆螻 螳. 11(3) Striving for Simplicity: The All Convolutional Net - Jost Tobias Springenberg et al. 2014 si,j,u(f ) = ( k/2 h=k/2 k/2 w=k/2 | fg(h,w,i,j,u) |p )1/p Notation f : feature map W,H : width, height N : Number of channels k : pooling size r : stride g(h,w,i,j,u) = (r*i + h, r*j + w, u) p : order of p-norm, p螳 覓危朱 螳 max-pooling螻 螳 覩 theta : convolutional weight sigma : activation function o : # of output channel ci,j,o(f ) = ( k/2 h=k/2 k/2 w=k/2 N u=1 慮h,w,u,o fg(h,w,i,j,u))
  • 12. / 29 2.2 螻手碓 覦覯襦 - Guided BackProp by Springenberg(Contd) ろ 觜蟲 ろ語 譬襯 A, B, C : Convolutional filter size螳 る C 3螳讌 襦 譬 れ: 麹 一検 觜螳 覈 觜蟲 12(3) Striving for Simplicity: The All Convolutional Net - Jost Tobias Springenberg et al. 2014 螳 一
  • 13. / 29 2.2 螻手碓 覦覯襦 - Guided BackProp by Springenberg(Contd) All-CNN-C 覈語 Deconvolution 覦朱 螳 讌 螳 Zeiler & Fergus(2014) Deconvolution 覦覯 企 覈語 Max-Pooling layer螳 伎 焔レ 譬讌 蟆 Guided BackProp Convolution layer襷 蠍 覓語 switch Activation 螳 0 伎願, Gradient 0 伎 蟆襷 a) Zeiler&Fergus(2014) 13
  • 14. / 29 2.3 螻手碓 覦覯襦 - Weight vector襷 讌譴 DeConvNet, Guided BackProp 覦覯 覈 Weight(Conv filter) 一 蟆郁骸 蟯 Weight螳 Data Signal 磯手讌 朱襦 企 覦覯れ Data 譴 覿覿 ′伎 覈詩 14
  • 15. / 29 3.1 Linear Model 蟲 - Deterministic distractor Linear model 牛 signal螻 distractor 讌 蟯谿 15 Notation w : filter or weight x : data y : condensed output s : relevant signal d : distracting component. output 覓企 覲企 螳讌螻 讌 覿覿 a_s : direction of signal. output 殊 覈 a_d : direction of distractor s = asyx = s + d d = ad狼 as = (1,0)T ad = (1,1)T y [1,1] 狼 (亮, 2 ) Data x signal s distractor d 襷譟燕蠍 伎 願, 伎伎 蠍 覓 wT x = y w = [1, 1]T wT asy = y wT ad狼 = 0
  • 16. / 29 3.1 Linear Model 蟲 - Deterministic distractor 16 , 覈襯 豢譟煙貅 weight distractor襯 蟇壱伎狩蠍 覓語 distractor direction螻 orthogonal り 讀 w signal direction螻 align讌 . weight distractor orthogonal 讌覃伎, 蠍 譟一 牛 讌 . Weight vector distractor 蟆 譬讌一 weight vector襷朱 企 input pattern output レ 殊讌 wT asy = y wT ad狼 = 0 - signal direction 蠏碁襦 讌 - distractor direction 覦 weight direction 覦 wT as = 1
  • 17. / 29 3.2 Linear Model 蟲 - No distractor, Additive isotropic Gaussian noise 17 Isotropic Gaussian noise襯 伎 zero mean: noise mean bias襯 牛 朱 讌 朱襦 0朱 . correlation企 structure螳 蠍 覓語 weight vector襯 牛り 伎 noise螳 蟇磯讌 . Gaussian noise襯 豢螳 蟆 L2 regularization螻 螳 螻朱ゼ 碁. 讀 weight襯 shirink . 譟郁唄 覓語 襷譟燕 螳 weight vector 螳 覦レ vector < Gaussian pattern > yn = 硫xn + 狼 N n=1 (yn |硫xn, 2 ) N n=1 (yn |硫xn, 2 )(硫|0,了1 ) N n=1 1 2 (yn 硫xn)2 了硫2 + const < Gaussian noise & L2 regularization > > likelihood, 皙 Logarithm wT as = 1 as as w w霞 w 1
  • 18. / 29 4. Approaches 18 Functions data x output y襯 觸 磯 覦覯. ex) gradients, saliency map y襯 x襦 覩碁伎 input 覲螳 企至 output 覲蟆讌 危エ覲碁. 企 model gradient襯 磯 蟆願 蟆郁記 gradient weight. Signal Signal: 覈語 neuron activate る 一危一 蟲 Output input space蟾讌 gradient襯 backprop貅 覲 蟯谿 DeConvNet, Guded BackProp 蟆 signal企 覲伎 覈詩. Attribution 轟 Signal 朱 output 蠍一讌 企 讌 Linear model signal螻 weight vector element-wise 螻煙朱 伎伎 Deep taylor decomposition 朱語 activation 螳 input contribution朱 覿危螻, LRP relevance 豺. y = wT x y/x = w PatternNet PatternAttribution
  • 19. / 29 5. Quality criterion for signal estimator 19 伎 wT x = y wT s + wT d = y (x = s + d)wT (s + d) = y wT s = y (wT d = 0) (wT )1 wT s = (wT )1 y s = uu1 (wT )1 y s = u(wT u)1 y u = random vector (wT u 0) Quality measure S(x) = s (S) = 1 maxvcorr(wT x, vT (x S(x))) d = x S(x) y = wT x, , = 1 maxv vT cov[y, d] 2 vT d 2 y 譬 signal estimator correlation 0朱 -> w 企 給 覈語 weight 螳 correlation scale invariant 蠍 覓語 覿一 覿郁骸 螳 蟆企 曙^蟇 豢螳 S(x)襯 螻り optimal 襯 谿城謂 覦 d y Least-squares regression vT d y v illposed problem. 企襦 襴讌 . るジ 覦
  • 20. / 29 6.1 蠍一ヾ Signal estimator 覦 20 The identity estimator data distractor , signal襷 譟伎 螳 data螳 企語 signal 企語 蠏碁襦企. linear model attribution 蟲 . (distractor螳 譟伎朱, attribution ) れ 一危一 distractor螳 螻, forward pass 蟇磯讌襷 backward pass element wise 螻煙 讌 螳 noise螳 襷 覲伎碁(LRP) Sx(x) = x r = w x = w s + w d The filter based estimator ∬豸° signal weight direction 螳 ex) DeConvNet, Guided BackProp weight normalize 伎 linear model attribution 螻旧 れ螻 螳螻 signal 襦 蟲燕讌 覈詩 Sw(x) = w wTw wT x r = w w wTw y
  • 21. / 29 6.2 PatternNet & PatternAttribution 21 覦 覦 螳 criterion 豕 給逢 覈 螳ロ 覯″ y d correlation 0 signal estimator S螳 optimal企 . Linear model y d covariance 0企 cov[y, x] cov[y, S(x)] = 0 v cov[y, x] = cov[y, S(x)] cov[y, d] = 0 (S) = 1 maxvcorr(wT x, vT (x S(x))) = 1 maxv vT cov[y, d] 2 vT d 2 y Quality measure
  • 22. / 29 6.2 PatternNet & PatternAttribution 22 The linear estimator linear neuron data x linear signal襷 豢豢 螳 豌 y linear 一一 signal linear model y, d covariance 0企襦 Sa(x) = awT x = ay cov[x, y] = cov[S(x), y] = cov[awT x, y] = a cov[y, y] a = cov[x, y] 2 y 襷 d s螳 orthogonal る DeConvNet螻 螳 filter-based 覦 螻 殊. Convolution layer 襷れ FC layer ReLU螳 郁屋伎 覿覿 correlation 蟇壱 朱襦 豌 criterion 豺 VGG16 criterion 觜蟲 襷蠏碁 襦 random, S_w, S_a, S_a+-
  • 23. / 29 6.2 PatternNet & PatternAttribution 23 The two-component(Non-linear) estimator linear estimator 螳 trick 一襷 y 螳 覿語 磯 螳螳 るゴ蟆 豌襴. 企一 燕伎讌 覿 覲企 distractor 譟伎 y螳 覿覿 螻 ReLU 覓語 れ positive domain襷 locally 一危 蠍 覓語 企ゼ 覲伎 covariance 螻旧 れ螻 螳螻 覿語 磯 磯 螻, 螳譴豺襦 . Sa+(x) = { a+w x if油w x > 0 aw x otherwise x = { s+ + d+ if油y > 0 s + d otherwise cov(x, y) = [xy] [x][y] cov(x, y) = +(+[xy] +[x][y]) +(1 +)(錫[xy] 錫[x][y]) cov(s, y) = +(+[sy] +[s][y]) +(1 +)(錫[sy] 錫[s][y]) cov(x,y), cov(s,y)螳 殊 , 覿語 覃 a+ = +[xy] +[x][y] w +[xy] w +[x][y]
  • 24. / 29 6.2 PatternNet & PatternAttribution 24 PatternNet and PatternAttribution
  • 25. / 29 6.2 PatternNet & PatternAttribution 25 PatternNet and PatternAttribution PatternNet, Linear cov[x,y], cov[s,y]螳 螳 a襯 螻壱 x, y襦襷 螻 螳 PatternNet, Non-linear ReLU activation 轟 螻 / a 螳 螻 Non-linear 覈語 焔 譬 PatternAttribution a 螳 w襯 element-wise 螻燕 蟆郁骸襦 伎蠍 譬 蟾 heat map 燕 . r = w a+ a = cov[x, y] 2 y a+ = +[xy] +[x][y] w +[xy] w +[x][y]
  • 26. / 29 7. Experiments 26 螳 觜蟲, VGG16 on ImageNet(S) Convolution layer 覲 朱語 linear estimator螳 覃伎 譬 焔レ 覲伎願 覲 朱語 non-linear estimator るジ filter-based, random 覲企 燕 焔 FC layer with ReLU 覲 朱語 linear estimator 焔 蠍蟆 伎 non-linear estimator 焔 讌
  • 27. / 29 7. Experiments 27 Qualitative evaluation 轟 企語 レ 觜蟲 伎 Methods 蟲覿 Sx : Identity estimator Sw : DeConvNet, Guided BackProp Sa : Linear Sa+- : Non-linear 一検朱 螳 襦 譬 structure襯錫 誤螻 碁蟆 ′碁.
  • 29. / 2929 螳. PatternNet & PatternAttribution