SlideShare a Scribd company logo
1 of 110
Download to read offline
1
20 2018/12/21
n
• ~2013.3, PhD@ ,
• 2013.4~2016.3, @IBM
• 2016.4~2017.8, @ ERATO, NII
• 2017.9~, @ ,
n
•
ECML’11
AISTATS’15,17
•
AISTATS’18
AAAI’17,18
ongoing
2
•
•
•
• AISTATS’18
• AAAI’17,18
3
AI
n
•
n
•
4
…
AI
n
•
n
•
5
XX
XX
AI
n
• AI
AI
AI AI
n
• AI
•
n
6
n
•
•
• AI
•
•
7
8
EU GDPR
n GDPR-22
1. The data subject shall have the right not to be subject to a decision based
solely on automated processing, including profiling, which produces legal
effects concerning him or her or similarly significantly affects him or her.
2. Paragraph 1 shall not apply if the decision: is necessary for entering into, or
performance of, a contract between the data subject and a data controller; is
authorised by Union or Member State law to which the controller is subject
and which also lays down suitable measures to safeguard the data subject’s
rights and freedoms and legitimate interests; or is based on the data subject’s
explicit consent.
3. In the cases referred to in points (a) and (c) of paragraph 2, the data controller
shall implement suitable measures to safeguard the data subject’s rights and
freedoms and legitimate interests, at least the right to obtain human
intervention on the part of the controller, to express his or her point of view
and to contest the decision.
4. Decisions referred to in paragraph 2 shall not be based on special categories of
personal data referred to in Article 9(2)1), unless point (a) or (g) of Article 9(2)
applies and suitable measures to safeguard the data subject’s rights and
freedoms and legitimate interests are in place.
9
n 2016
• ICML, NIPS
n
• , ,
Vol.33, No.3, pages 366--369, 2018.
• , Qiita
10
n AI
11
Peeking inside the black-box: A survey on Explainable Artificial Intelligence (XAI)
https://ieeexplore.ieee.org/document/8466590/
7 SCOPUS,
IEEExplore, ACM Digital Library, Google
Scholar, Citeseer Library, ScienceDirect,
arXiv
“intelligible”,
“interpretable”, “transparency”, “black box”,
“understandable”, “comprehensible”,
“explainable” AI
“Artificial Intelligence”, “Intelligent
system”, “Machine learning”, “deep learning”,
“classifier” , “decision tree”
•
•
•
• AISTATS’18
• AAAI’17,18
12
n
•
n
• 1.
• 2.
• 3.
• 4.
• …
13
n
n /
•
n
•
•
n “ ”
•
14
1.
•
2.
•
3.
•
15
n
n Why Should I Trust You?: Explaining the Predictions of
Any Classifier, KDD'16 [Python LIME; R LIME]
n A Unified Approach to Interpreting Model Predictions,
NIPS'17 [Python SHAP]
n Anchors: High-Precision Model-Agnostic Explanations,
AAAI'18 [Python Anchor]
n Understanding Black-box Predictions via Influence
Functions, ICML’17 [Python influence-release]
16
n
n Born Again Trees
n Making Tree Ensembles Interpretable: A Bayesian Model
Selection Approach, AISTATS'18 [Python defragTrees]
17
n
n [Python+Tensorflow
saliency; DeepExplain]
• Striving for Simplicity: The All Convolutional Net
(GuidedBackprop)
• On Pixel-Wise Explanations for Non-Linear Classifier Decisions
by Layer-Wise Relevance Propagation (Epsilon-LRP)
• Axiomatic Attribution for Deep Networks (IntegratedGrad)
• SmoothGrad: Removing Noise by Adding Noise (SmoothGrad)
• Learning Important Features Through Propagating Activation
Differences (DeepLIFT)
18
19
n
n Why Should I Trust You?: Explaining the Predictions of
Any Classifier, KDD'16 [Python LIME; R LIME]
n A Unified Approach to Interpreting Model Predictions,
NIPS'17 [Python SHAP]
n Anchors: High-Precision Model-Agnostic Explanations,
AAAI'18 [Python Anchor]
n Understanding Black-box Predictions via Influence
Functions, ICML’17 [Python influence-release]
20
n
n
• LIME, SHAP, Anchor
n
• influence
21
LIME
n Why Should I Trust You?: Explaining the Predictions of
Any Classifier, KDD'16 [Python LIME; R LIME]
•
•
22
LIME
23
LIME
n 2
• One-Hot
•
n LIME
• Adult One-Hot
24
LIME
n ! !′
• LIME !′ !# ∈ {0, 1}* +
!,
#
+
n -(!) !0
• - ! ≈ 2 !# ≔ 40 + 46!# for !# ∈ NeighborOf(!0
#
)
• 4 4,
25
LIME
n !(#) #%
• ! # ≈ ' #( ≔ *% + *,#( for #( ∈ NeighborOf(#%
(
)
n *
• min
:
∑ <,<> ∈? @AB
C ! C − ' C( E
s.t. * % ≤ G
* %
@AB
C #%
H #%
26
LIME
n
n
• vs
•
→ LIME
27
SHAP
n A Unified Approach to Interpreting Model Predictions,
NIPS'17 [Python SHAP]
•
• LIME
28
SHAP
n 1
n 2
29
SHAP
n SHAP LIME
• Adult One-Hot
n . “ ”
SHAP “ ”
30
SHAP
n SHAP = LIME
• ! "# = %& + %("# = %& + ∑* %*"*
#
3
n 1. + " = ! "#
•
31
SHAP
n SHAP = LIME
• ! "# = %& + %("# = %& + ∑* %*"*
#
3
n 2. "*
#
= 0 ⇒ %* = 0
•
32
SHAP
n SHAP = LIME
• ! "# = %& + %("# = %& + ∑* %*"*
#
3
n 3. + " = +, "# + +′
+,
# "# − +,
# "# ∖ 0 ≥ +, "# − +, "# ∖ 0 ⇒ %* +# ≥ %* +
• + +′ "*
#
+′ +
+# "*
#
+
33
SHAP
n SHAP = LIME
• ! "# = %& + %("# = %& + ∑* %*"*
#
SHAP
n 3
• %* = ∑+⊆-.
+ ! 01 + 12 !
0!
(4- 5 − 4-(5 ∖ 8))
• Shapley Value
34
SHAP
n LIME
• min
$
∑&∈( ) * +, * − . *
/
• ) * =
123
1 456678 & & (1 2|&|)
n
• Linear SHAP:
• Tree SHAP:
• Deep SHAP: DeepLIFT
35
Anchor
n Anchors: High-Precision Model-Agnostic Explanations,
AAAI'18 [Python Anchor]
•
36
Anchor
37
Anchor
n Anchor LIME
• Adult One-Hot
n
• Anchor +
38
Anchor
n “ +
•
39
Anchor
n !
• " ! ! " = 1
n %(⋅ |!) !
n ! =Anchor
• Anchor ! * " +
,- * ! 1. / 0. 1 ≥ +, ! " = 1
Anchor ! "
40
Anchor
n !" # $ 1& ' (& ) ≥ +
• 1 − -
Pr !" # $ 1& ' (& ) ≥ + ≥ 1 − -
41
Anchor
n ! =
!
• !
• max
%
&' ( [!(+)] s.t. Pr &' + ! 11 ( 21 3 ≥ 5 ≥ 1 − 7
n 1.
n 2.
• Pr &' + ! 11 ( 21 3 ≥ 5 1 − 7 !
42
n
n
• LIME, SHAP, Anchor
n
• influence
43
influence
n Understanding Black-box Predictions via Influence
Functions, ICML’17 [Python influence-release]
n ("′, %′)
"
44
influence
n ("′, %′)
"
n % = (("; *+), *+
*+ = argmin
2∈4
5
67(8,9)∈:
;(<; +)
*+=6> = argmin
2∈4
5
6∈: ?@A 6B6>
;(<; +)
n <> = ("′, %′) *+
• C+=6> − C+
*+=6> − *+ <>
45
<>
= ("′, %′)
influence
n !" = (%′, (′) *+
• ,+-." − ,+
*+-." − *+ !"
n
• !" = (%′, (′) ,+-."
•
n influence
• ,+-." − ,+
,+-." − ,+ ≈ −
1
2
345
-6
78(!"; ,+)
46
influence
n Data Poisoning
•
•
47
influence
n
•
48
This looks like that: deep learning for interpretable
image recognition, arxiv: 1806.10574.
n
n
• LIME
• SHAP
• Anchor
n
• influence
49
n
• Interpretable Predictions of Tree-based Ensembles
via Actionable Feature Tweaking, KDD’17
•
50
30 200
20 200
30 300
⭕
⭕
…
…
n
• Generating Visual Explanations, ECCV‘16
•
51
52
n
n Born Again Trees
n Making Tree Ensembles Interpretable: A Bayesian Model
Selection Approach, AISTATS'18 [Python defragTrees]
53
BATrees
n Born Again Trees
•
•
n
• !
!
•
54
n
• BATrees
• defragTrees RandomForest
55
56
n
n [Python+Tensorflow
saliency; DeepExplain]
• Striving for Simplicity: The All Convolutional Net
(GuidedBackprop)
• On Pixel-Wise Explanations for Non-Linear Classifier Decisions
by Layer-Wise Relevance Propagation (Epsilon-LRP)
• Axiomatic Attribution for Deep Networks (IntegratedGrad)
• SmoothGrad: Removing Noise by Adding Noise (SmoothGrad)
• Learning Important Features Through Propagating Activation
Differences (DeepLIFT)
57
n
•
58
DNN
n
•
59
DNN
n
•
60
DNN
n DNN
61
n
•
→
•
→
62
n ! = # $
n $
n [Simonyan et al., arXiv’14]
$%
&' (
&()
•
→ →
*+ ,
*,-
→
•
→ →
&' (
&()
→
63
n [Simonyan et al., arXiv’14]
!"
#$ %
#%&
n
• GuidedBP [Springenberg et al., arXiv’14]
back propagation
• LRP [Bach et al., PloS ONE’15]
• IntegratedGrad [Sundararajan et al., arXiv’17]
• SmoothGrad [Smilkov et al., arXiv’17]
• DeepLIFT [Shrikumar et al., ICML’17]
64
n
n
[Python+Tensorflow saliency; DeepExplain]
• Striving for Simplicity: The All Convolutional Net
(GuidedBackprop)
• On Pixel-Wise Explanations for Non-Linear Classifier Decisions
by Layer-Wise Relevance Propagation (Epsilon-LRP)
• Axiomatic Attribution for Deep Networks (IntegratedGrad)
• SmoothGrad: Removing Noise by Adding Noise (SmoothGrad)
• Learning Important Features Through Propagating Activation
Differences (DeepLIFT)
65
•
•
•
• AISTATS’18
• AAAI’17,18
66
n AISTATS’18
•
n AAAI’17,18
•
67
機械学習モデルの判断根拠の説明
defragTrees
n Making Tree Ensembles Interpretable: A Bayesian Model
Selection Approach, AISTATS'18 [Python defragTrees]
•
•
n
69
when
Relationship ≠ Not-in-family, Wife
Capital Gain < 7370
when
Relationship ≠ Not-in-family
Capital Gain >= 7370
when
Relationship ≠ Not-in-family, Unmarried
Capital Gain < 5095
Capital Loss < 2114
when
Relationship = Not-in-family
Country ≠ China, Peru
Capital Gain < 5095
when
Relationship ≠ Not-in-family
Country ≠ China
Capital Gain < 5095
when
Relationship ≠ Not-in-family
Capital Gain >= 7370
…
…
n
n
•
70
y = XOR(x1 < 0.5, x2 < 0.5) + ✏
n
n
71
2017 The State of Data Science & Machine LearningYour Year on Kaggle: Most Memorable
Community Stats from 2016
n
n
72
R
n
•
•
n
73
defragTrees
n 1.
• !" #, % &)
n 2. !"( #, % ))
• !"( #, % )) ≈ !"(#, %|&) ) ≪ &
!"( #, % ))
n
• )
• Factorized
Asymptotic Bayesian (FAB) Inference
74
&
)
n
n
•
•
•
75
D
Synthetic 2 1000 1000
Spambase 57 1000 1000
MiniBooNE 50 5000 5000
Magic 11 5000 5000
Higgs 28 5000 5000
Energy 8 384 384
n
76
n
77
n
•
n
•
•
78
n AISTATS’18
•
n AAAI’17,18
•
79
機械学習モデルの判断根拠の説明
n Enumerate Lasso Solu/ons for Feature Selec/on,
AAAI’17 [Python LassoVariants].
n Approximate and Exact Enumera/on of Rule Models,
AAAI'18.
→ NO!
n
•
82
n
• →
•
n
•
83
n
•
n
•
→
84
n
•
n
•
→
85
n
•
n
•
→
86
n
•
n
•
87
•
•
Lasso
Given: !", $" ∈ ℝ'×ℝ ) = 1, 2, … , .
Find: / ∈ ℝ' s.t. !"
0
/ ≈ $ () = 1, 2, … , .)
/
n
•
•
Lasso ℓ5
/∗ = argmin
=
1
2
>/ − $ @ + B / 5
• Lasso /∗ supp(/∗) = {) ∶ /"
∗
≠ 0}
Lasso
n
•
→ Lasso
n Lasso
•
→
n
機械学習モデルの判断根拠の説明
Lasso
n ! ⊆ {$%, $', … , $)} Lasso
Lasso ! = min
3
%
'
45 − 7 ' + 9 5 % s.t. supp 5 ⊆ !
Lasso
! Lasso ! <
supp 5 = !
• 9
• 9
• $%, $', $= , $%, $', $> , $%, $>, $? , $%, $' , …
Lasso !
Lawler !-best
1. " #
2. $ ∈ #
" $ "& = " ∖ {$}
Lasso("′) #′
(#&, "′)
3.
4.
Lawler !-best
1. " #
2. $ ∈ &
' $ '( = ' ∖ {$}
Lasso('′) &′
(&(, '′)
3.
4.
& = 56, 57, 58
' = 56, 57, 59, 58, 5:
&6 = 56, 57, 58
'6 = 56, 57, 59, 58, 5:
Lawler !-best
1. " #
2. $ ∈ &
' $ '( = ' ∖ {$}
Lasso("′) #′
(#(, "′)
3.
4.
"5
( = 67, 68, 69, 6:
"7
( = 65, 68, 69, 6:
"8
(
= 65, 67, 68, 6:
"5 = 65, 67, 68, 69, 6:
#5 = 65, 67, 69
"5 = 65, 67, 68, 69, 6:
Lawler !-best
1. " #
2. $ ∈ &
" ' "( = " ∖ {'}
-.//0(2′) &′
(&(, 2′)
3.
4.
(#6
(= 78, 79, 7: , "6
()"6
( = 78, 7;, 79, 7:
"8
( = 76, 7;, 79, 7:
";
(
= 76, 78, 7;, 7:
"6 = 76, 78, 7;, 79, 7:
#6 = 76, 78, 79
"6 = 76, 78, 7;, 79, 7:
Lawler !-best
1. " #
2. $ ∈ &
" ' "( = " ∖ {'}
-.//0(2′) &′
(&(, 2′)
3.
4.
(#6
(= 78, 79, 7: , "6
()"6
( = 78, 7;, 79, 7:
"8
( = 76, 7;, 79, 7:
";
(
= 76, 78, 7;, 7:
"6 = 76, 78, 7;, 79, 7:
(#8
(= 76, 7;, 79 , "8
()
#6 = 76, 78, 79
"6 = 76, 78, 7;, 79, 7:
Lawler !-best
1. " #
2. $ ∈ &
" ' "( = " ∖ {'}
-.//0(2′) &′
(&(, 2′)
3.
4.
(#6
(= 78, 79, 7: , "6
()"6
( = 78, 7;, 79, 7:
"8
( = 76, 7;, 79, 7:
";
(
= 76, 78, 7;, 7:
"6 = 76, 78, 7;, 79, 7:
(#8
(= 76, 7;, 79 , "8
()
(#;
(= 76, 78, 7: , ";
()#6 = 76, 78, 79
"6 = 76, 78, 7;, 79, 7:
Lawler !-best
1. " #
2. $ ∈ #
" $ "& = " ∖ {$}
+,--.("′) #′
(#&, "′)
3.
4.
(#3
&= 45, 46, 47 , "3
&)
(#5
&= 43, 48, 46 , "5
&)
(#8
&= 43, 45, 47 , "8
&)
#5 = 45, 46, 47
"5 = 45, 48, 46, 47
#3 = 43, 45, 46
"3 = 43, 45, 48, 46, 47
Lawler !-best
1. " #
2. $ ∈ &
' $ '( = ' ∖ {$}
Lasso("′) #′
(#(, "′)
3.
4.
#5 = 65, 67, 68
"5 = 65, 67, 69, 68, 6:
(#7
(= 65, 69, 68 , "7
()
(#9
(= 65, 67, 6: , "9
()
#7 = 67, 68, 6:
"7 = 67, 69, 68, 6:
"8
( = 69, 68, 6:
":
(
= 67, 69, 6:
";
(
= 67, 69, 68
"7 = 67, 69, 68, 6:
Lasso % %
n
• %
• % Lasso
機械学習モデルの判断根拠の説明
1.
n Thaliana gene expression data (Atwell et al. ’10):
• ! ∈ ℝ$%&%'( 2
• ) ∈ ℝ
• 134
2.
n 20 Newsgroups Data (Lang’95); ibm vs mac
• ! ∈ ℝ$$%&' tf-idf
• ( ∈ {ibm, mac} 2
• 1168
→
bios drive ibm
ide drive ibm
dos os, drive ibm
controller drive ibm
quadra, centris 040, clock mac
windows, bios, controller disk, drive ibm
bios, help, controller disk, drive ibm
centris, pc 610 mac
n
•
n Lasso
• Lawler !-best
n
•
•
•
•
•
• AISTATS’18
• AAAI’17,18
106
n
•
•
107
n
n Sanity Checks for Saliency Maps, NeurIPS’18.
•
• Sanity Check
108
“ ”
Guided-BP
n
•
•
•
n
• Please Stop Explaining Black Box Models for High-Stakes
Decisions, arXiv:1811.10154
109
n
•
•
n
•
110

More Related Content

What's hot

強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)
強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)
強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)Shota Imai
 
SSII2021 [OS2-02] 深層学習におけるデータ拡張の原理と最新動向
SSII2021 [OS2-02] 深層学習におけるデータ拡張の原理と最新動向SSII2021 [OS2-02] 深層学習におけるデータ拡張の原理と最新動向
SSII2021 [OS2-02] 深層学習におけるデータ拡張の原理と最新動向SSII
 
【論文調査】XAI技術の効能を ユーザ実験で評価する研究
【論文調査】XAI技術の効能を ユーザ実験で評価する研究【論文調査】XAI技術の効能を ユーザ実験で評価する研究
【論文調査】XAI技術の効能を ユーザ実験で評価する研究Satoshi Hara
 
グラフニューラルネットワーク入門
グラフニューラルネットワーク入門グラフニューラルネットワーク入門
グラフニューラルネットワーク入門ryosuke-kojima
 
backbone としての timm 入門
backbone としての timm 入門backbone としての timm 入門
backbone としての timm 入門Takuji Tahara
 
強化学習と逆強化学習を組み合わせた模倣学習
強化学習と逆強化学習を組み合わせた模倣学習強化学習と逆強化学習を組み合わせた模倣学習
強化学習と逆強化学習を組み合わせた模倣学習Eiji Uchibe
 
[DL輪読会]ドメイン転移と不変表現に関するサーベイ
[DL輪読会]ドメイン転移と不変表現に関するサーベイ[DL輪読会]ドメイン転移と不変表現に関するサーベイ
[DL輪読会]ドメイン転移と不変表現に関するサーベイDeep Learning JP
 
近年のHierarchical Vision Transformer
近年のHierarchical Vision Transformer近年のHierarchical Vision Transformer
近年のHierarchical Vision TransformerYusuke Uchida
 
[DL輪読会]Understanding Black-box Predictions via Influence Functions
[DL輪読会]Understanding Black-box Predictions via Influence Functions [DL輪読会]Understanding Black-box Predictions via Influence Functions
[DL輪読会]Understanding Black-box Predictions via Influence Functions Deep Learning JP
 
Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...
Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...
Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...joisino
 
Active Learning の基礎と最近の研究
Active Learning の基礎と最近の研究Active Learning の基礎と最近の研究
Active Learning の基礎と最近の研究Fumihiko Takahashi
 
SIX ABEJA 講演資料 もうブラックボックスとは呼ばせない~機械学習を支援する情報
SIX ABEJA 講演資料 もうブラックボックスとは呼ばせない~機械学習を支援する情報SIX ABEJA 講演資料 もうブラックボックスとは呼ばせない~機械学習を支援する情報
SIX ABEJA 講演資料 もうブラックボックスとは呼ばせない~機械学習を支援する情報Takayuki Itoh
 
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence ModelingDeep Learning JP
 
SSII2021 [OS2-01] 転移学習の基礎:異なるタスクの知識を利用するための機械学習の方法
SSII2021 [OS2-01] 転移学習の基礎:異なるタスクの知識を利用するための機械学習の方法SSII2021 [OS2-01] 転移学習の基礎:異なるタスクの知識を利用するための機械学習の方法
SSII2021 [OS2-01] 転移学習の基礎:異なるタスクの知識を利用するための機械学習の方法SSII
 
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
[DL輪読会]Learning Transferable Visual Models From Natural Language SupervisionDeep Learning JP
 
【DL輪読会】A Path Towards Autonomous Machine Intelligence
【DL輪読会】A Path Towards Autonomous Machine Intelligence【DL輪読会】A Path Towards Autonomous Machine Intelligence
【DL輪読会】A Path Towards Autonomous Machine IntelligenceDeep Learning JP
 
Active Learning 入門
Active Learning 入門Active Learning 入門
Active Learning 入門Shuyo Nakatani
 
アンサンブル木モデル解釈のためのモデル簡略化法
アンサンブル木モデル解釈のためのモデル簡略化法アンサンブル木モデル解釈のためのモデル簡略化法
アンサンブル木モデル解釈のためのモデル簡略化法Satoshi Hara
 
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料Yusuke Uchida
 
【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised LearningまとめDeep Learning JP
 

What's hot (20)

強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)
強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)
強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)
 
SSII2021 [OS2-02] 深層学習におけるデータ拡張の原理と最新動向
SSII2021 [OS2-02] 深層学習におけるデータ拡張の原理と最新動向SSII2021 [OS2-02] 深層学習におけるデータ拡張の原理と最新動向
SSII2021 [OS2-02] 深層学習におけるデータ拡張の原理と最新動向
 
【論文調査】XAI技術の効能を ユーザ実験で評価する研究
【論文調査】XAI技術の効能を ユーザ実験で評価する研究【論文調査】XAI技術の効能を ユーザ実験で評価する研究
【論文調査】XAI技術の効能を ユーザ実験で評価する研究
 
グラフニューラルネットワーク入門
グラフニューラルネットワーク入門グラフニューラルネットワーク入門
グラフニューラルネットワーク入門
 
backbone としての timm 入門
backbone としての timm 入門backbone としての timm 入門
backbone としての timm 入門
 
強化学習と逆強化学習を組み合わせた模倣学習
強化学習と逆強化学習を組み合わせた模倣学習強化学習と逆強化学習を組み合わせた模倣学習
強化学習と逆強化学習を組み合わせた模倣学習
 
[DL輪読会]ドメイン転移と不変表現に関するサーベイ
[DL輪読会]ドメイン転移と不変表現に関するサーベイ[DL輪読会]ドメイン転移と不変表現に関するサーベイ
[DL輪読会]ドメイン転移と不変表現に関するサーベイ
 
近年のHierarchical Vision Transformer
近年のHierarchical Vision Transformer近年のHierarchical Vision Transformer
近年のHierarchical Vision Transformer
 
[DL輪読会]Understanding Black-box Predictions via Influence Functions
[DL輪読会]Understanding Black-box Predictions via Influence Functions [DL輪読会]Understanding Black-box Predictions via Influence Functions
[DL輪読会]Understanding Black-box Predictions via Influence Functions
 
Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...
Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...
Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...
 
Active Learning の基礎と最近の研究
Active Learning の基礎と最近の研究Active Learning の基礎と最近の研究
Active Learning の基礎と最近の研究
 
SIX ABEJA 講演資料 もうブラックボックスとは呼ばせない~機械学習を支援する情報
SIX ABEJA 講演資料 もうブラックボックスとは呼ばせない~機械学習を支援する情報SIX ABEJA 講演資料 もうブラックボックスとは呼ばせない~機械学習を支援する情報
SIX ABEJA 講演資料 もうブラックボックスとは呼ばせない~機械学習を支援する情報
 
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling
 
SSII2021 [OS2-01] 転移学習の基礎:異なるタスクの知識を利用するための機械学習の方法
SSII2021 [OS2-01] 転移学習の基礎:異なるタスクの知識を利用するための機械学習の方法SSII2021 [OS2-01] 転移学習の基礎:異なるタスクの知識を利用するための機械学習の方法
SSII2021 [OS2-01] 転移学習の基礎:異なるタスクの知識を利用するための機械学習の方法
 
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
 
【DL輪読会】A Path Towards Autonomous Machine Intelligence
【DL輪読会】A Path Towards Autonomous Machine Intelligence【DL輪読会】A Path Towards Autonomous Machine Intelligence
【DL輪読会】A Path Towards Autonomous Machine Intelligence
 
Active Learning 入門
Active Learning 入門Active Learning 入門
Active Learning 入門
 
アンサンブル木モデル解釈のためのモデル簡略化法
アンサンブル木モデル解釈のためのモデル簡略化法アンサンブル木モデル解釈のためのモデル簡略化法
アンサンブル木モデル解釈のためのモデル簡略化法
 
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
 
【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ
 

Similar to 機械学習モデルの判断根拠の説明

Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and...
Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and...Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and...
Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and...Satoshi Hara
 
Active Neural Localization
Active Neural LocalizationActive Neural Localization
Active Neural LocalizationHaruya Ishikawa
 
(論文サーベイ)主成分分析によるオンライン外れ値検出
(論文サーベイ)主成分分析によるオンライン外れ値検出(論文サーベイ)主成分分析によるオンライン外れ値検出
(論文サーベイ)主成分分析によるオンライン外れ値検出kazuya_n
 
Mcs011 solved assignment by divya singh
Mcs011 solved assignment by divya singhMcs011 solved assignment by divya singh
Mcs011 solved assignment by divya singhDIVYA SINGH
 
Basics in algorithms and data structure
Basics in algorithms and data structure Basics in algorithms and data structure
Basics in algorithms and data structure Eman magdy
 
(RubyConf 2020) How prime numbers keep the internet secure
(RubyConf 2020) How prime numbers keep the internet secure(RubyConf 2020) How prime numbers keep the internet secure
(RubyConf 2020) How prime numbers keep the internet secureSun-Li Beatteay
 
Elasticsearch at EyeEm
Elasticsearch at EyeEmElasticsearch at EyeEm
Elasticsearch at EyeEmLars Fronius
 
K02-salen: Systems Thinking in Action 2011
K02-salen: Systems Thinking in Action 2011K02-salen: Systems Thinking in Action 2011
K02-salen: Systems Thinking in Action 2011pegasuscomm
 
Oceans 2019 tutorial-geophysical-nav_7-updated
Oceans 2019 tutorial-geophysical-nav_7-updatedOceans 2019 tutorial-geophysical-nav_7-updated
Oceans 2019 tutorial-geophysical-nav_7-updatedFrancisco Curado-Teixeira
 
第5回NIPS読み会・関西発表資料
第5回NIPS読み会・関西発表資料第5回NIPS読み会・関西発表資料
第5回NIPS読み会・関西発表資料Kyoichiro Kobayashi
 
Paper Reading: Pessimistic Cardinality Estimation
Paper Reading: Pessimistic Cardinality EstimationPaper Reading: Pessimistic Cardinality Estimation
Paper Reading: Pessimistic Cardinality EstimationPingCAP
 
Moment-Based Estimation for Hierarchical Models in Apache Spark with Kyle Sch...
Moment-Based Estimation for Hierarchical Models in Apache Spark with Kyle Sch...Moment-Based Estimation for Hierarchical Models in Apache Spark with Kyle Sch...
Moment-Based Estimation for Hierarchical Models in Apache Spark with Kyle Sch...Databricks
 
Duplicates everywhere (Kiev)
Duplicates everywhere (Kiev)Duplicates everywhere (Kiev)
Duplicates everywhere (Kiev)Alexey Grigorev
 
Rob Sullivan at Heroku's Waza 2013: Your Database -- A Story of Indifference
Rob Sullivan at Heroku's Waza 2013: Your Database -- A Story of IndifferenceRob Sullivan at Heroku's Waza 2013: Your Database -- A Story of Indifference
Rob Sullivan at Heroku's Waza 2013: Your Database -- A Story of IndifferenceHeroku
 
A3 sec -_regular_expressions
A3 sec -_regular_expressionsA3 sec -_regular_expressions
A3 sec -_regular_expressionsa3sec
 
(KO) 온라인 뉴스 댓글 플랫폼을 흐리는 어뷰저 분석기 / (EN) Online ...
(KO) 온라인 뉴스 댓글 플랫폼을 흐리는 어뷰저 분석기 / (EN) Online ...(KO) 온라인 뉴스 댓글 플랫폼을 흐리는 어뷰저 분석기 / (EN) Online ...
(KO) 온라인 뉴스 댓글 플랫폼을 흐리는 어뷰저 분석기 / (EN) Online ...Ji Hyung Moon
 
Datamining R 2nd
Datamining R 2ndDatamining R 2nd
Datamining R 2ndsesejun
 
Parallel Computing in R
Parallel Computing in RParallel Computing in R
Parallel Computing in Rmickey24
 
Locality sensitive hashing
Locality sensitive hashingLocality sensitive hashing
Locality sensitive hashingSEMINARGROOT
 

Similar to 機械学習モデルの判断根拠の説明 (20)

Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and...
Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and...Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and...
Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and...
 
Active Neural Localization
Active Neural LocalizationActive Neural Localization
Active Neural Localization
 
機械学習と自動微分
機械学習と自動微分機械学習と自動微分
機械学習と自動微分
 
(論文サーベイ)主成分分析によるオンライン外れ値検出
(論文サーベイ)主成分分析によるオンライン外れ値検出(論文サーベイ)主成分分析によるオンライン外れ値検出
(論文サーベイ)主成分分析によるオンライン外れ値検出
 
Mcs011 solved assignment by divya singh
Mcs011 solved assignment by divya singhMcs011 solved assignment by divya singh
Mcs011 solved assignment by divya singh
 
Basics in algorithms and data structure
Basics in algorithms and data structure Basics in algorithms and data structure
Basics in algorithms and data structure
 
(RubyConf 2020) How prime numbers keep the internet secure
(RubyConf 2020) How prime numbers keep the internet secure(RubyConf 2020) How prime numbers keep the internet secure
(RubyConf 2020) How prime numbers keep the internet secure
 
Elasticsearch at EyeEm
Elasticsearch at EyeEmElasticsearch at EyeEm
Elasticsearch at EyeEm
 
K02-salen: Systems Thinking in Action 2011
K02-salen: Systems Thinking in Action 2011K02-salen: Systems Thinking in Action 2011
K02-salen: Systems Thinking in Action 2011
 
Oceans 2019 tutorial-geophysical-nav_7-updated
Oceans 2019 tutorial-geophysical-nav_7-updatedOceans 2019 tutorial-geophysical-nav_7-updated
Oceans 2019 tutorial-geophysical-nav_7-updated
 
第5回NIPS読み会・関西発表資料
第5回NIPS読み会・関西発表資料第5回NIPS読み会・関西発表資料
第5回NIPS読み会・関西発表資料
 
Paper Reading: Pessimistic Cardinality Estimation
Paper Reading: Pessimistic Cardinality EstimationPaper Reading: Pessimistic Cardinality Estimation
Paper Reading: Pessimistic Cardinality Estimation
 
Moment-Based Estimation for Hierarchical Models in Apache Spark with Kyle Sch...
Moment-Based Estimation for Hierarchical Models in Apache Spark with Kyle Sch...Moment-Based Estimation for Hierarchical Models in Apache Spark with Kyle Sch...
Moment-Based Estimation for Hierarchical Models in Apache Spark with Kyle Sch...
 
Duplicates everywhere (Kiev)
Duplicates everywhere (Kiev)Duplicates everywhere (Kiev)
Duplicates everywhere (Kiev)
 
Rob Sullivan at Heroku's Waza 2013: Your Database -- A Story of Indifference
Rob Sullivan at Heroku's Waza 2013: Your Database -- A Story of IndifferenceRob Sullivan at Heroku's Waza 2013: Your Database -- A Story of Indifference
Rob Sullivan at Heroku's Waza 2013: Your Database -- A Story of Indifference
 
A3 sec -_regular_expressions
A3 sec -_regular_expressionsA3 sec -_regular_expressions
A3 sec -_regular_expressions
 
(KO) 온라인 뉴스 댓글 플랫폼을 흐리는 어뷰저 분석기 / (EN) Online ...
(KO) 온라인 뉴스 댓글 플랫폼을 흐리는 어뷰저 분석기 / (EN) Online ...(KO) 온라인 뉴스 댓글 플랫폼을 흐리는 어뷰저 분석기 / (EN) Online ...
(KO) 온라인 뉴스 댓글 플랫폼을 흐리는 어뷰저 분석기 / (EN) Online ...
 
Datamining R 2nd
Datamining R 2ndDatamining R 2nd
Datamining R 2nd
 
Parallel Computing in R
Parallel Computing in RParallel Computing in R
Parallel Computing in R
 
Locality sensitive hashing
Locality sensitive hashingLocality sensitive hashing
Locality sensitive hashing
 

More from Satoshi Hara

Explanation in Machine Learning and Its Reliability
Explanation in Machine Learning and Its ReliabilityExplanation in Machine Learning and Its Reliability
Explanation in Machine Learning and Its ReliabilitySatoshi Hara
 
機械学習で嘘をつく話
機械学習で嘘をつく話機械学習で嘘をつく話
機械学習で嘘をつく話Satoshi Hara
 
異常の定義と推定
異常の定義と推定異常の定義と推定
異常の定義と推定Satoshi Hara
 
Convex Hull Approximation of Nearly Optimal Lasso Solutions
Convex Hull Approximation of Nearly Optimal Lasso SolutionsConvex Hull Approximation of Nearly Optimal Lasso Solutions
Convex Hull Approximation of Nearly Optimal Lasso SolutionsSatoshi Hara
 
Maximally Invariant Data Perturbation as Explanation
Maximally Invariant Data Perturbation as ExplanationMaximally Invariant Data Perturbation as Explanation
Maximally Invariant Data Perturbation as ExplanationSatoshi Hara
 
機械学習モデルの列挙
機械学習モデルの列挙機械学習モデルの列挙
機械学習モデルの列挙Satoshi Hara
 
KDD'17読み会:Anomaly Detection with Robust Deep Autoencoders
KDD'17読み会:Anomaly Detection with Robust Deep AutoencodersKDD'17読み会:Anomaly Detection with Robust Deep Autoencoders
KDD'17読み会:Anomaly Detection with Robust Deep AutoencodersSatoshi Hara
 
特徴選択のためのLasso解列挙
特徴選択のためのLasso解列挙特徴選択のためのLasso解列挙
特徴選択のためのLasso解列挙Satoshi Hara
 

More from Satoshi Hara (8)

Explanation in Machine Learning and Its Reliability
Explanation in Machine Learning and Its ReliabilityExplanation in Machine Learning and Its Reliability
Explanation in Machine Learning and Its Reliability
 
機械学習で嘘をつく話
機械学習で嘘をつく話機械学習で嘘をつく話
機械学習で嘘をつく話
 
異常の定義と推定
異常の定義と推定異常の定義と推定
異常の定義と推定
 
Convex Hull Approximation of Nearly Optimal Lasso Solutions
Convex Hull Approximation of Nearly Optimal Lasso SolutionsConvex Hull Approximation of Nearly Optimal Lasso Solutions
Convex Hull Approximation of Nearly Optimal Lasso Solutions
 
Maximally Invariant Data Perturbation as Explanation
Maximally Invariant Data Perturbation as ExplanationMaximally Invariant Data Perturbation as Explanation
Maximally Invariant Data Perturbation as Explanation
 
機械学習モデルの列挙
機械学習モデルの列挙機械学習モデルの列挙
機械学習モデルの列挙
 
KDD'17読み会:Anomaly Detection with Robust Deep Autoencoders
KDD'17読み会:Anomaly Detection with Robust Deep AutoencodersKDD'17読み会:Anomaly Detection with Robust Deep Autoencoders
KDD'17読み会:Anomaly Detection with Robust Deep Autoencoders
 
特徴選択のためのLasso解列挙
特徴選択のためのLasso解列挙特徴選択のためのLasso解列挙
特徴選択のためのLasso解列挙
 

Recently uploaded

UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8DianaGray10
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1DianaGray10
 
Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Adtran
 
IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdf
IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdfIaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdf
IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdfDaniel Santiago Silva Capera
 
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesThousandEyes
 
Bird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemBird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemAsko Soukka
 
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostKubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostMatt Ray
 
UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7DianaGray10
 
Introduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptxIntroduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptxMatsuo Lab
 
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...DianaGray10
 
Cloud Revolution: Exploring the New Wave of Serverless Spatial Data
Cloud Revolution: Exploring the New Wave of Serverless Spatial DataCloud Revolution: Exploring the New Wave of Serverless Spatial Data
Cloud Revolution: Exploring the New Wave of Serverless Spatial DataSafe Software
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.YounusS2
 
Babel Compiler - Transforming JavaScript for All Browsers.pptx
Babel Compiler - Transforming JavaScript for All Browsers.pptxBabel Compiler - Transforming JavaScript for All Browsers.pptx
Babel Compiler - Transforming JavaScript for All Browsers.pptxYounusS2
 
UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6DianaGray10
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Commit University
 
UiPath Community: AI for UiPath Automation Developers
UiPath Community: AI for UiPath Automation DevelopersUiPath Community: AI for UiPath Automation Developers
UiPath Community: AI for UiPath Automation DevelopersUiPathCommunity
 
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019IES VE
 
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UbiTrack UK
 
PicPay - GenAI Finance Assistant - ChatGPT for Customer Service
PicPay - GenAI Finance Assistant - ChatGPT for Customer ServicePicPay - GenAI Finance Assistant - ChatGPT for Customer Service
PicPay - GenAI Finance Assistant - ChatGPT for Customer ServiceRenan Moreira de Oliveira
 
9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding TeamAdam Moalla
 

Recently uploaded (20)

UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1
 
Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™
 
IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdf
IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdfIaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdf
IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdf
 
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
 
Bird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemBird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystem
 
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostKubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
 
UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7
 
Introduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptxIntroduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptx
 
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
 
Cloud Revolution: Exploring the New Wave of Serverless Spatial Data
Cloud Revolution: Exploring the New Wave of Serverless Spatial DataCloud Revolution: Exploring the New Wave of Serverless Spatial Data
Cloud Revolution: Exploring the New Wave of Serverless Spatial Data
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.
 
Babel Compiler - Transforming JavaScript for All Browsers.pptx
Babel Compiler - Transforming JavaScript for All Browsers.pptxBabel Compiler - Transforming JavaScript for All Browsers.pptx
Babel Compiler - Transforming JavaScript for All Browsers.pptx
 
UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)
 
UiPath Community: AI for UiPath Automation Developers
UiPath Community: AI for UiPath Automation DevelopersUiPath Community: AI for UiPath Automation Developers
UiPath Community: AI for UiPath Automation Developers
 
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
 
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
 
PicPay - GenAI Finance Assistant - ChatGPT for Customer Service
PicPay - GenAI Finance Assistant - ChatGPT for Customer ServicePicPay - GenAI Finance Assistant - ChatGPT for Customer Service
PicPay - GenAI Finance Assistant - ChatGPT for Customer Service
 
9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team
 

機械学習モデルの判断根拠の説明

  • 2. n • ~2013.3, PhD@ , • 2013.4~2016.3, @IBM • 2016.4~2017.8, @ ERATO, NII • 2017.9~, @ , n • ECML’11 AISTATS’15,17 • AISTATS’18 AAAI’17,18 ongoing 2
  • 8. 8
  • 9. EU GDPR n GDPR-22 1. The data subject shall have the right not to be subject to a decision based solely on automated processing, including profiling, which produces legal effects concerning him or her or similarly significantly affects him or her. 2. Paragraph 1 shall not apply if the decision: is necessary for entering into, or performance of, a contract between the data subject and a data controller; is authorised by Union or Member State law to which the controller is subject and which also lays down suitable measures to safeguard the data subject’s rights and freedoms and legitimate interests; or is based on the data subject’s explicit consent. 3. In the cases referred to in points (a) and (c) of paragraph 2, the data controller shall implement suitable measures to safeguard the data subject’s rights and freedoms and legitimate interests, at least the right to obtain human intervention on the part of the controller, to express his or her point of view and to contest the decision. 4. Decisions referred to in paragraph 2 shall not be based on special categories of personal data referred to in Article 9(2)1), unless point (a) or (g) of Article 9(2) applies and suitable measures to safeguard the data subject’s rights and freedoms and legitimate interests are in place. 9
  • 10. n 2016 • ICML, NIPS n • , , Vol.33, No.3, pages 366--369, 2018. • , Qiita 10
  • 11. n AI 11 Peeking inside the black-box: A survey on Explainable Artificial Intelligence (XAI) https://ieeexplore.ieee.org/document/8466590/ 7 SCOPUS, IEEExplore, ACM Digital Library, Google Scholar, Citeseer Library, ScienceDirect, arXiv “intelligible”, “interpretable”, “transparency”, “black box”, “understandable”, “comprehensible”, “explainable” AI “Artificial Intelligence”, “Intelligent system”, “Machine learning”, “deep learning”, “classifier” , “decision tree”
  • 13. n • n • 1. • 2. • 3. • 4. • … 13
  • 16. n n Why Should I Trust You?: Explaining the Predictions of Any Classifier, KDD'16 [Python LIME; R LIME] n A Unified Approach to Interpreting Model Predictions, NIPS'17 [Python SHAP] n Anchors: High-Precision Model-Agnostic Explanations, AAAI'18 [Python Anchor] n Understanding Black-box Predictions via Influence Functions, ICML’17 [Python influence-release] 16
  • 17. n n Born Again Trees n Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach, AISTATS'18 [Python defragTrees] 17
  • 18. n n [Python+Tensorflow saliency; DeepExplain] • Striving for Simplicity: The All Convolutional Net (GuidedBackprop) • On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation (Epsilon-LRP) • Axiomatic Attribution for Deep Networks (IntegratedGrad) • SmoothGrad: Removing Noise by Adding Noise (SmoothGrad) • Learning Important Features Through Propagating Activation Differences (DeepLIFT) 18
  • 19. 19
  • 20. n n Why Should I Trust You?: Explaining the Predictions of Any Classifier, KDD'16 [Python LIME; R LIME] n A Unified Approach to Interpreting Model Predictions, NIPS'17 [Python SHAP] n Anchors: High-Precision Model-Agnostic Explanations, AAAI'18 [Python Anchor] n Understanding Black-box Predictions via Influence Functions, ICML’17 [Python influence-release] 20
  • 21. n n • LIME, SHAP, Anchor n • influence 21
  • 22. LIME n Why Should I Trust You?: Explaining the Predictions of Any Classifier, KDD'16 [Python LIME; R LIME] • • 22
  • 24. LIME n 2 • One-Hot • n LIME • Adult One-Hot 24
  • 25. LIME n ! !′ • LIME !′ !# ∈ {0, 1}* + !, # + n -(!) !0 • - ! ≈ 2 !# ≔ 40 + 46!# for !# ∈ NeighborOf(!0 # ) • 4 4, 25
  • 26. LIME n !(#) #% • ! # ≈ ' #( ≔ *% + *,#( for #( ∈ NeighborOf(#% ( ) n * • min : ∑ <,<> ∈? @AB C ! C − ' C( E s.t. * % ≤ G * % @AB C #% H #% 26
  • 28. SHAP n A Unified Approach to Interpreting Model Predictions, NIPS'17 [Python SHAP] • • LIME 28
  • 30. SHAP n SHAP LIME • Adult One-Hot n . “ ” SHAP “ ” 30
  • 31. SHAP n SHAP = LIME • ! "# = %& + %("# = %& + ∑* %*"* # 3 n 1. + " = ! "# • 31
  • 32. SHAP n SHAP = LIME • ! "# = %& + %("# = %& + ∑* %*"* # 3 n 2. "* # = 0 ⇒ %* = 0 • 32
  • 33. SHAP n SHAP = LIME • ! "# = %& + %("# = %& + ∑* %*"* # 3 n 3. + " = +, "# + +′ +, # "# − +, # "# ∖ 0 ≥ +, "# − +, "# ∖ 0 ⇒ %* +# ≥ %* + • + +′ "* # +′ + +# "* # + 33
  • 34. SHAP n SHAP = LIME • ! "# = %& + %("# = %& + ∑* %*"* # SHAP n 3 • %* = ∑+⊆-. + ! 01 + 12 ! 0! (4- 5 − 4-(5 ∖ 8)) • Shapley Value 34
  • 35. SHAP n LIME • min $ ∑&∈( ) * +, * − . * / • ) * = 123 1 456678 & & (1 2|&|) n • Linear SHAP: • Tree SHAP: • Deep SHAP: DeepLIFT 35
  • 36. Anchor n Anchors: High-Precision Model-Agnostic Explanations, AAAI'18 [Python Anchor] • 36
  • 38. Anchor n Anchor LIME • Adult One-Hot n • Anchor + 38
  • 40. Anchor n ! • " ! ! " = 1 n %(⋅ |!) ! n ! =Anchor • Anchor ! * " + ,- * ! 1. / 0. 1 ≥ +, ! " = 1 Anchor ! " 40
  • 41. Anchor n !" # $ 1& ' (& ) ≥ + • 1 − - Pr !" # $ 1& ' (& ) ≥ + ≥ 1 − - 41
  • 42. Anchor n ! = ! • ! • max % &' ( [!(+)] s.t. Pr &' + ! 11 ( 21 3 ≥ 5 ≥ 1 − 7 n 1. n 2. • Pr &' + ! 11 ( 21 3 ≥ 5 1 − 7 ! 42
  • 43. n n • LIME, SHAP, Anchor n • influence 43
  • 44. influence n Understanding Black-box Predictions via Influence Functions, ICML’17 [Python influence-release] n ("′, %′) " 44
  • 45. influence n ("′, %′) " n % = (("; *+), *+ *+ = argmin 2∈4 5 67(8,9)∈: ;(<; +) *+=6> = argmin 2∈4 5 6∈: ?@A 6B6> ;(<; +) n <> = ("′, %′) *+ • C+=6> − C+ *+=6> − *+ <> 45 <> = ("′, %′)
  • 46. influence n !" = (%′, (′) *+ • ,+-." − ,+ *+-." − *+ !" n • !" = (%′, (′) ,+-." • n influence • ,+-." − ,+ ,+-." − ,+ ≈ − 1 2 345 -6 78(!"; ,+) 46
  • 48. influence n • 48 This looks like that: deep learning for interpretable image recognition, arxiv: 1806.10574.
  • 49. n n • LIME • SHAP • Anchor n • influence 49
  • 50. n • Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking, KDD’17 • 50 30 200 20 200 30 300 ⭕ ⭕ … …
  • 51. n • Generating Visual Explanations, ECCV‘16 • 51
  • 52. 52
  • 53. n n Born Again Trees n Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach, AISTATS'18 [Python defragTrees] 53
  • 54. BATrees n Born Again Trees • • n • ! ! • 54
  • 55. n • BATrees • defragTrees RandomForest 55
  • 56. 56
  • 57. n n [Python+Tensorflow saliency; DeepExplain] • Striving for Simplicity: The All Convolutional Net (GuidedBackprop) • On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation (Epsilon-LRP) • Axiomatic Attribution for Deep Networks (IntegratedGrad) • SmoothGrad: Removing Noise by Adding Noise (SmoothGrad) • Learning Important Features Through Propagating Activation Differences (DeepLIFT) 57
  • 63. n ! = # $ n $ n [Simonyan et al., arXiv’14] $% &' ( &() • → → *+ , *,- → • → → &' ( &() → 63
  • 64. n [Simonyan et al., arXiv’14] !" #$ % #%& n • GuidedBP [Springenberg et al., arXiv’14] back propagation • LRP [Bach et al., PloS ONE’15] • IntegratedGrad [Sundararajan et al., arXiv’17] • SmoothGrad [Smilkov et al., arXiv’17] • DeepLIFT [Shrikumar et al., ICML’17] 64
  • 65. n n [Python+Tensorflow saliency; DeepExplain] • Striving for Simplicity: The All Convolutional Net (GuidedBackprop) • On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation (Epsilon-LRP) • Axiomatic Attribution for Deep Networks (IntegratedGrad) • SmoothGrad: Removing Noise by Adding Noise (SmoothGrad) • Learning Important Features Through Propagating Activation Differences (DeepLIFT) 65
  • 69. defragTrees n Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach, AISTATS'18 [Python defragTrees] • • n 69 when Relationship ≠ Not-in-family, Wife Capital Gain < 7370 when Relationship ≠ Not-in-family Capital Gain >= 7370 when Relationship ≠ Not-in-family, Unmarried Capital Gain < 5095 Capital Loss < 2114 when Relationship = Not-in-family Country ≠ China, Peru Capital Gain < 5095 when Relationship ≠ Not-in-family Country ≠ China Capital Gain < 5095 when Relationship ≠ Not-in-family Capital Gain >= 7370 … …
  • 70. n n • 70 y = XOR(x1 < 0.5, x2 < 0.5) + ✏
  • 71. n n 71 2017 The State of Data Science & Machine LearningYour Year on Kaggle: Most Memorable Community Stats from 2016
  • 74. defragTrees n 1. • !" #, % &) n 2. !"( #, % )) • !"( #, % )) ≈ !"(#, %|&) ) ≪ & !"( #, % )) n • ) • Factorized Asymptotic Bayesian (FAB) Inference 74 & )
  • 75. n n • • • 75 D Synthetic 2 1000 1000 Spambase 57 1000 1000 MiniBooNE 50 5000 5000 Magic 11 5000 5000 Higgs 28 5000 5000 Energy 8 384 384
  • 76. n 76
  • 77. n 77
  • 81. n Enumerate Lasso Solu/ons for Feature Selec/on, AAAI’17 [Python LassoVariants]. n Approximate and Exact Enumera/on of Rule Models, AAAI'18.
  • 89. Lasso Given: !", $" ∈ ℝ'×ℝ ) = 1, 2, … , . Find: / ∈ ℝ' s.t. !" 0 / ≈ $ () = 1, 2, … , .) / n • • Lasso ℓ5 /∗ = argmin = 1 2 >/ − $ @ + B / 5 • Lasso /∗ supp(/∗) = {) ∶ /" ∗ ≠ 0}
  • 92. Lasso n ! ⊆ {$%, $', … , $)} Lasso Lasso ! = min 3 % ' 45 − 7 ' + 9 5 % s.t. supp 5 ⊆ ! Lasso ! Lasso ! < supp 5 = ! • 9 • 9 • $%, $', $= , $%, $', $> , $%, $>, $? , $%, $' , … Lasso !
  • 93. Lawler !-best 1. " # 2. $ ∈ # " $ "& = " ∖ {$} Lasso("′) #′ (#&, "′) 3. 4.
  • 94. Lawler !-best 1. " # 2. $ ∈ & ' $ '( = ' ∖ {$} Lasso('′) &′ (&(, '′) 3. 4. & = 56, 57, 58 ' = 56, 57, 59, 58, 5: &6 = 56, 57, 58 '6 = 56, 57, 59, 58, 5:
  • 95. Lawler !-best 1. " # 2. $ ∈ & ' $ '( = ' ∖ {$} Lasso("′) #′ (#(, "′) 3. 4. "5 ( = 67, 68, 69, 6: "7 ( = 65, 68, 69, 6: "8 ( = 65, 67, 68, 6: "5 = 65, 67, 68, 69, 6: #5 = 65, 67, 69 "5 = 65, 67, 68, 69, 6:
  • 96. Lawler !-best 1. " # 2. $ ∈ & " ' "( = " ∖ {'} -.//0(2′) &′ (&(, 2′) 3. 4. (#6 (= 78, 79, 7: , "6 ()"6 ( = 78, 7;, 79, 7: "8 ( = 76, 7;, 79, 7: "; ( = 76, 78, 7;, 7: "6 = 76, 78, 7;, 79, 7: #6 = 76, 78, 79 "6 = 76, 78, 7;, 79, 7:
  • 97. Lawler !-best 1. " # 2. $ ∈ & " ' "( = " ∖ {'} -.//0(2′) &′ (&(, 2′) 3. 4. (#6 (= 78, 79, 7: , "6 ()"6 ( = 78, 7;, 79, 7: "8 ( = 76, 7;, 79, 7: "; ( = 76, 78, 7;, 7: "6 = 76, 78, 7;, 79, 7: (#8 (= 76, 7;, 79 , "8 () #6 = 76, 78, 79 "6 = 76, 78, 7;, 79, 7:
  • 98. Lawler !-best 1. " # 2. $ ∈ & " ' "( = " ∖ {'} -.//0(2′) &′ (&(, 2′) 3. 4. (#6 (= 78, 79, 7: , "6 ()"6 ( = 78, 7;, 79, 7: "8 ( = 76, 7;, 79, 7: "; ( = 76, 78, 7;, 7: "6 = 76, 78, 7;, 79, 7: (#8 (= 76, 7;, 79 , "8 () (#; (= 76, 78, 7: , "; ()#6 = 76, 78, 79 "6 = 76, 78, 7;, 79, 7:
  • 99. Lawler !-best 1. " # 2. $ ∈ # " $ "& = " ∖ {$} +,--.("′) #′ (#&, "′) 3. 4. (#3 &= 45, 46, 47 , "3 &) (#5 &= 43, 48, 46 , "5 &) (#8 &= 43, 45, 47 , "8 &) #5 = 45, 46, 47 "5 = 45, 48, 46, 47 #3 = 43, 45, 46 "3 = 43, 45, 48, 46, 47
  • 100. Lawler !-best 1. " # 2. $ ∈ & ' $ '( = ' ∖ {$} Lasso("′) #′ (#(, "′) 3. 4. #5 = 65, 67, 68 "5 = 65, 67, 69, 68, 6: (#7 (= 65, 69, 68 , "7 () (#9 (= 65, 67, 6: , "9 () #7 = 67, 68, 6: "7 = 67, 69, 68, 6: "8 ( = 69, 68, 6: ": ( = 67, 69, 6: "; ( = 67, 69, 68 "7 = 67, 69, 68, 6:
  • 101. Lasso % % n • % • % Lasso
  • 103. 1. n Thaliana gene expression data (Atwell et al. ’10): • ! ∈ ℝ$%&%'( 2 • ) ∈ ℝ • 134
  • 104. 2. n 20 Newsgroups Data (Lang’95); ibm vs mac • ! ∈ ℝ$$%&' tf-idf • ( ∈ {ibm, mac} 2 • 1168 → bios drive ibm ide drive ibm dos os, drive ibm controller drive ibm quadra, centris 040, clock mac windows, bios, controller disk, drive ibm bios, help, controller disk, drive ibm centris, pc 610 mac
  • 105. n • n Lasso • Lawler !-best n • •
  • 108. n n Sanity Checks for Saliency Maps, NeurIPS’18. • • Sanity Check 108 “ ” Guided-BP
  • 109. n • • • n • Please Stop Explaining Black Box Models for High-Stakes Decisions, arXiv:1811.10154 109