Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
“Why Should I Trust You?” Explaining the Predictions of Any Classifier
Search
Wei Lu
November 06, 2017
Science
0
32
“Why Should I Trust You?” Explaining the Predictions of Any Classifier
Papers We Love, Nov 2017
Wei Lu
November 06, 2017
Tweet
Share
More Decks by Wei Lu
See All by Wei Lu
A Brief Introduction to the Basics of Game Theory
weilu
0
78
Bundler vs npm
weilu
0
470
Cryptocurrency
weilu
1
170
Peatio - An open-source crypto currency exchange
weilu
0
650
Bitcoin Applications in JavaScript
weilu
0
76
Writing expressive tests with RSpec
weilu
0
120
Other Decks in Science
See All in Science
Endocannabinology 101
drbonci
PRO
0
250
ABEMAの効果検証事例〜効果の異質性を考える〜
s1ok69oo
3
1.5k
AI(人工知能)の過去・現在・未来 —AIは人間を超えるのか—
tagtag
0
260
20240127_OpenRadiossエアバッグ解析
kamakiri1225
0
140
HIBINO Aiko
genomethica
0
360
AI Alignment: A Comprehensive Survey
s_ota
0
180
Yasuke
drawsbygba
0
610
遺伝子発現プロファイルに基づく新しい薬物間相互作用予測法
tagtag
0
100
同じデータでもP値が変わる話/key_considerations_in_NHST
florets1
1
1.1k
OptimizationNight~機械学習と数理最適化の融合~
hidenari
0
290
BigQueryで参加するレコメンドコンペ / bq-recommend-competition-kaggle-meetup-tokyo-2023
shimacos
1
1.3k
統計的因果探索の方法
sshimizu2006
0
860
Featured
See All Featured
Typedesign – Prime Four
hannesfritz
36
2.1k
Fashionably flexible responsive web design (full day workshop)
malarkey
397
65k
The Cult of Friendly URLs
andyhume
74
5.7k
The Power of CSS Pseudo Elements
geoffreycrofte
59
5k
Side Projects
sachag
451
41k
Principles of Awesome APIs and How to Build Them.
keavy
120
16k
A designer walks into a library…
pauljervisheath
199
23k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
34
8.9k
Building Applications with DynamoDB
mza
88
5.6k
Rails Girls Zürich Keynote
gr2m
91
13k
Pencils Down: Stop Designing & Start Developing
hursman
117
11k
Code Review Best Practice
trishagee
54
15k
Transcript
“Why Should I Trust You?” Explaining the Predictions of Any
Classifier Papers We Love Nov 2017
None
Can I trust the prediction?
Can I trust the prediction?
Trust • Trusting a prediction: whether a user trusts an
individual prediction sufficiently to take some action based on it. • Trusting a model: whether the user trusts a model to behave in reasonable ways if deployed.
Trust Prediction Model
LIME: Local Interpretable Model-agnostic Explanations Local: global model can be
complicated and hard to approximate Interpretable: because human Model-agnostic: works on any black box Explanation: back to “trust”
Local fidelity
Pick predictions: Submodular pick (SP)