$30 off During Our Annual Pro Sale. View Details »

“Why Should I Trust You?” Explaining the Predic...

Avatar for Wei Lu Wei Lu
November 06, 2017
Science
0
55

“Why Should I Trust You?” Explaining the Predictions of Any Classifier

Papers We Love, Nov 2017

Avatar for Wei Lu

Wei Lu

November 06, 2017
Tweet

More Decks by Wei Lu

See All by Wei Lu
A Brief Introduction to the Basics of Game Theory
Avatar for Wei Lu weilu
0
130
Bundler vs npm
Avatar for Wei Lu weilu
0
530
Cryptocurrency
Avatar for Wei Lu weilu
1
230
Peatio - An open-source crypto currency exchange
Avatar for Wei Lu weilu
0
680
Bitcoin Applications in JavaScript
Avatar for Wei Lu weilu
0
87
Writing expressive tests with RSpec
Avatar for Wei Lu weilu
0
140

Other Decks in Science

See All in Science
【論文紹介】Is CLIP ideal? No. Can we fix it?Yes! 第65回 コンピュータビジョン勉強会＠関東
Avatar for Shun Makino shun6211
5
2.1k
蔵本モデルが解き明かす同期と相転移の秘密　〜拍手のリズムはなぜ揃うのか？〜
Avatar for Syota-Sasaki syotasasaki593876
1
160
白金鉱業Vol.21【初学者向け発表枠】身近な例から学ぶ数理最適化の基礎 / Learning the Basics of Mathematical Optimization Through Everyday Examples
Avatar for BrainPad brainpadpr
1
470
AI(人工知能)の過去・現在・未来 —AIは人間を超えるのか—
Avatar for Y-h. Taguchi tagtag
0
130
ランサムウェア対策にも考慮したVMware、Hyper-V、Azure、AWS間のリアルタイムレプリケーション「Zerto」を徹底解説
Avatar for Climb climbteam
0
180
Kaggle: NeurIPS - Open Polymer Prediction 2025 コンペ 反省会
Avatar for calpis10000 calpis10000
0
290
People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
Avatar for hajime kiyama rudorudo11
0
170
データベース11: 正規化(1/2) - 望ましくない関係スキーマ
Avatar for Y. Yamamoto trycycle
PRO
0
1k
データベース06: SQL (3/3) 副問い合わせ
Avatar for Y. Yamamoto trycycle
PRO
1
700
PPIのみを用いたAIによる薬剤–遺伝子–疾患 相互作用の同定
Avatar for Y-h. Taguchi tagtag
0
120
AIに仕事を奪われる
最初の医師たちへ
Avatar for iKora128 ikora128
0
1k
Agent開発フレームワークのOverviewとW&B Weaveとのインテグレーション
Avatar for W&B Si siyoo
0
400

Featured

See All Featured
Ten Tips & Tricks for a 🌱 transition
Avatar for Manu Carrasco Molina stuffmc
0
34
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
Avatar for Mfonobong Umondia mfonobong
2
230
Java REST API Framework Comparison - PWX 2021
Avatar for Matt Raible mraible
34
9k
Typedesign – Prime Four
Avatar for Hannes Fritz hannesfritz
42
2.9k
What Being in a Rock Band Can Teach Us About Real World SEO
Avatar for Ade Holder 427marketing
0
150
How Fast Is Fast Enough? [PerfNow 2025]
Avatar for Tammy Everts tammyeverts
3
400
Google's AI Overviews - The New Search
Avatar for Barry Adams badams
0
870
Deep Space Network (abreviated)
Avatar for Tony Rice tonyrice
0
20
Everyday Curiosity
Avatar for Cassini Nazir cassininazir
0
110
How to Build an AI Search Optimization Roadmap - Criteria and Steps to Take #SEOIRL
Avatar for Aleyda Solis aleyda
1
1.8k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
Avatar for Eileen M. Uchitelle eileencodes
141
34k
The State of eCommerce SEO: How to Win in Today's Products SERPs - #SEOweek
Avatar for Aleyda Solis aleyda
2
9.1k

Transcript

  1. “Why Should I Trust You?” Explaining the Predictions of Any

    Classifier Papers We Love Nov 2017
  2. None

  3. Can I trust the prediction?

  4. Can I trust the prediction?

  5. 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.

  6. Trust Prediction Model

  7. 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”

  8. Local fidelity

  9. Pick predictions: Submodular pick (SP)