Data | Extracting human understandable insights

date
Jun 6, 2020
slug
human-understandable-insights
status
Published
summary
Three great materials I found on TDS(TowardDataScience.com) and the City of Statistics today.
tags
Academic
Reading
Engineering
AI
ML
Python
type
Post
Three great materials I found on TDS(TowardDataScience.com) and the City of Statistics today:
  • Extracting human understandable insights from any Machine Learning model (Parul Pandey) Four methods, Permutation Importance, Partial Dependence Plots, SHAP values，Advanced Uses of SHAP Values, are introduced here；
  • Guide to Interpretable Machine Learning (Matthew Stewart, PhD Researcher), focus on visulization.
  • Christoph Molnar’s new book,Interpretable Machine Learning, a systematic introduction on understabdability of machine learning techniques.
可解释的模型(Interpretable Models)
  • Linear Regression 线性回归 [2] [3]
  • Logistic Regression 逻辑回归 [3]
  • GLM, GAM and more 广义线性模型、广义加法模型和更多 [3]
  • Decision Tree 决策树 [2] [3]
  • Decision Rules 判定准则（不仅是贝叶斯判定准则） [3]
  • RuleFit 规则拟合 [3]
  • Other Interpretable Models 其他可解释模型 [3]
    • Naive Bayes Classifier 朴素贝叶斯分类器 [3]
    • K-nearest Neighbors K 近邻法 [3]
模型不可知方法(Example-Based Explanations)
  • Partial Dependence Plots 部分依赖图 [1] [2] [3]
  • Individual Conditional Expectation (ICE) [2] [3]
  • Accumulated Local Effects (ALE) Plot [2] [3]
  • Feature Interaction [2] [3]
  • Permutation Importance 排列重要性 [1] [3]
  • Global Surrogate [3]
  • Local Surrogate (LIME) [2] [3]
  • Scoped Rules (Anchors) [2] [3]
  • Shapley Values [3]
  • SHAP Values SHapley Additive exPlanation 值 [1] [2] [3]
  • Advanced Uses of SHAP Values SHAP 值的高级应用 [1] [3]
  • Dimensional Reduction Techniques (PCA, t-SNE) 降维技术 [2]
  • Model Distillation 模型蒸馏 [2]
基于例子的解释(Example Based Explanations)
  • Counterfactual Explanations 反事实解释 [2] [3]
  • Adversarial Examples 对抗样本 [3]
  • Prototypes and Criticisms 原型和批评 [3]
  • Influential Instances 有影响力的实例 [3]
神经网络的解释(Neural Network Interpretation)
  • Learned Features 学成特征 [3]

References

The first article https://towardsdatascience.com/interpretable-machine-learning-1dec0f2f3e6b
The second article https://towardsdatascience.com/guide-to-interpretable-machine-learning-d40e8a64b6cf
That book https://christophm.github.io/interpretable-ml-book/
 

© Rongxin 2021 - 2024