Awesome-explainable-AI

by wangyongjie-ntu

awesome listMarkdownpushed almost 2 years ago

A collection of research materials on explainable AI/ML

AI summary

Explainability library

A curated collection of research materials on explainable AI/ML, providing insights into techniques and methods for improving model interpretability.

stars: 1.4K
forks: 199
watching: 42
awesome lists: 3
entries: 11

What's in the list

11 links in 5 sections, with live GitHub stats.activeno commit in 2y

Papers

1. Transparent Model Design
1.4Kalmost 2 years
2. Post-Explanation
1.4Kalmost 2 years

Papers / 2. Post-Explanation

2.1 Model Explanation(Model-level)
1.4Kalmost 2 years
2.2 Model Inspection
1.4Kalmost 2 years
2.3 Outcome Explanation
1.4Kalmost 2 years

Papers / 2. Post-Explanation / 2.3 Outcome Explanation

2.3.1 Feature Attribution/Importance(Saliency Map)
1.4Kalmost 2 years

Papers / 2. Post-Explanation

2.4 Neuron Importance
1.4Kalmost 2 years
2.5 Example-based Explanations
1.4Kalmost 2 years

Papers / 2. Post-Explanation / 2.5 Example-based Explanations

2.5.1 Counterfactual Explanations(Recourse)
1.4Kalmost 2 years
2.5.2 Influential Instances
1.4Kalmost 2 years
2.5.3 Prototypes&Criticisms
1.4Kalmost 2 years

Featured in 3 awesome lists

Each link jumps to the spot where the list mentions Awesome-explainable-AI.