📜
Paper a Week (PaW)
  • Paper a Week
  • “Why Should I Trust You?” Explaining the Predictions of Any Classifier (LIME)
  • Born Again Tree Ensembles
  • Robust and Stable Black Box Explanations
  • InterpretML: A Unified Framework for Machine Learning Interpretability
  • Global Explanations of Neural Networks
  • Explainable Machine Learning in Deployment
Powered by GitBook
On this page

Was this helpful?

Last updated 4 years ago

The idea is simple.

A paper summary, every week. With code snippets and basic usage, if possible.

Field of AI/ML/DL with a focus (usually) on explainability, trees and other topics I come across.

I write about everything else at

adityalahiri.github.io
Next“Why Should I Trust You?” Explaining the Predictions of Any Classifier (LIME)

Paper a Week

We tend to think we understand what we read - until we try to rewrite it in our own words.