📃 Edge#247: Classifying ML Interpretability Methods

In this issue:

• we classify ML interpretability methods; 

• we explore the building blocks of interpretability by Google Research;

• we explain TensorWatch, an open-source framework for debugging ML models. 

Enjoy the learning!  

---

💡 ML Concept of the Day: Classifying ML Interpretability Methods    

The ML interpretability space is vast and full of distinctive methods. From that perspective, it is essential to establish general criteria by which we can understand the different ML interpretability methods. One of the most popular taxonomies in ML theory classifies interpretability techniques across three main dimensions: