Model Interpretability with TCAV (Testing with Concept Activation Vectors)
Domino Data Lab
JANUARY 20, 2019
What if there was a way to quantitatively measure whether your machine learning (ML) model reflects specific domain expertise or potential bias? TCAV “uses directional derivatives to quantify the degree to which a user-defined concept is important to a classification result” ( Kim et al 2018 ). with post-training explanations?
Let's personalize your content