Challenges in Interpretability
Been Kim discusses the issues she observed in the field of interpretability, such as relying on face value tasks and the need for better evaluation methods. She also highlights the connection between interpretability and philosophy, emphasizing the importance of considering context and objectives in defining explanations.In this clip
From this podcast
The Gradient
Been Kim: Interpretable Machine Learning
Related Questions
What are the key topics in AI interpretability as discussed in the episode Been Kim: Interpretable Machine Learning and the clip Challenges in Interpretability?
What are the key topics in AI interpretability as discussed in the episode Studying Machine Intelligence with Been Kim - #571 and the clip Interpretable Machine Learning?
What are the key topics in AI interpretability as discussed in the episode Studying Machine Intelligence with Been Kim - #571 and the clip Interpretable Machine Learning?