Beyond Accuracy: Behavioral Testing of NLP Models with Sameer Singh - #406
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
00:00
The Lasting Impact and Challenges of LIME in Model Explainability
This chapter explores the significance of the LIME paper in model explainability, emphasizing its enduring influence and relevance. It addresses both the excitement it sparked and the complexities in its application, along with ongoing research into its vulnerabilities within the broader context of machine learning explainability.
Transcript
Play full episode
