Interpretability Insights
Shreya delves into the concept of interpretability in machine learning, emphasizing the importance of understanding how predictions are influenced by training data. She highlights the intriguing paper "Understanding black box predictions via influence functions" as a key resource in this area of research.In this clip
From this podcast

Gradient Dissent - A Machine Learning Podcast
Operationalizing Machine Learning: Interview with Shreya Shankar
Related Questions