Dexa/Machine Learning Street Talk (MLST)

Tackling Model Robustness

Hadi discusses the challenge of making models more human-like in their understanding and handling of perturbations. Sayak emphasizes the importance of addressing distribution shift to achieve model robustness against common corruptions.

In this clip
From this podcast
Machine Learning Street Talk (MLST)
#52 - Unadversarial Examples (Hadi Salman, MIT)
Related Questions
- What are the challenges in machine learning as discussed in the episode #52 - Unadversarial Examples (Hadi Salman, MIT) and the clip Writing Impactful Papers?