Adversarial Training Insights
Hadi delves into the impact of adversarial training on feature representation, highlighting the significance of robust features and their role in transfer learning. By masking non-robust features, adversarial training enhances model performance in scenarios with limited data, emphasizing the importance of quality features in knowledge transfer.In this clip
From this podcast

Machine Learning Street Talk (MLST)
#52 - Unadversarial Examples (Hadi Salman, MIT)
Related Questions