On Adversarial Training & Robustness with Bhavna Gopal
Thinking Machines: AI & Philosophy
00:00
Exploring Adversarial Training and Accuracy Metrics in Machine Learning
This chapter explores the intricacies of adversarial training and its evaluation metrics in machine learning. The discussion highlights the challenges of traditional accuracy measures versus adversarial accuracy, particularly in the context of language models and their robustness.
Transcript
Play full episode
