Delays, Detours, and Forks in the Road: Latent State Models of Training DynamicsJan 1, 2023·Michael Hu,Angelica ChenNaomi Saphra,Kyunghyun Cho· 0 min read Cite URLTypeJournal articlePublicationTransactions of Machine Learning Research (TMLR)Last updated on Jan 1, 2023Training Dynamics Interpretability Science of Deep Learning Random Variation AuthorsNaomi SaphraResearch Fellow ← Understanding biological active sensing behaviors by interpreting learned artificial agent policies Jan 1, 2024Interpretability Creationism Jan 1, 2023 →
