Connections Explored
Daniel and Hattie discuss the connections between their work and recent studies on neural net training phenomena, specifically focusing on the double descent and groking phenomena. They explore the similarities between forget relearn and the interpolation regime, and delve into the idea of inductive bias and its impact on training outcomes.In this clip
From this podcast

The Gradient
Hattie Zhou: Lottery Tickets and Algorithmic Reasoning in LLMs
Related Questions