
31 - Singular Learning Theory with Daniel Murfet
AXRP - the AI X-risk Research Podcast
Comparing Learning Theories in Deep Learning
This chapter examines the differences between Singular Learning Theory (SLT) and Neural Tangent Kernel (NTK) approaches, focusing on how NTK explains the dynamics of infinitely wide neural networks. The discussion highlights the implications of NTK for hyperparameter selection and its mathematical foundations, while also addressing ongoing debates in the field.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.