Over Parameterization Debate
Jonathan discusses the necessity of over parameterization in neural networks, questioning its role in the lottery ticket hypothesis. The debate centers around the need for memorizing noisy data and the level of over parameterization required for network generalization.In this clip
From this podcast
Machine Learning Street Talk (MLST)
The Lottery Ticket Hypothesis with Jonathan Frankle
Related Questions
How does double descent occur in practical deep learning systems as discussed in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Double Descent Explained?
How does double descent occur in practical deep learning systems as discussed in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Introduction to Deep Double Descent?