News for hackers. Stuff that matters.
Re:Deep Learning State of the Art (2019) [video] by cs702 on Friday January 18, 2019 @12:53PM (#18941178)
Nice work. I can think of only two things that are missing:

* Normalizing flows - e.g., https://arxiv.org/abs/1605.08803 , https://arxiv.org/abs/1807.03039 , among many others

* ODEnets and continous normalizing flows - https://arxiv.org/abs/1806.07366

Re:Deep Learning State of the Art (2019) [video] by grej on Friday January 18, 2019 @02:38PM (#18942233)
Yeah strange that ODEnets were left off, and I’m glad you mentioned it. That has the opportunity to be a transformative approach to more efficient training and much better performance on time-series problems.