Hacker News Reader

It's like, fine. If you're an engineer curious about the basic notions of deep learning, have at it. It's not very technical; very big picture.

If you're well experienced with deep learning already, maybe only the last 2-3 minutes on the future is worth watching.

The interview itself was good but rather high level. My personal bottom line: unsupervised learning is the next frontier.

The future IMO is recursive meta learning. This far the max recursion depth afaik has been 1, and that's just a first step.

Also, SeLUs were supposed to be game changing. Are they, or why are they not? Why haven't they been used more? Or what's still missing?

Scaled-ELU is meant to create self-normalizing nets, but that's nothing you can't achieve a bit less efficiently with explicit normalization (batch norm, etc), so hardly a game changer.