AI & machine learning2017 · shared on Hacker News
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
Explore PathNet: Evolution Channels Gradient Descent in Super Neural Networks, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yndr ·
Elon Musk’s Neuralink wants to boost the brain to keep up with AI
315 points272 comments
YAnon84 ·
Neurons that fire together, wire together, but how?
127 points45 comments
YRSchaeffer ·
Overcoming Catastrophic Forgetting in Neural Networks
123 points11 comments
Yjweissman ·
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
60 points6 comments
YOsiris30 ·
DeepMind just posted a mind blowing paper – achievement of transfer learning
56 points12 comments
YMichaelBurge ·
DeepMind just published a mind blowing paper: PathNet
37 points6 comments
Yheydenberk ·
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
3 points0 comments
Ydanm07 ·
DeepMind's PathNet – potentially describing how general AI will look like
1 points0 comments