AI & machine learning2016 · shared on Hacker News
Reinforcement Learning Designed NNs Equal Human Performance
Explore Reinforcement Learning Designed NNs Equal Human Performance, 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.
Yrbanffy ·
Google.ai
611 points222 comments
Ysethbannon ·
Darpa Goes “Meta” with Machine Learning for Machine Learning (2016)
254 points109 comments
Yayanray ·
Tensorflow and Deep Learning, Without a PhD, Martin Gorner, Google [video]
218 points33 comments
Yhardmaru ·
Reinforcement Learning for Improving Agent Design
103 points6 comments
YMichaelBurge ·
Simplified Gating in Long Short-Term Memory (LSTM) Recurrent Neural Networks
49 points11 comments
Ynl ·
Reinforcement Learning Designed NNs Equal Human Performance
14 points0 comments
Yhardmaru ·
Neural Architecture Search with Reinforcement Learning (Google Brain)
3 points1 comments