Neural Architecture Search with Reinforcement Learning

Re:Neural Architecture Search with Reinforcement Learning by deepnotderp on Thursday January 19, 2017 @05:36PM (#13440117)

This is pretty old, and neural nets can train neural nets too (better than humans as usual). Check learning to learn w/ gradient descent by gradient descent

[ Parent | on HN ]

Re:Neural Architecture Search with Reinforcement Learning by westoncb on Thursday January 19, 2017 @05:49PM (#13440202)

Err.. this paper cites the one you're referring to, so I do not think it's older (also, the dates they were published).

[ Parent | on HN ]

Re:Neural Architecture Search with Reinforcement Learning by deepnotderp on Thursday January 19, 2017 @08:17PM (#13441008)

(Learning to learn is older, I just thought it would be cool)

[ Parent | on HN ]