Neural Architecture Search with Reinforcement Learning

Re:Neural Architecture Search with Reinforcement Learning by jordansmithnz on Thursday January 19, 2017 @08:21PM (#13441020)

Wait... if the neural net can design other neural nets, can it be taught to design itself?

[ Parent | on HN ]

Re:Neural Architecture Search with Reinforcement Learning by mastazi on Thursday January 19, 2017 @08:48PM (#13441156)

Ironically, this is one of the oldest ideas in computer science https://en.wikipedia.org/wiki/Von_Neumann_universal_construc...

[ Parent | on HN ]

Re:Neural Architecture Search with Reinforcement Learning by Houshalter on Thursday January 19, 2017 @09:19PM (#13441290)

Von Neumanns constructor is about self replication. Not quite an AI that can self improve.

I think the first person to put the idea forward was I. J. Good in 1962. He speculated that someday AIs would be good enough to do AI research better than their human masters. Then they would start making even better AIs. Which would make even better AIs, and so on. Leading to what he called an "intelligence explosion". He thought it would be "the last invention that man need ever make."

http://web.archive.org/web/20160428183531/http://le-cretin-t...

[ Parent | on HN ]

Re:Neural Architecture Search with Reinforcement Learning by mastazi on Sunday January 22, 2017 @02:32AM (#13454133)

Parent's comment was about self-replication, I was addressing that.

[ Parent | on HN ]

Re:Neural Architecture Search with Reinforcement Learning by EvgeniyZh on Sunday January 22, 2017 @06:50AM (#13454812)

Can it be taught to design a better version of itself?

[ Parent | on HN ]