Ask HN: Can we adapt AlphaZero's self-play technique for better human learning?

Re:Ask HN: Can we adapt AlphaZero's self-play technique for ... by jdoliner on Friday December 08, 2017 @07:15PM (#15883290)

That wasn't who I had in mind, but thanks for sharing that example. I think the guy I'm thinking of is at Cornell and still alive. He also might actually be in CS instead of Math. I tried googling it but, unfortunately, "math professor who doesn't read papers" didn't come up with any results.

[ Parent | on HN ]

Re:Ask HN: Can we adapt AlphaZero's self-play technique for ... by sabalaba on Saturday December 09, 2017 @12:32AM (#15884479)

Shinichi Mochizuki developed a new theory (IUT) which eventually yielded a proof to the abc conjecture. I believe he largely developed it in isolation and thus when it was published it took years to bring the rest of the community up to speed. Not sure if he doesn’t read other’s papers but maybe this is what’s you were thinking about?

1. https://en.wikipedia.org/wiki/Shinichi_Mochizuki

2. https://en.wikipedia.org/wiki/Inter-universal_Teichm%C3%BCll...

3. https://en.wikipedia.org/wiki/Abc_conjecture

[ Parent | on HN ]

Re:Ask HN: Can we adapt AlphaZero's self-play technique for ... by ararar on Monday December 11, 2017 @07:36AM (#15896651)

You might be thinking of R.L. Moore and his "Moore Method" except it was only used in a teaching context, not in day to day work. See https://en.wikipedia.org/wiki/Moore_method

[ Parent | on HN ]

Re:Ask HN: Can we adapt AlphaZero's self-play technique for ... by SamReidHughes on Tuesday December 19, 2017 @02:00AM (#15958315)

Maybe it was a physics professor.

[ Parent | on HN ]