Google AlphaGo—who is the real winner? http://gu.com/p/4g895/stw True but all ML to date uses more data than any human consumes for same task.
@stevesi AG only trained on 30,000 games. Not so different than what a human masters studies - amounts to ~ 8 games a day for 10 years
-
-
@michael_nielsen 30M moves I thought? ~150K games? -
@stevesi Oh, that's my mistake, you're right. Still, same order of magnitude as many Go masters, I expect. Not like Deep Blue & endgames, sy
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.