Re:AlphaGo beats the world champion Lee Sedol in first of fi...
by argonaut on Wednesday March 09, 2016 @04:27PM
(#11255846)
Even without the neural net system, AI is able to beat most amateurs, and predict moves experts would make.
Re:AlphaGo beats the world champion Lee Sedol in first of fi...
by Houshalter on Thursday March 10, 2016 @02:23PM
(#11261481)
I'm not sure that's correct. MCTS has well known weaknesses, and isn't even a predictive algorithm. MCTS on it's own couldn't get anywhere near beating the top Go champion, that requires deepminds neural networks.
Re:AlphaGo beats the world champion Lee Sedol in first of fi...
by argonaut on Friday March 11, 2016 @07:55AM
(#11266304)
http://www.milesbrundage.com/blog-posts/alphago-and-ai-progr...
The best Go program before AlphaGo was CrazyStone, ranked at 5-dan ("high amateur" range).
Re:AlphaGo beats the world champion Lee Sedol in first of fi...
by Houshalter on Friday March 11, 2016 @03:25PM
(#11269241)
There's a massive skill difference between ameatures and professionals. It couldn't even beat the top ameatures.
Likewise NNs are uncaring what application you put them into. Give them a different input and a different goal, and they will learn to do that instead. Alphago gave it's NN's control over a monte carlo search tree, and that turned out to be enough to beat Go. They could plug the same AI into a car and it would learn to control that instead.
Note that even without the monte carlo search system, it was able to beat most amateurs, and predict the moves experts would make most of the time.