Re:AlphaGo shows its true strength in 3rd victory against Le...
by asdfologist on Saturday March 12, 2016 @04:01PM
(#11274530)
But in this case, the training data consists of human games, which are flawed. Supervising with flawed data can have unpredictable results.
[ Parent
| on HN ]
Re:AlphaGo shows its true strength in 3rd victory against Le...
by pixl97 on Saturday March 12, 2016 @05:28PM
(#11274953)
That depends on the reasons that humans make flaws. If human flaws are mostly errors related to failures in our meat (stress, lack of focus, jittery nerves) that keep us from looking in depth then the algorithm will easily use the good points in each game and with its superior ability to look deep into the future the results are predictable that the machine will win every time.
Re:AlphaGo shows its true strength in 3rd victory against Le...
by seanwilson on Saturday March 12, 2016 @10:05PM
(#11275985)
I think flawed is a strong word. It's likely humans are stuck in locally optimised strategies though.