A thought about that impressive article:
Move prediction has become the bot workhorse. But I have a question: how
can those predictions work, without having a goal? The predictions are
obviously purely shape based, so a 41% success rate is really pretty
awesome. But that means that some positions,
CGF Open(Computer Go tournament in Japan) was held on October 3rd-4th.
Ray won in 9x9. Ray's author is Yuki Kobayashi. He is a UEC student,
and he has started Go programming since last year. He said Ray got
stronger recently by using Latent Factor Ranking insted of MM.
Move Prediction in Go,
Hi Hiroshi,
thanks for the info, and congratulations to "your"
win on 19x19-board.
Ingo.
> Gesendet: Montag, 19. Oktober 2015 um 13:31 Uhr
> Von: "Hiroshi Yamashita" <y...@bd.mbn.or.jp>
> An: computer-go@computer-go.org
> Betreff: [Computer-go] CGF Ope