Hacker News new | past | comments | ask | show | jobs | submit login

David Silver of Google DeepMind has stated that the program has not been specifically trained using Lee's previous games.

"specifically" Not that he was not trained on his games at all




It was in the press conference for Game 4 IIRC.


Also in the pre-game commentary for game 3.

It was mentioned that AlphaGo was trained on so many games that the games of Lee Sedol that were used for training were not more than a drop in the ocean. This was the answer to the question about whether AlphaGo was trained specifically against Lee Sedol.


Demis was asked about this, training AlphaGo with Lee Sedol's games and said that it would take tens of thousands of games to make any difference.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: