阿法狗團隊說了,他們沒有作任何改變,一切都由狗自學調整,而且自學到什麽程度他們也不知,隻能用實戰檢驗。
所有跟帖:
•
至於78手,是policy network的決策,這一手的可能性是萬分之一,所以沒有作深度計算。
-talkatwxc-
♂
(0 bytes)
()
03/15/2016 postreply
07:10:22
•
a lot of people don't know the difference between DeepBlue and A
-Maike369-
♂
(69 bytes)
()
03/15/2016 postreply
07:12:37
•
CC
-八卦流星錘-
♂
(22652 bytes)
()
03/15/2016 postreply
07:34:01
•
check what IBM said.
-Maike369-
♂
(148 bytes)
()
03/15/2016 postreply
08:21:33
•
同意。 這就是ibm and deepmind 的不同。Demis Hassabis is an neuroscientist
-temptemp-
♀
(39 bytes)
()
03/16/2016 postreply
12:01:59
•
Go is not their final purpose.
-Maike369-
♂
(96 bytes)
()
03/15/2016 postreply
07:10:49
•
more than that. they are after the future.
-temptemp-
♀
(0 bytes)
()
03/16/2016 postreply
12:03:11