Re:AlphaGo Zero: Learning from scratch
by waqf on Wednesday October 18, 2017 @07:07PM
(#15504062)
AlphaGo is still based around layers of 3×3 local convolutions.
That represents a strong assumption about locality in the network design. I would expect AlphaGo to perform poorly on the game "Go with the vertices randomly permuted".
That represents a strong assumption about locality in the network design. I would expect AlphaGo to perform poorly on the game "Go with the vertices randomly permuted".