Re:Show HN: Play Go Against a Deep Neural Network
by deepnet on Friday November 13, 2015 @11:42PM
(#10564492)
Since this neural net is trained to respond as a professional would to a given board state - could it be that a 'naive' or less sophisticated level of play would elucidate a matching level of response ?
Concretely, if the player plays worse does the net respond at that level ?
Concretely, if the player plays worse does the net respond at that level ?