buybuydandavis comments on Green Emeralds, Grue Diamonds - Less Wrong Discussion
You are viewing a comment permalink. View the original post to see all comments and the full post content.
You are viewing a comment permalink. View the original post to see all comments and the full post content.
Comments (20)
"So the naturalness of the category depended on the type of evidence we expected to find."
Reminds me of the No Free Lunch theorems of David Wolpert, particularly the basic NFL for learning algorithms. Basically, there is no a priori distinction between learning algorithms, and the actual performance is determined by the "fit" of the algorithm to the problem.