Intelligence is the degree of efficiency with which a learning system turns experience (data) into generalizable programs. I = G / E In AI, "system" should be understood as including the human engineers. Most of the "data -> generalization" conversion happens during model design
-
-
something in the lines of Galois connection?
-
I ping
@MonniauxD on that topic, he knows abstraction better than me I'm sure
End of conversation
New conversation -
-
-
Cf Kurt Gödel.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
What do you have in mind?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Category Theory is known as abstract general nonsense
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
One approach might be: 1 - formulate AI system as a mapping 2 - select method to quantify degree of mapping invariance accross spaces 3 - define set of spaces which span set of “general” problems we care about 4 - compute ave degree of mapping invariance across those spaces
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.