Interesting! To concretize the metaphor, would a merger between two different learning networks ... two disparate datasets ... be like a weld? Would the ability to delete portions of the net & outputs be like lathing?
-
-
-
I am a big fan of the idea of growing models
- 1 more reply
New conversation -
-
-
Someone needs to invent conviction learning. ML with prior conviction about the world
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.