It would be very convenient (though mind-numbingly boring) if the content of our days was just a simple interpolation of things we had experienced hundreds of times before. We could train a deep learning model to replace us!
-
-
Machine learning is about fitting to a static distribution -- human learning is about gathering knowledge that may turn out to be useful in a future that is guaranteed to share little commonality with the past.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Love it.. btw, your last avatar pic was way better. Yes, mine's terrible too
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Very true words!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Profound statement that, unfortunately, is not true.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
We naturally solve 4d schema invariance. It's an incredible feat. Solving AGI is solving how we create and use these 4d schema.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Can one truly be sure of the uniqueness. What if the perceived novelty of everyday is really an interpolation in an unknown complex manifold.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
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.