"After crossing an apparent critical value (between 1010 and 1011 effective parameters), the model seems to be catapulted into a new regime in which it can complete this (fairly complicated) task with drastically increased accuracy."
"The important part about this phenomenon is that we, a priori, do not know that this will happen in advance or even at what scale it might happen. "
1 comment
[ 3.1 ms ] story [ 17.4 ms ] thread"The important part about this phenomenon is that we, a priori, do not know that this will happen in advance or even at what scale it might happen. "