I was confused at first by this second term not having the summation, and then realized it was intentional when Andrew points it out at at the point that I screenshotted below.
Could someone explain though why this is dropped?
I was confused at first by this second term not having the summation, and then realized it was intentional when Andrew points it out at at the point that I screenshotted below.
Could someone explain though why this is dropped?
Whoops, my apologies. I probably should of spent more time searching as I see this was already answered here: Derivative of regularization term - #2 by shanup