loss function
1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement May 9, 2018 by Carola Schönlieb · across every show →
Everything said about loss function, oldest first
May 9, 2018 neutral
Schönlieb: Exactly minimizing training loss often hurts neural network generalization
“You do not necessarily need to solve your optimization problem, your training exactly. And maybe sometimes, or most of the time you actually don't want it, want to save it exactly because you only have a finite amount of training examples. And so when you thin…”