3 votes

How to comment on goodness of loss functions?

A loss being less than another loss has nothing to do with its usefulness. You can simply subtract a constant from a loss to obtain another loss (i.e. $\mathcal{L}_2 = \mathcal{L}_1 - \alpha$) that is ...
noe's user avatar
  • 26.6k
1 vote

Applying dropout effectively in CNN

Firstly, why do we use dropout in the first place? Dropout is a regularization technique designed to improve generalization and prevent overfitting. With this in mind, you should not necessarily ...
Karl's user avatar
  • 636

Only top scored, non community-wiki answers of a minimum length are eligible