← Search

Taewook Nam

2 accepted papers

2020

Meta Dropout: Learning to Perturb Latent Features for Generalization

ICLR 2020poster

A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we know how to optimally perturb training examples to account for test examples, we may achieve better generalization performance. However, obtaining such perturbation is not possible in standar…

Cited by 60SourcecodeScholar