Browsing Titles index "Latent data augmentation and modular structure for improved generalization"
Now showing items 1-1 of 1
-
Latent data augmentation and modular structure for improved generalization
(2022-10-26)This thesis explores the nature of generalization in deep learning and several settings in which it fails. In particular, deep neural networks can struggle to generalize in settings with limited data, insufficient supervision, challenging long-range ...