Deep learning generalizes because the parameter-function map is biased towards simple functions - researchr publication

researchr

You are not signed in
Sign in
Sign up

Guillermo Valle Pérez, Chico Q. Camargo, Ard A. Louis. Deep learning generalizes because the parameter-function map is biased towards simple functions. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net, 2019. [doi]

Abstract is missing.

runs on WebDSL