Semanlink - NLP@ENS ; DL: why does it work? AND DL: why does it work?

Printer friendly

Search Tag:

Search Doc:

Preferences...

Tag Cloud

Arxiv Doc - DL: why does it work? - Facebook FAIR - Information theory AND Deep Learning - Minimum Description Length Principle - NLP@ENS - Occam's razor - Overfitting/Generalization -

NLP@ENS ; DL: why does it work? AND DL: why does it work?

Common descendants

1 Document

[1802.07044] The Description Length of Deep Learning Models

Tags:

2019-10-11 About