Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks
BibSLEIGH corpus
BibSLEIGH tags
BibSLEIGH bundles
BibSLEIGH people
EDIT!
CC-BY
Open Knowledge
XHTML 1.0 W3C Rec
CSS 2.1 W3C CanRec
email twitter

Lechao Xiao, Yasaman Bahri, Jascha Sohl-Dickstein, Samuel S. Schoenholz, Jeffrey Pennington
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks
ICML, 2018.

ICML 2018
DBLP
Scholar
?EE?
Full names Links ISxN
@inproceedings{ICML-2018-XiaoBSSP,
	author        = "Lechao Xiao and Yasaman Bahri and Jascha Sohl-Dickstein and Samuel S. Schoenholz and Jeffrey Pennington",
	booktitle     = "{Proceedings of the 35th International Conference on Machine Learning}",
	ee            = "http://proceedings.mlr.press/v80/xiao18a.html",
	pages         = "5389--5398",
	publisher     = "{PMLR}",
	title         = "{Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks}",
	year          = 2018,
}

Tags:



Bibliography of Software Language Engineering in Generated Hypertext (BibSLEIGH) is created and maintained by Dr. Vadim Zaytsev.
Hosted as a part of SLEBOK on GitHub.