ResearchTrend.AI
The role of a layer in deep neural networks: a Gaussian Process perspective

The role of a layer in deep neural networks: a Gaussian Process perspective

Oded Ben-David
Zohar Ringel
ArXivPDFHTML

Papers citing "The role of a layer in deep neural networks: a Gaussian Process perspective"

1 / 1 papers shown
Title
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
Lechao Xiao
Yasaman Bahri
Jascha Narain Sohl-Dickstein
S. Schoenholz
Jeffrey Pennington
260
351
0
14 Jun 2018