v1v2 (latest)

DiracNets: Training Very Deep Neural Networks Without Skip-Connections

1 June 2017

Papers citing "DiracNets: Training Very Deep Neural Networks Without Skip-Connections"

2 / 52 papers shown

Title
EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks Xuanyi Dong Guoliang Kang Kun Zhan Yi Yang 64 16 0 22 Sep 2017
The Shattered Gradients Problem: If resnets are the answer, then what is the question? David Balduzzi Marcus Frean Lennox Leary J. P. Lewis Kurt Wan-Duo Ma Brian McWilliams ODL 95 407 0 28 Feb 2017