no code implementations • ICLR 2018 • Chris Hettinger, Tanner Christensen, Jeffrey Humpherys, Tyler J. Jarvis
Due to the success of residual networks (resnets) and related architectures, shortcut connections have quickly become standard tools for building convolutional neural networks.
1 code implementation • 8 Jun 2017 • Chris Hettinger, Tanner Christensen, Ben Ehlert, Jeffrey Humpherys, Tyler Jarvis, Sean Wade
We present a general framework for training deep neural networks without backpropagation.