36 citations · 66 across the 3 of their papers we have counts for
3 papers · 1 filter
Tandem Blocks in Deep Convolutional Neural Networks
Chris Hettinger, Tanner Christensen, Jeffrey Humpherys +1
Due to the success of residual networks (resnets) and related architectures, shortcut connections have quickly become standard tools for building convolutional neural networks. The…
Forward Thinking: Building and Training Neural Networks One Layer at a Time
Chris Hettinger, Tanner Christensen, Ben Ehlert +3
We present a general framework for training deep neural networks without backpropagation. This substantially decreases training time and also allows for construction of deep networ…
Forward Thinking: Building Deep Random Forests
Kevin Miller, Chris Hettinger, Jeffrey Humpherys +2
The success of deep neural networks has inspired many to wonder whether other learners could benefit from deep, layered architectures. We present a general framework called forward…