1 citations · 1 across the 3 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021★ 1 cited
Learning DNN networks using un-rectifying ReLU with compressed sensing application
Wen-Liang Hwang, Shih-Shuo Tung
The un-rectifying technique expresses a non-linear point-wise activation function as a data-dependent variable, which means that the activation variable along with its input and ou…
cs.LG2019
Deep Representation with ReLU Neural Networks
Andreas Heinecke, Wen-Liang Hwang
We consider deep feedforward neural networks with rectified linear units from a signal processing perspective. In this view, such representations mark the transition from using a s…