20 citations · 82 across the 14 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019
Layerwise Noise Maximisation to Train Low-Energy Deep Neural Networks
Sébastien Henwood, François Leduc-Primeau, Yvon Savaria
Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the…
eess.IV2019
U-Net Fixed-Point Quantization for Medical Image Segmentation
MohammadHossein AskariHemmat, Sina Honari, Lucas Rouhier +4
Model quantization is leveraged to reduce the memory consumption and the computation time of deep neural networks. This is achieved by representing weights and activations with a l…