Experiments show that shifted-ReLU layers can replace batch-normalization in single-bit-weight wide residual networks on CIFAR-10/100 and ImageNet without consistent accuracy penalty.
Weight normalization: A simple reparam- eterization to accelerate training of deep neural networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems
Experiments show that shifted-ReLU layers can replace batch-normalization in single-bit-weight wide residual networks on CIFAR-10/100 and ImageNet without consistent accuracy penalty.