WAGEUBN trains ResNet models on ImageNet using 8-bit integers for weights, activations, gradients, errors, batch normalization, and the Momentum optimizer, with moderate accuracy loss.
A unified archi- tecture for natural language processing: Deep neural networks with multitask learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers
WAGEUBN trains ResNet models on ImageNet using 8-bit integers for weights, activations, gradients, errors, batch normalization, and the Momentum optimizer, with moderate accuracy loss.