Some GLU variants using non-sigmoid nonlinearities improve Transformer quality over ReLU and GELU in feed-forward sublayers.
Deep sparse rectifier neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2020 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GLU Variants Improve Transformer
Some GLU variants using non-sigmoid nonlinearities improve Transformer quality over ReLU and GELU in feed-forward sublayers.