SG-Blend, a learnable convex combination of a shifted Swish and GELU, reports modest accuracy and BLEU gains on CIFAR-10, IMDB, and a WMT14 subset, with no variance reporting.
Learning Multiple Layers of Features from Tiny Images , 1 2009
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SG-Blend: Learning an Interpolation Between Improved Swish and GELU for Robust Neural Representations
SG-Blend, a learnable convex combination of a shifted Swish and GELU, reports modest accuracy and BLEU gains on CIFAR-10, IMDB, and a WMT14 subset, with no variance reporting.