SQS is a new GLU activation that reportedly preserves bilinear weight spectra for interpretability while achieving competitive performance on MNIST, FMNIST, and Tiny Stories.
The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Preserving Bilinear Weight Spectra with a Signed and Shrunk Quadratic Activation Function
SQS is a new GLU activation that reportedly preserves bilinear weight spectra for interpretability while achieving competitive performance on MNIST, FMNIST, and Tiny Stories.