λ-GELU learns layer-wise hardness parameters via constrained reparameterization to allow controlled post-training conversion from smooth GELU to ReLU activations.
Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
$\lambda$-GELU: Learning Gating Hardness for Controlled ReLU-ization in Deep Networks
λ-GELU learns layer-wise hardness parameters via constrained reparameterization to allow controlled post-training conversion from smooth GELU to ReLU activations.