A bounded softlog transform between softmax layers is proposed for ensemble learning along with a bounded divergence and a performance tensor, but the claimed benefits are not compared against standard softmax ensembles.
Zero-shot neural architecture search: Challenges, solutions, and opportunities,
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
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Softlog-Softmax Layers and Divergences Contribute to a Computationally Dependable Ensemble Learning
A bounded softlog transform between softmax layers is proposed for ensemble learning along with a bounded divergence and a performance tensor, but the claimed benefits are not compared against standard softmax ensembles.