Variable-depth, residual-like networks generalize better than fixed-depth networks of matched average nonlinear depth, even when optimization differences are minimized.
Bach, Thomas Hofmann, and Aur \' e lien Lucchi
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
-
ResNets Are Deeper Than You Think
Variable-depth, residual-like networks generalize better than fixed-depth networks of matched average nonlinear depth, even when optimization differences are minimized.