A domain-adversarial objective over random halves of a single training set is proposed as a general-purpose neural network regularizer, with mixed empirical support across benchmarks.
The effects of adding noise during backprop- agation training on a generalization performance
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization
A domain-adversarial objective over random halves of a single training set is proposed as a general-purpose neural network regularizer, with mixed empirical support across benchmarks.