NSAC reformulates attention logit computation as the solution of an Ornstein-Uhlenbeck SDE with input-dependent nonlinear gates from NCPs to induce Gaussian distributions over logits and logistic-normal distributions over attention weights for joint aleatoric and epistemic uncertainty quantification
Sde-net: Equipping deep neural networks with uncertainty esti- mates.arXiv preprint arXiv:2008.10546,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Numerical study comparing feedforward NN and DeepONet with data-driven and physics-informed losses on stochastic heat equation, highlighting larger errors at distribution tails due to extrapolation.
citing papers explorer
-
A numerical study into neural network surrogate model performance for uncertainty propagation
Numerical study comparing feedforward NN and DeepONet with data-driven and physics-informed losses on stochastic heat equation, highlighting larger errors at distribution tails due to extrapolation.