BARNN converts autoregressive and recurrent networks into Bayesian versions via time-dependent variational dropout and a temporal aggregated-posterior prior, yielding calibrated uncertainty on PDE and molecule-generation tasks.
An Essay towards solving a Problem in the Doctrine of Chances
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
-
BARNN: A Bayesian Autoregressive and Recurrent Neural Network
BARNN converts autoregressive and recurrent networks into Bayesian versions via time-dependent variational dropout and a temporal aggregated-posterior prior, yielding calibrated uncertainty on PDE and molecule-generation tasks.