A neural network approximates the velocity field of log-homotopy particle flow by enforcing a derived master PDE from the continuity equation, enabling unsupervised amortized Bayesian updates with reduced stiffness.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Laplace approximation and MCMC are compared for Bayesian uncertainty quantification in hybrid γ-ray spectral unmixing, with MCMC remaining accurate when constraints activate or background dominates.
citing papers explorer
-
Physics-informed neural particle flow for the Bayesian update step
A neural network approximates the velocity field of log-homotopy particle flow by enforcing a derived master PDE from the continuity equation, enabling unsupervised amortized Bayesian updates with reduced stiffness.
-
Bayesian approach for uncertainty quantification of hybrid spectral unmixing in $\gamma$-ray spectrometry
Laplace approximation and MCMC are compared for Bayesian uncertainty quantification in hybrid γ-ray spectral unmixing, with MCMC remaining accurate when constraints activate or background dominates.