Log-Gaussian Gamma Processes for Training Bayesian Neural Networks in Raman and CARS Spectroscopies

no code implementations • 12 Oct 2023 • Teemu Härkönen, Erik M. Vartiainen, Lasse Lensu, Matthew T. Moores, Lassi Roininen

We train two Bayesian neural networks to estimate parameters of the gamma process which can then be used to estimate the underlying Raman spectrum and simultaneously provide uncertainty through the estimation of parameters of a probability distribution.

Gaussian Processes Synthetic Data Generation