1 code implementation • 31 Oct 2023 • Guoxuan Xia, Duolikun Danier, Ayan Das, Stathi Fotiadis, Farhang Nabiei, Ushnish Sengupta, Alberto Bernacchia
As a simple fix, we propose to instead reparameterise the score (at inference) by dividing it by the average absolute value of previous score estimates at that time step collected from offline high NFE generations.
no code implementations • 10 Aug 2023 • Ushnish Sengupta, Chinkuo Jao, Alberto Bernacchia, Sattar Vakili, Da-Shan Shiu
In this paper, we propose a diffusion model based channel sampling approach for rapidly synthesizing channel realizations from limited data.
no code implementations • NeurIPS Workshop Deep_Invers 2021 • Maximilian L. Croci, Ushnish Sengupta, Matthew P Juniper
The ensemble learns a surrogate of the approximate Bayesian posterior of the parameters given the observations, from which the flame can be re-simulated beyond the observation window of the experiment.
no code implementations • 16 Jul 2021 • Ushnish Sengupta, Alexandros Kontogiannis, Matthew P. Juniper
In this paper, we present a physics-informed neural network that instead uses the noisy MRV data alone to simultaneously infer the most likely boundary shape and de-noised velocity field.
no code implementations • 1 Jul 2021 • Ushnish Sengupta, Günther Waxenegger-Wilfing, Jan Martin, Justin Hardi, Matthew P. Juniper
The 100 MW cryogenic liquid oxygen/hydrogen multi-injector combustor BKD operated by the DLR Institute of Space Propulsion is a research platform that allows the study of thermoacoustic instabilities under realistic conditions, representative of small upper stage rocket engines.
1 code implementation • 26 Apr 2021 • Maximilian L. Croci, Ushnish Sengupta, Matthew P. Juniper
Heteroscedastic Bayesian neural network ensembles are trained on a library of 1. 7 million flame fronts simulated in LSGEN2D, a G-equation solver, to learn the Bayesian posterior distribution of the model parameters given observations.
no code implementations • 25 Nov 2020 • Günther Waxenegger-Wilfing, Ushnish Sengupta, Jan Martin, Wolfgang Armbruster, Justin Hardi, Matthew Juniper, Michael Oschwald
In most cases, the method is able to timely predict two types of thermoacoustic instabilities on test data not used for training.
no code implementations • 11 Oct 2020 • Ushnish Sengupta, Maximilian L. Croci, Matthew P. Juniper
The trained neural networks are then used to infer model parameters from real videos of a premixed Bunsen flame captured using a high-speed camera in our lab.
1 code implementation • NeurIPS 2020 • Ushnish Sengupta, Matt Amos, J. Scott Hosking, Carl Edward Rasmussen, Matthew Juniper, Paul J. Young
Ensembles of geophysical models improve projection accuracy and express uncertainties.