2 papers
stat.CO2026
Heteroscedastic Neural Surrogate Modeling for Robust and Rapid Bayesian Inference in Fusion Plasma Diagnostics
Liyun Zhang, Naoya Mamada, Kentaro Sakai +2
Bayesian inference via Markov Chain Monte Carlo (MCMC) provides effective parameter estimation, but its real-time application in complex physical systems is hindered by heavy compu…
cond-mat.mtrl-sci2023
Detection of Non-uniformity in Parameters for Magnetic Domain Pattern Generation by Machine Learning
Naoya Mamada, Masaichiro Mizumaki, Ichiro Akai +1
We estimate the spatial distribution of heterogeneous physical parameters involved in the formation of magnetic domain patterns of polycrystalline thin films by using convolutional…