Quantifying predictive uncertainty in damage classification for nondestructive evaluation using Bayesian approximation and deep learning

DOI10.1088/1361-6420/AD2F63MaRDI QIDQ6557656FDOQ6557656

Authors: Zi Li, Yiming Deng 

Publication date: 18 June 2024

Published in: Inverse Problems (Search for Journal in Brave)

zbMATH Keywords

deep learninguncertainty quantificationmagnetic flux leakageBayesian approximationinverse NDE

Mathematics Subject Classification ID

Basic linear algebra (15Axx) Artificial intelligence (68Txx) Computer science (68-XX)

Cites Work

• Bagging predictors
• Title not available (Why is that?)
• Quantitative nondestructive evaluation
• MCMC-based image reconstruction with uncertainty quantification
• Uncertainty quantification using Bayesian neural networks in classification: application to biomedical image segmentation

Cited In (1)

• New trends in electromagnetic inverse problems

This page was built for publication: Quantifying predictive uncertainty in damage classification for nondestructive evaluation using Bayesian approximation and deep learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6557656)