Uncertainty Quantification by Ensemble Learning for Computational Optical Form Measurements

03/01/2021
by   Lara Hoffmann, et al.
0

Uncertainty quantification by ensemble learning is explored in terms of an application from computational optical form measurements. The application requires to solve a large-scale, nonlinear inverse problem. Ensemble learning is used to extend a recently developed deep learning approach for this application in order to provide an uncertainty quantification of its predicted solution to the inverse problem. By systematically inserting out-of-distribution errors as well as noisy data the reliability of the developed uncertainty quantification is explored. Results are encouraging and the proposed application exemplifies the ability of ensemble methods to make trustworthy predictions on high dimensional data in a real-world application.

READ FULL TEXT

page 4

page 21

research
09/13/2021

Minimum Discrepancy Methods in Uncertainty Quantification

The lectures were prepared for the École Thématique sur les Incertitudes...
research
04/27/2020

Workshop on Quantification, Communication, and Interpretation of Uncertainty in Simulation and Data Science

Modern science, technology, and politics are all permeated by data that ...
research
02/13/2020

Simple and Accurate Uncertainty Quantification from Bias-Variance Decomposition

Accurate uncertainty quantification is crucial for many applications whe...
research
11/04/2022

Multi-output Gaussian processes for inverse uncertainty quantification in neutron noise analysis

In a fissile material, the inherent multiplicity of neutrons born throug...
research
07/01/2020

Deep Neural Networks for Computational Optical Form Measurements

Deep neural networks have been successfully applied in many different fi...
research
06/26/2022

Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection

Out-of-distribution (OOD) detection has recently received much attention...

Please sign up or login with your details

Forgot password? Click here to reset