Comparison and Evaluation of Different Methods for Uncertainty Quantification in Machine Learning
Principal Investigator
Name
Katharina Juliane Lempe
Degrees
B.Sc.
Institution
Universität Leipzig, Medizinische Fakultät, Innovation Center Computer Assisted Surgery
Position Title
master student
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-1763
Initial CDAS Request Approval
Dec 16, 2024
Title
Comparison and Evaluation of Different Methods for Uncertainty Quantification in Machine Learning
Summary
Different methods for uncertainty quantification will be compared to find out which method works the best. This is supposed to help make machine learning safer and easier to use, for example in the health care sector. The methods are supposed to be tested on the PLCO data, to ensure that they work on real life data, not just test sets.
Aims
- compare and evaluate different methods for uncertainty quantification
- evaluate pros and cons of each method
- ensure real life applicability
Collaborators
Johannes Keller
Dr. Daniel Schneider
Prof. Dr. Thomas Neumuth
(Universität Leipzig, Medizinische Fakultät, Innovation Center Computer Assisted Surgery)