We propose a re-calibration method for Machine Learning models, based on computing confidence intervals for the predicted confidence scores. We show the effectiveness of the proposed method on a COVID-19 diagnosis benchmark.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.3233/SHTI220413 | DOI Listing |
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!