Search Results for author: Richard Mudd

Found 2 papers, 1 papers with code

Active learning with biased non-response to label requests

no code implementations13 Dec 2023 Thomas Robinson, Niek Tax, Richard Mudd, Ido Guy

We conceptualise this degradation by considering the type of non-response present in the data, demonstrating that biased non-response is particularly detrimental to model performance.

Active Learning

TCE: A Test-Based Approach to Measuring Calibration Error

1 code implementation25 Jun 2023 Takuo Matsubara, Niek Tax, Richard Mudd, Ido Guy

This paper proposes a new metric to measure the calibration error of probabilistic binary classifiers, called test-based calibration error (TCE).

Cannot find the paper you are looking for? You can Submit a new open access paper.