English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In safety-critical domains such as autonomous driving and medical diagnosis,the reliability of machine learning models is crucial. One significantchallenge to reliability is concept drift, which can cause model deteriorationover time. Traditionally, drift detectors rely on true labels, which are oftenscarce and costly. This study conducts a comprehensive empirical evaluation ofusing uncertainty values as substitutes for error rates in detecting drifts,aiming to alleviate the reliance on labeled post-deployment data. We examinefive uncertainty estimation methods in conjunction with the ADWIN detectoracross seven real-world datasets. Our results reveal that while the SWAG methodexhibits superior calibration, the overall accuracy in detecting drifts is notnotably impacted by the choice of uncertainty estimation method, with even themost basic method demonstrating competitive performance. These findings offervaluable insights into the practical applicability of uncertainty-based driftdetection in real-world, safety-critical applications.

An Empirical Study of Uncertainty Estimation Techniques for Detecting Drift in Data Streams