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

Farquhar et al. [2021] show that correcting for active learning bias withunderparameterised models leads to improved downstream performance. Foroverparameterised models such as NNs, however, correction leads either todecreased or unchanged performance. They suggest that this is due to an"overfitting bias" which offsets the active learning bias. We show that depthuncertainty networks operate in a low overfitting regime, much likeunderparameterised models. They should therefore see an increase in performancewith bias correction. Surprisingly, they do not. We propose that this negativeresult, as well as the results Farquhar et al. [2021], can be explained via thelens of the bias-variance decomposition of generalisation error.

Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not