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

Neural Linear Models (NLM) are deep Bayesian models that produce predictiveuncertainties by learning features from the data and then performing Bayesianlinear regression over these features. Despite their popularity, few works havefocused on methodically evaluating the predictive uncertainties of thesemodels. In this work, we demonstrate that traditional training procedures forNLMs drastically underestimate uncertainty on out-of-distribution inputs, andthat they therefore cannot be naively deployed in risk-sensitive applications.We identify the underlying reasons for this behavior and propose a noveltraining framework that captures useful predictive uncertainties for downstreamtasks.

Uncertainty-Aware (UNA) Bases for Deep Bayesian Regression Using Multi-Headed Auxiliary Networks