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 this work, we demonstrate how to reliably estimate epistemic uncertaintywhile maintaining the flexibility needed to capture complicated aleatoricdistributions. To this end, we propose an ensemble of Normalizing Flows (NF),which are state-of-the-art in modeling aleatoric uncertainty. The ensembles arecreated via sets of fixed dropout masks, making them less expensive thancreating separate NF models. We demonstrate how to leverage the uniquestructure of NFs, base distributions, to estimate aleatoric uncertainty withoutrelying on samples, provide a comprehensive set of baselines, and deriveunbiased estimates for differential entropy. The methods were applied to avariety of experiments, commonly used to benchmark aleatoric and epistemicuncertainty estimation: 1D sinusoidal data, 2D windy grid-world ($\it{WetChicken}$), $\it{Pendulum}$, and $\it{Hopper}$. In these experiments, we setupan active learning framework and evaluate each model's capability at measuringaleatoric and epistemic uncertainty. The results show the advantages of usingNF ensembles in capturing complicated aleatoric while maintaining accurateepistemic uncertainty estimates.

Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling