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

Robust machine learning models with accurately calibrated uncertainties arecrucial for safety-critical applications. Probabilistic machine learning andespecially the Bayesian formalism provide a systematic framework to incorporaterobustness through the distributional estimates and reason about uncertainty.Recent works have shown that approximate inference approaches that take theweight space uncertainty of neural networks to generate ensemble prediction arethe state-of-the-art. However, architecture choices have mostly been ad hoc,which essentially ignores the epistemic uncertainty from the architecturespace. To this end, we propose a Unified probabilistic architecture and weightensembling Neural Architecture Search (UraeNAS) that leverages advances inprobabilistic neural architecture search and approximate Bayesian inference togenerate ensembles form the joint distribution of neural network architecturesand weights. The proposed approach showed a significant improvement both within-distribution (0.86% in accuracy, 42% in ECE) CIFAR-10 andout-of-distribution (2.43% in accuracy, 30% in ECE) CIFAR-10-C compared to thebaseline deterministic approach.

Unified Probabilistic Neural Architecture and Weight Ensembling Improves Model Robustness