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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The ability to replicate predictions by machine learning (ML) or artificialintelligence (AI) models and results in scientific workflows that incorporatesuch ML/AI predictions is driven by numerous factors. An uncertainty-awaremetric that can quantitatively assess the reproducibility of quantities ofinterest (QoI) would contribute to the trustworthiness of results obtained fromscientific workflows involving ML/AI models. In this article, we discuss howuncertainty quantification (UQ) in a Bayesian paradigm can provide a generaland rigorous framework for quantifying reproducibility for complex scientificworkflows. Such as framework has the potential to fill a critical gap thatcurrently exists in ML/AI for scientific workflows, as it will enableresearchers to determine the impact of ML/AI model prediction variability onthe predictive outcomes of ML/AI-powered workflows. We expect that theenvisioned framework will contribute to the design of more reproducible andtrustworthy workflows for diverse scientific applications, and ultimately,accelerate scientific discoveries.

A Rigorous Uncertainty-Aware Quantification Framework Is Essential for Reproducible and Replicable Machine Learning Workflows