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

Despite successful use in a wide variety of disciplines for data analysis andprediction, machine learning (ML) methods suffer from a lack of understandingof the reliability of predictions due to the lack of transparency and black-boxnature of ML models. In materials science and other fields, typical ML modelresults include a significant number of low-quality predictions. This problemis known to be particularly acute for target systems which differ significantlyfrom the data used for ML model training. However, to date, a general methodfor characterization of the difference between the predicted and trainingsystem has not been available. Here, we show that a simple metric based onEuclidean feature space distance and sampling density allows effectiveseparation of the accurately predicted data points from data points with poorprediction accuracy. We show that the metric effectiveness is enhanced by thedecorrelation of the features using Gram-Schmidt orthogonalization. Todemonstrate the generality of the method, we apply it to support vectorregression models for various small data sets in materials science and otherfields. Our method is computationally simple, can be used with any ML learningmethod and enables analysis of the sources of the ML prediction errors.Therefore, it is suitable for use as a standard technique for the estimation ofML prediction reliability for small data sets and as a tool for data setdesign.

Distance-based Analysis of Machine Learning Prediction Reliability for Datasets in Materials Science and Other Fields