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

With machine learning being a popular topic in current computationalmaterials science literature, creating representations for compounds has becomecommon place. These representations are rarely compared, as evaluating theirperformance - and the performance of the algorithms that they are used with -is non-trivial. With many materials datasets containing bias and skew caused bythe research process, leave one cluster out cross validation (LOCO-CV) has beenintroduced as a way of measuring the performance of an algorithm in predictingpreviously unseen groups of materials. This raises the question of the impact,and control, of the range of cluster sizes on the LOCO-CV measurement outcomes.We present a thorough comparison between composition-based representations, andinvestigate how kernel approximation functions can be used to better separatedata to enhance LOCO-CV applications.  We find that domain knowledge does not improve machine learning performancein most tasks tested, with band gap prediction being the notable exception. Wealso find that the radial basis function improves the linear separability ofchemical datasets in all 10 datasets tested and provide a framework for theapplication of this function in the LOCO-CV process to improve the outcome ofLOCO-CV measurements regardless of machine learning algorithm, choice ofmetric, and choice of compound representation. We recommend kernelised LOCO-CVas a training paradigm for those looking to measure the extrapolatory power ofan algorithm on materials data.

digital discovery

Random projections and Kernelised Leave One Cluster Out  Cross-Validation: Universal baselines and evaluation tools for supervised  machine learning for materials properties