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

Inspired by the recent achievements of machine learning in diverse domains,data-driven metamaterials design has emerged as a compelling paradigm that canunlock the potential of multiscale architectures. The model-centric researchtrend, however, lacks principled frameworks dedicated to data acquisition,whose quality propagates into the downstream tasks. Often built by naivespace-filling design in shape descriptor space, metamaterial datasets sufferfrom property distributions that are either highly imbalanced or at odds withdesign tasks of interest. To this end, we present t-METASET: anactive-learning-based data acquisition framework aiming to guide both diverseand task-aware data generation. Distinctly, we seek a solution to a commonplaceyet frequently overlooked scenario at early stages of data-driven design ofmetamaterials: when a massive (~O(10^4 )) shape-only library has been preparedwith no properties evaluated. The key idea is to harness a data-driven shapedescriptor learned from generative models, fit a sparse regressor as a start-upagent, and leverage metrics related to diversity to drive data acquisition toareas that help designers fulfill design goals. We validate the proposedframework in three deployment cases, which encompass general use, task-specificuse, and tailorable use. Two large-scale mechanical metamaterial datasets areused to demonstrate the efficacy. Applicable to general image-based designrepresentations, t-METASET could boost future advancements in data-drivendesign.

t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning