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/

Zendy Plus

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

Zendy Tools

Zendy Open

Deep Generative Machine Learning Models have been growing in popularityacross the design community thanks to their ability to learn and mimic complexdata distributions. While early works are promising, further advancement willdepend on addressing several critical considerations such as design quality,feasibility, novelty, and targeted inverse design. We propose the Design TargetAchievement Index (DTAI), a differentiable, tunable metric that scores adesign's ability to achieve designer-specified minimum performance targets. Wedemonstrate that DTAI can drastically improve the performance of generateddesigns when directly used as a training loss in Deep Generative Models. Weapply the DTAI loss to a Performance-Augmented Diverse GAN (PaDGAN) anddemonstrate superior generative performance compared to a set of baseline DeepGenerative Models including a Multi-Objective PaDGAN and specialized tabulargeneration algorithms like the Conditional Tabular GAN (CTGAN). We furtherenhance PaDGAN with an auxiliary feasibility classifier to encourage feasibledesigns. To evaluate methods, we propose a comprehensive set of evaluationmetrics for generative methods that focus on feasibility, diversity, andsatisfaction of design performance targets. Methods are tested on a challengingbenchmarking problem: the FRAMED bicycle frame design dataset featuringmixed-datatype parametric data, heavily skewed and multimodal distributions,and ten competing performance objectives.

Design Target Achievement Index: A Differentiable Metric to Enhance Deep Generative Models in Multi-Objective Inverse Design