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

Upon the significant performance of the supervised deep neural networks,conventional procedures of developing ML system are \textit{task-centric},which aims to maximize the task accuracy. However, we scrutinized this\textit{task-centric} ML system lacks in engineering efficiency when the MLpractitioners solve multiple tasks in their domain. To resolve this problem, wepropose an \textit{efficiency-centric} ML system that concatenates numerousdatasets, classifiers, out-of-distribution detectors, and prediction tablesexisting in the practitioners' domain into a single ML pipeline. Under variousimage recognition tasks in the real world car-sharing platform, our studyillustrates how we established the proposed system and lessons learned fromthis journey as follows. First, the proposed ML system accomplishes supremeengineering efficiency while achieving a competitive task accuracy. Moreover,compared to the \textit{task-centric} paradigm, we discovered that the\textit{efficiency-centric} ML system yields satisfactory prediction results onmulti-labelable samples, which frequently exist in the real world. We analyzethese benefits derived from the representation power, which learned broaderlabel spaces from the concatenated dataset. Last but not least, our studyelaborated how we deployed this \textit{efficiency-centric} ML system isdeployed in the real world live cloud environment. Based on the proposedanalogies, we highly expect that ML practitioners can utilize our study toelevate engineering efficiency in their domain.

Towards an Efficient ML System: Unveiling a Trade-off between Task Accuracy and Engineering Efficiency in a Large-scale Car Sharing Platform