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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Neural architecture search (NAS), an important branch of automatic machinelearning, has become an effective approach to automate the design of deeplearning models. However, the major issue in NAS is how to reduce the largesearch time imposed by the heavy computational burden. While most recentapproaches focus on pruning redundant sets or developing new searchmethodologies, this paper attempts to formulate the problem based on the datacuration manner. Our key strategy is to search the architecture usingsummarized data distribution, i.e., core-set. Typically, many NAS algorithmsseparate searching and training stages, and the proposed core-set methodologyis only used in search stage, thus their performance degradation can beminimized. In our experiments, we were able to save overall computational timefrom 30.8 hours to 3.5 hours, 8.8x reduction, on a single RTX 3090 GPU withoutsacrificing accuracy.

Core-set Sampling for Efficient Neural Architecture Search