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

Neural Architecture Search (NAS) refers to automatically design thearchitecture. We propose an hourglass-inspired approach (HourNAS) for thisproblem that is motivated by the fact that the effects of the architectureoften proceed from the vital few blocks. Acting like the narrow neck of anhourglass, vital blocks in the guaranteed path from the input to the output ofa deep neural network restrict the information flow and influence the networkaccuracy. The other blocks occupy the major volume of the network and determinethe overall network complexity, corresponding to the bulbs of an hourglass. Toachieve an extremely fast NAS while preserving the high accuracy, we propose toidentify the vital blocks and make them the priority in the architecturesearch. The search space of those non-vital blocks is further shrunk to onlycover the candidates that are affordable under the computational resourceconstraints. Experimental results on the ImageNet show that only using 3 hours(0.1 days) with one GPU, our HourNAS can search an architecture that achieves a77.0% Top-1 accuracy, which outperforms the state-of-the-art methods.

HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens