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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Neural Architecture Search (NAS) has become the de-facto approach fordesigning accurate and efficient networks for edge devices. Since models aretypically quantized for edge deployment, recent work has investigatedquantization-aware NAS (QA-NAS) to search for highly accurate and efficientquantized models. However, existing QA-NAS approaches, particularly few-bitmixed-precision (FB-MP) methods, do not scale to larger tasks. Consequently,QA-NAS has mostly been limited to low-scale tasks and tiny networks. In thiswork, we present an approach to enable QA-NAS (INT8 and FB-MP) on large-scaletasks by leveraging the block-wise formulation introduced by block-wise NAS. Wedemonstrate strong results for the semantic segmentation task on the Cityscapesdataset, finding FB-MP models 33% smaller and INT8 models 17.6% faster thanDeepLabV3 (INT8) without compromising task performance.

Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge