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

Recent breakthroughs in Neural Architectural Search (NAS) have achievedstate-of-the-art performances in applications such as image classification andlanguage modeling. However, these techniques typically ignore device-relatedobjectives such as inference time, memory usage, and power consumption.Optimizing neural architecture for device-related objectives is immenselycrucial for deploying deep networks on portable devices with limited computingresources. We propose DPP-Net: Device-aware Progressive Search forPareto-optimal Neural Architectures, optimizing for both device-related (e.g.,inference time and memory usage) and device-agnostic (e.g., accuracy and modelsize) objectives. DPP-Net employs a compact search space inspired by currentstate-of-the-art mobile CNNs, and further improves search efficiency byadopting progressive search (Liu et al. 2017). Experimental results on CIFAR-10are poised to demonstrate the effectiveness of Pareto-optimal networks found byDPP-Net, for three different devices: (1) a workstation with Titan X GPU, (2)NVIDIA Jetson TX1 embedded system, and (3) mobile phone with ARM Cortex-A53.Compared to CondenseNet and NASNet (Mobile), DPP-Net achieves betterperformances: higher accuracy and shorter inference time on various devices.Additional experimental results show that models found by DPP-Net also achieveconsiderably-good performance on ImageNet as well.

DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures