BriefGPT.xyz
Jun, 2020
Bonsai-Net: 一种基于可微分剪枝器的一次性神经架构搜索
Bonsai-Net: One-Shot Neural Architecture Search via Differentiable Pruners
HTML
PDF
Rob Geada, Dennis Prangle, Andrew Stephen McGough
TL;DR
通过放宽神经架构搜索领域的范围,本研究提出了一种高效的一次性神经架构搜索方法Bonsai-Net,可同时进行模型搜索和训练,并可显著减少使用更少参数比其他现有方法更好地发现优秀架构的全过程所需的时间。
Abstract
One-shot
neural architecture search
(NAS) aims to minimize the
computational expense
of discovering state-of-the-art models. However, in the past year attention has been drawn to the comparable performance of nai
→