Abstract
Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed architectures have mostly been developed manually by human experts, which is a time-consuming and error-prone process. Because of this, there is growing interest in automated neural architecture search methods. We provide an overview of existing work in this field of research and categorize them according to three dimensions: search space, search strategy, and performance estimation strategy.
Abstract (translated)
在过去几年中,深度学习在图像识别、语音识别和机器翻译等各种任务上取得了显著进展。这一进展的一个关键方面是新的神经架构。目前使用的架构大多是由人类专家手工开发的,这是一个耗时且容易出错的过程。正因为如此,人们对自动神经架构搜索方法越来越感兴趣。我们概述了这一研究领域的现有工作,并根据搜索空间、搜索策略和性能评估策略三个维度对其进行分类。
URL
https://arxiv.org/abs/1808.05377