arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.00709cs.LGcs.CVstat.ML
收藏

AutoML:最新技术综述

AutoML: A Survey of the State-of-the-Art

Hong Kong Baptist University(香港浸会大学)

Xin He, Kaiyong Zhao, Xiaowen Chu

摘要:

深度学习(DL)技术已经渗透到我们生活的方方面面,给我们带来了极大的便利。然而,为特定任务构建高质量的深度学习系统高度依赖于人类的专业知识,阻碍了深度学习在更多领域的应用。自动化机器学习(AutoML)是一种在没有人工辅助的情况下构建深度学习系统的有前途的解决方案,越来越多的研究人员关注AutoML。在本文中,我们对AutoML中的最新技术(SOTA)进行了全面而最新的回顾。首先,我们根据管道介绍AutoML方法,包括数据准备,特征工程,超参数优化和神经结构搜索(NAS)。我们更关注NAS,因为它是AutoML目前非常热门的子主题。本文在CIFAR-10和ImageNet数据集上,总结了典型NAS算法的性能,并进一步讨论了NAS方法的几个值得研究的方向:单阶段/两阶段NAS、单次NAS以及超参数和架构联合优化。最后,我们讨论了现有的AutoML方法的一些开放性问题,为未来的研究。

英文摘要:

Deep learning (DL) techniques have penetrated all aspects of our lives and brought us great convenience. However, building a high-quality DL system for a specific task highly relies on human expertise, hindering the applications of DL to more areas. Automated machine learning (AutoML) becomes a promising solution to build a DL system without human assistance, and a growing number of researchers focus on AutoML. In this paper, we provide a comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML. First, we introduce AutoML methods according to the pipeline, covering data preparation, feature engineering, hyperparameter optimization, and neural architecture search (NAS). We focus more on NAS, as it is currently very hot sub-topic of AutoML. We summarize the performance of the representative NAS algorithms on the CIFAR-10 and ImageNet datasets and further discuss several worthy studying directions of NAS methods: one/two-stage NAS, one-shot NAS, and joint hyperparameter and architecture optimization. Finally, we discuss some open problems of the existing AutoML methods for future research.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑