arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.08727cs.LGcs.AIstat.ML
收藏

神经架构搜索:1000篇论文的见解

Neural Architecture Search: Insights from 1000 Papers

University of Freiburg(弗赖堡大学);Sailyond Technology & Research Institute of Tsinghua University(清华大学赛力扬技术研究院);Bosch Center for Artificial Intelligence(博世人工智能中心);Microsoft Research(微软研究院)

Colin White, Mahmoud Safari, Rhea Sukthanker, Binxin Ru, Thomas Elsken, Arber Zela, Debadeepta Dey, Frank Hutter

摘要:

在过去的十年中,深度学习的进步在各个领域取得了突破,包括计算机视觉、自然语言理解、语音识别和强化学习。专门的高性能神经架构对于深度学习在这些领域的成功至关重要。神经架构搜索(NAS)是为给定任务自动化神经架构设计的过程,是自动化机器学习的下一个必然步骤,并且已经在许多任务上超过了最好的人类设计架构。在过去的几年里,NAS的研究进展迅速,自2020年以来发表了1000多篇论文(Deng和Lindauer,2021)。在这项调查中,我们提供了一个有组织的和全面的神经结构搜索指南。我们给出了搜索空间、算法和加速技术的分类,并讨论了基准测试、最佳实践、其他调查和开源库等资源。

英文摘要:

In the past decade, advances in deep learning have resulted in breakthroughs in a variety of areas, including computer vision, natural language understanding, speech recognition, and reinforcement learning. Specialized, high-performing neural architectures are crucial to the success of deep learning in these areas. Neural architecture search (NAS), the process of automating the design of neural architectures for a given task, is an inevitable next step in automating machine learning and has already outpaced the best human-designed architectures on many tasks. In the past few years, research in NAS has been progressing rapidly, with over 1000 papers released since 2020 (Deng and Lindauer, 2021). In this survey, we provide an organized and comprehensive guide to neural architecture search. We give a taxonomy of search spaces, algorithms, and speedup techniques, and we discuss resources such as benchmarks, best practices, other surveys, and open-source libraries.

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。

↑