信息网络安全 ›› 2023, Vol. 23 ›› Issue (9): 58-74.doi: 10.3969/j.issn.1671-1122.2023.09.006

• 技术研究 • 上一篇    下一篇

深层神经网络架构搜索综述

薛羽(), 张逸轩   

  1. 南京信息工程大学计算机与软件学院,南京 210044
  • 收稿日期:2023-04-28 出版日期:2023-09-10 发布日期:2023-09-18
  • 通讯作者: 薛羽 E-mail:xueyu@nuist.edu.cn
  • 作者简介:薛羽(1981—),男,山东,教授,博士,CCF会员,主要研究方向为深度学习、演化计算、机器学习和计算机视觉|张逸轩(1998—),男,江苏,硕士研究生,主要研究方向为演化计算、多目标优化和神经架构搜索
  • 基金资助:
    国家自然科学基金(61876089);国家自然科学基金(61876185);国家自然科学基金(61902281);国家自然科学基金(61403206);江苏省自然科学基金(BK20141005);江苏省高校自然科学基金(14KJB520025)

Survey on Deep Neural Architecture Search

XUE Yu(), ZHANG Yixuan   

  1. School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, China
  • Received:2023-04-28 Online:2023-09-10 Published:2023-09-18
  • Contact: XUE Yu E-mail:xueyu@nuist.edu.cn

摘要:

近年来,深度神经网络应用到图像识别、语音识别、目标检测、机器翻译等领域,加速了网络的性能演进与灵活性提升。但这些网络通常结构复杂,需要拥有大量专业知识的人员消耗大量时间调整参数以匹配具体环境。这样通过人工来调整参数的常规方法效率较低且错误频出。因此,神经网络架构搜索(NAS)的研究被提上日程。文章对现有的NAS相关算法进行了较全面地介绍和评价,并对未来神经网络架构搜索的发展提出构想。

关键词: 机器学习, 自动化, 深度学习, 卷积神经网络, 人工智能

Abstract:

In recent years, deep neural networks have been applied to image recognition, speech recognition, target detection, machine translation and other aspects of life. Greatly accelerating the performance evolution and flexibility improvement of the network. But these networks often have complex structures, require personnel with a large amount of professional knowledge, and require a significant amount of time to adjust parameters to suit specific environments. The efficiency of adjusting parameters using conventional manual methods is too low and errors occur frequently. Therefore, research on neural network architecture search has also been put on the agenda. In order to provide readers with a comprehensive understanding of the research progress of neural network architecture search, the article introduced and evaluated existing relevant algorithms, and proposed ideas for the future development of neural network architecture search.

Key words: machine learning, automation, deep learning, convolutional neural network, artificial intelligence

中图分类号: