arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.10937cs.NE
收藏

进化神经网络结构搜索综述

A Survey on Evolutionary Neural Architecture Search

Yuqiao Liu, Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen, Kay Chen Tan

摘要:

深度神经网络(DNN)在许多应用中取得了巨大的成功。DNN的架构在其性能中起着至关重要的作用,通常是通过丰富的专业知识手动设计的。然而,由于试错过程,这样的设计过程是劳动密集型的,并且由于实践中的稀有专业知识,也不容易实现。神经网络架构搜索(NAS)是一种能够自动设计架构的技术。在实现NAS的各种方法中,演化计算(EC)方法近年来获得了广泛的关注和成功。不幸的是,还没有一个全面的总结,基于EC的NAS算法。本文从核心组件的角度,对200多篇最新的基于EC的NAS方法进行了综述,系统地讨论了它们的设计原则以及设计的合理性。此外,目前的挑战和问题也进行了讨论,以确定未来的研究在这一新兴领域。

英文摘要:

Deep Neural Networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labour intensive because of the trial-and-error process, and also not easy to realize due to the rare expertise in practice. Neural Architecture Search (NAS) is a type of technology that can design the architectures automatically. Among different methods to realize NAS, Evolutionary Computation (EC) methods have recently gained much attention and success. Unfortunately, there has not yet been a comprehensive summary of the EC-based NAS algorithms. This paper reviews over 200 papers of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles as well as justifications on the design. Furthermore, current challenges and issues are also discussed to identify future research in this emerging field.

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。

↑