Survey on Evolutionary Deep Learning: Principles, Algorithms, Applications, and Open Issues

Author:

Li Nan1ORCID,Ma Lianbo1ORCID,Yu Guo2ORCID,Xue Bing3ORCID,Zhang Mengjie3ORCID,Jin Yaochu4ORCID

Affiliation:

1. Northeastern University, China

2. Nanjing Tech University, China

3. Victoria University of Wellington, New Zealand

4. Bielefeld University, Germany

Abstract

Over recent years, there has been a rapid development of deep learning (DL) in both industry and academia fields. However, finding the optimal hyperparameters of a DL model often needs high computational cost and human expertise. To mitigate the above issue, evolutionary computation (EC) as a powerful heuristic search approach has shown significant merits in the automated design of DL models, so-called evolutionary deep learning (EDL). This article aims to analyze EDL from the perspective of automated machine learning (AutoML). Specifically, we first illuminate EDL from DL and EC and regard EDL as an optimization problem. According to the DL pipeline, we systematically introduce EDL methods ranging from data preparation, model generation, to model deployment with a new taxonomy (i.e., what and how to evolve/optimize), and focus on the discussions of solution representation and search paradigm in handling the optimization problem by EC. Finally, key applications, open issues, and potentially promising lines of future research are suggested. This survey has reviewed recent developments of EDL and offers insightful guidelines for the development of EDL.

Funder

National Natural Science Foundation of China

National Key R&D Program of China

Project funded by China Postdoctoral Science Foundation

Joint Funds of the Natural Science Foundation of Liaoning Province

Fundamental Research Funds for the Central Universities

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science,Theoretical Computer Science

Reference242 articles.

1. Principal component analysis

2. Amr Ahmed, Saad Mohamed Darwish, and Mohamed M. El-Sherbiny. 2019. A novel automatic CNN architecture design approach based on genetic algorithm. In Proceedings of the International Conference on Advanced Intelligent Systems and Informatics.473–482.

3. Multiple feature construction for effective biomarker identification and classification using genetic programming

4. Training feedforward neural networks using multi-phase particle swarm optimization

5. A survey on evolutionary machine learning

Cited by 8 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3