A Multi-Objective Evolutionary Approach Based on Graph-in-Graph for Neural Architecture Search of Convolutional Neural Networks

Author:

Xue Yu12,Jiang Pengcheng1,Neri Ferrante3,Liang Jiayu4

Affiliation:

1. School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, P. R. China

2. Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology, Nanjing, P. R. China

3. COL Laboratory, School of Computer Science, University of Nottingham, Nottingham, UK

4. Tianjin Key Laboratory of Autonomous Intelligent Technology and System, Tiangong University, Tianjin, P. R. China

Abstract

With the development of deep learning, the design of an appropriate network structure becomes fundamental. In recent years, the successful practice of Neural Architecture Search (NAS) has indicated that an automated design of the network structure can efficiently replace the design performed by human experts. Most NAS algorithms make the assumption that the overall structure of the network is linear and focus solely on accuracy to assess the performance of candidate networks. This paper introduces a novel NAS algorithm based on a multi-objective modeling of the network design problem to design accurate Convolutional Neural Networks (CNNs) with a small structure. The proposed algorithm makes use of a graph-based representation of the solutions which enables a high flexibility in the automatic design. Furthermore, the proposed algorithm includes novel ad-hoc crossover and mutation operators. We also propose a mechanism to accelerate the evaluation of the candidate solutions. Experimental results demonstrate that the proposed NAS approach can design accurate neural networks with limited size.

Funder

National Natural Science Foundation of China

Jiangsu Key Laboratory of Data Science and Smart Software

Natural Science Foundation of Jiangsu Province

National Natural Science Foundation of the Jiangsu Higher Education Institutions of China

Publisher

World Scientific Pub Co Pte Lt

Subject

Computer Networks and Communications,General Medicine

Cited by 87 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