DNA computing inspired deep networks design
文献类型:期刊论文
作者 | Zhong, Guoqiang3; Li, Tao3; Jiao, Wencong3; Wang, Li-Na3; Dong, Junyu3; Liu, Cheng-Lin1,2,4 |
刊名 | NEUROCOMPUTING |
出版日期 | 2020-03-21 |
卷号 | 382页码:140-147 |
ISSN号 | 0925-2312 |
关键词 | Deep neural networks DNA computing Automatic architecture design Image classification |
DOI | 10.1016/j.neucom.2019.11.098 |
通讯作者 | Zhong, Guoqiang(gqzhong@ouc.edu.cn) |
英文摘要 | Deep neural networks have gained state-of-the-art results in many applications, such as pattern recognition and computer vision. However, most of the deep neural networks are designed manually by researchers. This architecture design process is generally time consuming and needs much expertise. Hence, automatic neural network design becomes an important issue. In this paper, we propose a novel method, called DNA computing inspired networks design (DNAND), to automatically learn high performance deep networks. In DNAND, we use DNA strands to represent blocks of a model, and these DNA strands are reacted to construct the overall networks according to the base pairing principle. We also present the killing strategy, with which we stop training "bad" models if they fail to reach the specific accuracy threshold on the validation set, so as to reduce the computational cost and accelerate the learning process. Extensive experiments on image classification and detection data sets demonstrate the effectiveness of the proposed method. (C) 2019 Elsevier B.V. All rights reserved. |
WOS关键词 | NEURAL-NETWORK ; EVOLUTIONARY ; OPTIMIZATION ; COMPUTATION |
资助项目 | Major Project for New Generation of AI[2018AAA0100400] ; National Key R&D Program of China[2016YFC1401004] ; National Natural Science Foundation of China (NSFC)[41706010] ; Science and Technology Program of Qingdao[17-3-3-20-nsh] ; CERNET Innovation Project[NGII20170416] ; Ministry of Education of China[6141A020337] ; Fundamental Research Funds for the Central Universities of China ; Joint Fund of the Equipments Pre-Research[6141A020337] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000512881200015 |
资助机构 | Major Project for New Generation of AI ; National Key R&D Program of China ; National Natural Science Foundation of China (NSFC) ; Science and Technology Program of Qingdao ; CERNET Innovation Project ; Ministry of Education of China ; Fundamental Research Funds for the Central Universities of China ; Joint Fund of the Equipments Pre-Research |
源URL | [http://ir.ia.ac.cn/handle/173211/28610] |
专题 | 自动化研究所_模式识别国家重点实验室_模式分析与学习团队 |
通讯作者 | Zhong, Guoqiang |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China 3.Ocean Univ China, Dept Comp Sci & Technol, Qingdao 266100, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Zhong, Guoqiang,Li, Tao,Jiao, Wencong,et al. DNA computing inspired deep networks design[J]. NEUROCOMPUTING,2020,382:140-147. |
APA | Zhong, Guoqiang,Li, Tao,Jiao, Wencong,Wang, Li-Na,Dong, Junyu,&Liu, Cheng-Lin.(2020).DNA computing inspired deep networks design.NEUROCOMPUTING,382,140-147. |
MLA | Zhong, Guoqiang,et al."DNA computing inspired deep networks design".NEUROCOMPUTING 382(2020):140-147. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。