中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 模式分析与学习团队
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
DOI10.1016/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。