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. 深度强化学习
ModuleNet: Knowledge-Inherited Neural Architecture Search

文献类型：期刊论文

作者Chen, Yaran3,4; Gao, Ruiyuan1; Liu, Fenggang2; Zhao, Dongbin3,4
刊名IEEE TRANSACTIONS ON CYBERNETICS
出版日期2021-06-04
页码11
关键词Computer architecture Task analysis Knowledge based systems Microprocessors Statistics Sociology Computational modeling Evaluation algorithm knowledge inherited neural architecture search (NAS)
ISSN号2168-2267
DOI10.1109/TCYB.2021.3078573
通讯作者Zhao, Dongbin(dongbin.zhao@ia.ac.cn)
英文摘要Although neural the architecture search (NAS) can bring improvement to deep models, it always neglects precious knowledge of existing models. The computation and time costing property in NAS also means that we should not start from scratch to search, but make every attempt to reuse the existing knowledge. In this article, we discuss what kind of knowledge in a model can and should be used for a new architecture design. Then, we propose a new NAS algorithm, namely, ModuleNet, which can fully inherit knowledge from the existing convolutional neural networks. To make full use of the existing models, we decompose existing models into different modules, which also keep their weights, consisting of a knowledge base. Then, we sample and search for a new architecture according to the knowledge base. Unlike previous search algorithms, and benefiting from inherited knowledge, our method is able to directly search for architectures in the macrospace by the NSGA-II algorithm without tuning parameters in these modules. Experiments show that our strategy can efficiently evaluate the performance of a new architecture even without tuning weights in convolutional layers. With the help of knowledge we inherited, our search results can always achieve better performance on various datasets (CIFAR10, CIFAR100, and ImageNet) over original architectures.
WOS关键词GENETIC ALGORITHM ; MODEL
资助项目National Natural Science Foundation of China (NSFC)[62006226] ; Youth Research Fund of the State Key Laboratory of Management and Control for Complex Systems[20190213] ; Huawei Technologies Company Ltd.[FA2018111061SOW12]
WOS研究方向Automation & Control Systems ; Computer Science
语种英语
WOS记录号WOS:000732096300001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China (NSFC) ; Youth Research Fund of the State Key Laboratory of Management and Control for Complex Systems ; Huawei Technologies Company Ltd.
源URL[http://ir.ia.ac.cn/handle/173211/46905]  
专题复杂系统管理与控制国家重点实验室_深度强化学习
通讯作者Zhao, Dongbin
作者单位1.Chinese Univ Hong Kong, Dept Comp Sci & Engn, Hong Kong, Peoples R China
2.Beijing Inst Technol, Coll Automat, Beijing 100811, Peoples R China
3.Univ Chinese Acad Sci, Coll Artificial Intelligence, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Yaran,Gao, Ruiyuan,Liu, Fenggang,et al. ModuleNet: Knowledge-Inherited Neural Architecture Search[J]. IEEE TRANSACTIONS ON CYBERNETICS,2021:11.
APA Chen, Yaran,Gao, Ruiyuan,Liu, Fenggang,&Zhao, Dongbin.(2021).ModuleNet: Knowledge-Inherited Neural Architecture Search.IEEE TRANSACTIONS ON CYBERNETICS,11.
MLA Chen, Yaran,et al."ModuleNet: Knowledge-Inherited Neural Architecture Search".IEEE TRANSACTIONS ON CYBERNETICS (2021):11.

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。