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
Heuristic rank selection with progressively searching tensor ring network

文献类型：期刊论文

作者Li, Nannan3,4; Pan, Yu1; Chen, Yaran3,4; Ding, Zixiang3,4; Zhao, Dongbin3,4; Xu, Zenglin1,2
刊名COMPLEX & INTELLIGENT SYSTEMS
出版日期2021-03-17
页码15
关键词Tensor ring networks Rank selection Progressively search Image classification
ISSN号2199-4536
DOI10.1007/s40747-021-00308-x
通讯作者Chen, Yaran(chenyaran2013@ia.ac.cn) ; Xu, Zenglin(zenglin@gmail.com)
英文摘要Recently, tensor ring networks (TRNs) have been applied in deep networks, achieving remarkable successes in compression ratio and accuracy. Although highly related to the performance of TRNs, rank selection is seldom studied in previous works and usually set to equal in experiments. Meanwhile, there is not any heuristic method to choose the rank, and an enumerating way to find appropriate rank is extremely time-consuming. Interestingly, we discover that part of the rank elements is sensitive and usually aggregate in a narrow region, namely an interest region. Therefore, based on the above phenomenon, we propose a novel progressive genetic algorithm named progressively searching tensor ring network search (PSTRN), which has the ability to find optimal rank precisely and efficiently. Through the evolutionary phase and progressive phase, PSTRN can converge to the interest region quickly and harvest good performance. Experimental results show that PSTRN can significantly reduce the complexity of seeking rank, compared with the enumerating method. Furthermore, our method is validated on public benchmarks like MNIST, CIFAR10/100, UCF11 and HMDB51, achieving the state-of-the-art performance.
资助项目National Natural Science Foundation of China (NSFC)[62006226]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000629881600002
出版者SPRINGER HEIDELBERG
资助机构National Natural Science Foundation of China (NSFC)
源URL[http://ir.ia.ac.cn/handle/173211/44070]  
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Chen, Yaran; Xu, Zenglin
作者单位1.Harbin Inst Technol Shenzhen, Shenzhen, Peoples R China
2.Pengcheng Lab, Shenzhen, Peoples R China
3.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China
推荐引用方式
GB/T 7714		 Li, Nannan,Pan, Yu,Chen, Yaran,et al. Heuristic rank selection with progressively searching tensor ring network[J]. COMPLEX & INTELLIGENT SYSTEMS,2021:15.
APA Li, Nannan,Pan, Yu,Chen, Yaran,Ding, Zixiang,Zhao, Dongbin,&Xu, Zenglin.(2021).Heuristic rank selection with progressively searching tensor ring network.COMPLEX & INTELLIGENT SYSTEMS,15.
MLA Li, Nannan,et al."Heuristic rank selection with progressively searching tensor ring network".COMPLEX & INTELLIGENT SYSTEMS (2021):15.

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。