中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN)

文献类型:期刊论文

;
作者Dong, Qiulei1,2,3; Liu, Bo1,2; Hu, Zhanyi1,2,3
刊名FRONTIERS IN COMPUTATIONAL NEUROSCIENCE ; FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
出版日期2020-05-12 ; 2020-05-12
卷号14页码:9
关键词deep convolutional neural network deep convolutional neural network neural object representation inferotemporal cortex non-uniqueness image object representation neural object representation inferotemporal cortex non-uniqueness image object representation
DOI10.3389/fncom.2020.00035 ; 10.3389/fncom.2020.00035
通讯作者Hu, Zhanyi(huzy@nlpr.ia.ac.cn)
英文摘要Recently DCNN (Deep Convolutional Neural Network) has been advocated as a general and promising modeling approach for neural object representation in primate inferotemporal cortex. In this work, we show that some inherent non-uniqueness problem exists in the DCNN-based modeling of image object representations. This non-uniqueness phenomenon reveals to some extent the theoretical limitation of this general modeling approach, and invites due attention to be taken in practice.;

Recently DCNN (Deep Convolutional Neural Network) has been advocated as a general and promising modeling approach for neural object representation in primate inferotemporal cortex. In this work, we show that some inherent non-uniqueness problem exists in the DCNN-based modeling of image object representations. This non-uniqueness phenomenon reveals to some extent the theoretical limitation of this general modeling approach, and invites due attention to be taken in practice.

WOS关键词PYRAMIDAL NEURONS ; PYRAMIDAL NEURONS ; VISUAL RESPONSES ; INFORMATION ; STATISTICS ; VISUAL RESPONSES ; INFORMATION ; STATISTICS
资助项目Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32070100] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32070100] ; National Natural Science Foundation of China[61991423] ; National Natural Science Foundation of China[U1805264] ; National Natural Science Foundation of China[61573359] ; National Natural Science Foundation of China[61421004] ; National Natural Science Foundation of China[61991423] ; National Natural Science Foundation of China[U1805264] ; National Natural Science Foundation of China[61573359] ; National Natural Science Foundation of China[61421004]
WOS研究方向Mathematical & Computational Biology ; Mathematical & Computational Biology ; Neurosciences & Neurology ; Neurosciences & Neurology
语种英语 ; 英语
WOS记录号WOS:000537211000001 ; WOS:000537211000001
出版者FRONTIERS MEDIA SA ; FRONTIERS MEDIA SA
资助机构Strategic Priority Research Program of the Chinese Academy of Sciences ; Strategic Priority Research Program of the Chinese Academy of Sciences ; National Natural Science Foundation of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/39520]  
专题自动化研究所_模式识别国家重点实验室_机器人视觉团队
通讯作者Hu, Zhanyi
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai, Peoples R China
推荐引用方式
GB/T 7714
Dong, Qiulei,Liu, Bo,Hu, Zhanyi. Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN), Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN)[J]. FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, FRONTIERS IN COMPUTATIONAL NEUROSCIENCE,2020, 2020,14, 14:9, 9.
APA Dong, Qiulei,Liu, Bo,&Hu, Zhanyi.(2020).Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN).FRONTIERS IN COMPUTATIONAL NEUROSCIENCE,14,9.
MLA Dong, Qiulei,et al."Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN)".FRONTIERS IN COMPUTATIONAL NEUROSCIENCE 14(2020):9.

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。