Knowledge Commons of Institute of Automation,CAS
Exploring the brain-like properties of deep neural networks: a neural encoding perspective | |
Qiongyi Zhou1,2; Changde Du1,2; Huiguang He1,2,3 | |
发表期刊 | Machine Intelligence Research |
2022-07 | |
卷号 | 19期号:5页码:439-455 |
摘要 | Nowadays,deep neural networks (DNNs) have been equipped with powerful representation capabilities. The deep convolutional neural networks (CNNs) that draw inspiration from the visual processing mechanism of the primate early visual cortex have outperformed humans on object categorization and have been found to possess many brain-like properties. Recently,Vision Transformers (ViTs) are striking paradigms of DNNs and have achieved remarkable improvements on many vision tasks compared to CNNs. It is natural to ask how are the brain-like properties of ViTs. Beyond the model paradigm,we are also interested in the effects of factors,such as model size,multimodality,and temporality,on the ability of networks to model the human visual pathway,especially when considering that existing research has been limited to the CNNs. In this paper,we systematically evaluate the brain-like properties of 30 kinds of computer vision models varying from CNNs,ViTs to their hybrids from the perspective of explaining brain activities of the human visual cortex triggered by dynamic stimuli. Experiments on two neural datasets demonstrate that neither CNN nor transformer is the optimal model paradigm for modeling the human visual pathway. ViTs reveal hierarchical correspondences to the visual pathway as CNNs do. Moreover,we find that multi-modal and temporal networks can better explain the neural activities of large parts of the visual cortex,whereas a larger model size is not a sufficient condition for bridging the gap between human vision and artificial networks. Our study sheds light on the design principles for more brain-like networks. The code is available at https://github.com/QYiZhou/LWNeuralEncoding. |
DOI | 10.1007/s11633-022-1348-x |
收录类别 | EI |
七大方向——子方向分类 | 脑机接口 |
国重实验室规划方向分类 | 人工智能基础前沿理论 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/50878 |
专题 | 脑图谱与类脑智能实验室_神经计算与脑机交互 |
通讯作者 | Huiguang He |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Qiongyi Zhou,Changde Du,Huiguang He. Exploring the brain-like properties of deep neural networks: a neural encoding perspective[J]. Machine Intelligence Research,2022,19(5):439-455. |
APA | Qiongyi Zhou,Changde Du,&Huiguang He.(2022).Exploring the brain-like properties of deep neural networks: a neural encoding perspective.Machine Intelligence Research,19(5),439-455. |
MLA | Qiongyi Zhou,et al."Exploring the brain-like properties of deep neural networks: a neural encoding perspective".Machine Intelligence Research 19.5(2022):439-455. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
J76-Exploring the br(6004KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论