Shan Xu
Beijing Normal University
14 Papers
10 Citations
Shan Xu is an academic researcher from Beijing Normal University. The author has contributed to research in topics: Convolutional neural network & Computer science. The author has an hindex of 2, co-authored 9 publications.
Chat about Author
Papers
The Face Module Emerged in a Deep Convolutional Neural Network Selectively Deprived of Face Experience
TL;DR: Zhang et al. as mentioned in this paper built a model of selective deprivation of the experience on faces with a representative deep convolutional neural network, AlexNet, by removing all images containing faces from its training stimuli.
Behavioral and neural correlates of social network size: The unique and common contributions of face recognition and extraversion
TL;DR: This study suggests that both face recognition and extraversion may be important correlates of SNS, and the underlying spontaneous neural substrates are partially dissociable.
11
The Neural Correlates of Computational Thinking: Collaboration of Distinct Cognitive Components Revealed by fMRI.
TL;DR: In this article, the authors used functional magnetic resonance imaging to examine the neural correlates of programming to understand the cognitive substrates of computational thinking (CT), and they found that CT recruited distributed cortical regions, including the posterior parietal cortex, the medial frontal cortex, and the left lateral frontal cortex.
11
The face module emerged in a deep convolutional neural network selectively deprived of face experience
TL;DR: This study builds a model of selective deprivation of the experience on faces with a representative deep convolutional neural network, AlexNet, by removing all images containing faces from its training stimuli and found that deprivation reduced the domain-specificity of the face module.
10
Implementation-Independent Representation for Deep Convolutional Neural Networks and Humans in Processing Faces.
TL;DR: In this paper, a reverse-correlation method was applied to make explicit representations of DCNNs and humans when performing face gender classification, which showed that humans and a typical DCNN, VGG-Face, used similar critical information for this task, which mainly resided at low spatial frequencies.