Q
Quanshi Zhang
Researcher at Shanghai Jiao Tong University
Publications - 117
Citations - 3152
Quanshi Zhang is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 22, co-authored 98 publications receiving 2252 citations. Previous affiliations of Quanshi Zhang include University of Tokyo & Peking University.
Papers
More filters
Proceedings ArticleDOI
Interpretable Convolutional Neural Networks
TL;DR: A method to modify a traditional convolutional neural network into an interpretable CNN, in order to clarify knowledge representations in high conv-layers of the CNN, which can help people understand the logic inside a CNN.
Posted Content
Interpretable Convolutional Neural Networks
TL;DR: In this paper, the authors proposed a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs.
Proceedings ArticleDOI
Interpreting CNNs via Decision Trees
TL;DR: In this article, the authors propose to learn a decision tree, which decomposes feature representations in high convolutional layers of the CNN into elementary concepts of object parts and explain the specific reason for each prediction made by the CNN at the semantic level.
Posted Content
Interpreting CNNs via Decision Trees
TL;DR: The proposed decision tree is a decision tree, which clarifies the specific reason for each prediction made by the CNN at the semantic level, and organizes all potential decision modes in a coarse-to-fine manner to explain CNN predictions at different fine-grained levels.
Proceedings ArticleDOI
Prediction of human emergency behavior and their mobility following large-scale disaster
TL;DR: A model of human behavior is developed that takes into account social relationship, intensity of disaster, damage level, government appointed shelters, news reporting, large population flow and etc. for accurately predicting human emergency behavior and their mobility following large-scale disaster.