Z
Zhouhan Lin
Researcher at Université de Montréal
Publications - 56
Citations - 7705
Zhouhan Lin is an academic researcher from Université de Montréal. The author has contributed to research in topics: Computer science & Recurrent neural network. The author has an hindex of 18, co-authored 43 publications receiving 6258 citations. Previous affiliations of Zhouhan Lin include Harbin Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Straight to the Tree: Constituency Parsing with Neural Syntactic Distance
TL;DR: The authors proposed a constituency parsing scheme, which predicts a real-valued scalar, named syntactic distance, for each split position in the sentence and the topology of grammar tree is then determined by the values of syntactic distances.
Proceedings ArticleDOI
Spectral-Spatial Classification of Hyperspectral Image Using Autoencoders
TL;DR: In this article, the authors proposed a new framework of spectral-spatial feature extraction for hyperspectral image classification, in which for the first time the concept of deep learning is introduced.
Proceedings ArticleDOI
Spectral-spatial classification of hyperspectral image using autoencoders
TL;DR: A new framework of spectral-spatial feature extraction for HSI classification, in which for the first time the concept of deep learning is introduced, and achieves the highest classification accuracy among all methods, and outperforms classical classifiers such as SVM and PCA-based SVM.
Posted Content
Recurrent Neural Networks With Limited Numerical Precision
TL;DR: This paper addresses the question of how to best reduce weight precision during training in the case of RNNs by presenting results from the use of different stochastic and deterministic reduced precision training methods applied to three major RNN types which are then tested on several datasets.
Posted Content
Architectural Complexity Measures of Recurrent Neural Networks
Saizheng Zhang,Yuhuai Wu,Tong Che,Zhouhan Lin,Roland Memisevic,Ruslan Salakhutdinov,Yoshua Bengio +6 more
TL;DR: In this article, a graph-theoretic framework is presented to analyze the connecting architectures of RNNs and three architecture complexity measures are proposed: the recurrent depth, the feedforward depth and the recurrent skip coefficient.