X
Xiaowen Chu
Researcher at Hong Kong Baptist University
Publications - 276
Citations - 7866
Xiaowen Chu is an academic researcher from Hong Kong Baptist University. The author has contributed to research in topics: Deep learning & Computer science. The author has an hindex of 39, co-authored 255 publications receiving 5776 citations. Previous affiliations of Xiaowen Chu include Hangzhou Dianzi University & Hang Seng Management College.
Papers
More filters
Journal ArticleDOI
AutoML: A survey of the state-of-the-art
Xin He,Kaiyong Zhao,Xiaowen Chu +2 more
TL;DR: A comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML methods according to the pipeline, covering data preparation, feature engineering, hyperparameter optimization, and neural architecture search (NAS).
Journal Article
Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes.
Xianyan Jia,Shutao Song,He Wei,Yangzihao Wang,Haidong Rong,Feihu Zhou,Liqiang Xie,Zhenyu Guo,Yuanzhou Yang,Liwei Yu,Tiegang Chen,Guangxiao Hu,Shaohuai Shi,Xiaowen Chu +13 more
TL;DR: This work builds a highly scalable deep learning training system for dense GPU clusters with three main contributions: a mixed-precision training method that significantly improves the training throughput of a single GPU without losing accuracy, an optimization approach for extremely large mini-batch size that can train CNN models on the ImageNet dataset without lost accuracy, and highly optimized all-reduce algorithms.
Journal ArticleDOI
Electric Vehicle Charging Station Placement: Formulation, Complexity, and Solutions
TL;DR: In this article, the authors formulated the EV charging station placement problem (EVCSPP) and proved that the problem is non-deterministic polynomial-time hard, and proposed four solution methods to tackle it.
Journal ArticleDOI
Electric Vehicle Charging Station Placement: Formulation, Complexity, and Solutions
TL;DR: It is proved that the EV charging station placement problem is nondeterministic polynomial-time hard and four solution methods are proposed to tackle EVCSPP, and their performance on various artificial and practical cases are evaluated.
Journal ArticleDOI
SOAP3: ultra-fast GPU-based parallel alignment tool for short reads.
Chi-Man Liu,Thomas K. F. Wong,Ed X. Wu,Ruibang Luo,Siu-Ming Yiu,Yingrui Li,Bingqiang Wang,Chang Yu,Xiaowen Chu,Kaiyong Zhao,Ruiqiang Li,Tak-Wah Lam +11 more
TL;DR: SOAP3 is the first short read alignment tool that leverages the multi-processors in a graphic processing unit (GPU) to achieve a drastic improvement in speed and aligns slightly more reads than BWA and Bowtie.