Junwen Huang
Researcher at Capital of Statistics | 统计之都
Guangzhou City, Guangdong Province, China
Summary
🤩
Rockstar🎓
Top SchoolJunwen Huang is a researcher at Tencent with 14 years of experience bridging mathematics, statistics, and computer science to build practical machine learning and data-driven systems. With an MS in Statistics from UC San Diego and a strong BS in Information and Computational Science, he combines rigorous statistical modeling with hands-on engineering—evidenced by contributions to deep learning resources such as batch normalization implementations in the well-known "Dive into Deep Learning" ecosystem. He has applied mixed-effects models and multivariate analysis in clinical research, built reproducible analytics and visualization pipelines for finance, and contributed editorially to the Chinese statistics community. At Tencent he focuses on research-grade solutions that are production-aware, and his GitHub showcases open-source projects reflecting both scratch implementations and framework-level expertise. Colleagues know him for clear, reproducible code and a knack for translating theoretical ideas into deployable tools.
14 years of coding experience
University of California San DiegoBachelor of Science (BS), Information and Computational Science, 3.9/4.0, Bachelor of Science (BS), Information and Computational Science, 3.9/4.0 at Sun Yat-Sen University
English, Chinese, Chinese
Stackoverflow
1reputation
18reached
0answers
1question
Github Skills (10)
mask-rcnn10
faster-rcnn10
mxnet10
deep-learning10
batch-normalization10
python10
gluon9
mnist7
callback6
javascript6
Programming languages (23)
Github contributions (5)
zackchase/mxnet-the-straight-dope
Aug 2017 - Aug 2017
An interactive book on deep learning. Much easy, so MXNet. Wow. [Straight Dope is growing up] ---> Much of this content has been incorporated into the new Dive into Deep Learning Book available at https://d2l.ai/.
Role in this project:
ML Engineer / Data Scientist
ML Engineer / Data ScientistContributions:13 commits, 5 PRs, 4 comments in 15 days
Contributions summary:Junwen primarily contributed to implementing and refining batch normalization techniques within the context of deep learning models, specifically focusing on convolutional neural networks (CNNs) and multi-layer perceptrons (MLPs). Their contributions involved both scratch implementations and the use of the Gluon framework, demonstrating a solid understanding of the underlying principles and practical application of batch normalization. The user also addressed minor coding style improvements and wording corrections within the project.
pytorchd2lmxnetdeep-learninghas-content
fyears/electron-python-example
Jun 2015 - Dec 2019
Electron as GUI of Python Applications
Contributions:23 commits, 8 PRs, 22 pushes in 4 years 6 months
pythonelectronguipython-applicationspython3
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.