Tzer-jen Wei
Associate Professor
Taipei, Taiwan
Summary
🤩
Rockstar🎓
Top SchoolTzer-jen Wei is an associate professor and AI practitioner based in Taipei with 14 years of experience at the intersection of mathematics, cryptography, and machine learning. With a PhD in Mathematics from Caltech and a long academic track record, he translates theoretical rigor into practical AI solutions as a consultant and course lecturer for industry and government. He contributes to open-source tooling and testing—improving Cython’s type-testing infrastructure—and has implemented and experimented with GAN variants across Lasagne, Keras, and PyTorch. A community builder, he founded local Python and R user groups, helps organize PyCon events, and serves on Taiwan’s IMO advisory committee, reflecting a commitment to education and outreach. His work blends deep math intuition with hands-on ML engineering, and he even used his own neural-style avatar generator to craft a distinctive Hatsune Miku profile image.
14 years of coding experience
14 years of employment as a software developer
Master, Math, Master, Math at National Taiwan UniversityPhd, Math, Phd, Math at California Institute of Technology
Chinese, English
Github Skills (16)
lasagne10
keras10
pytorch10
test-framework10
cgan10
cyclegan10
python10
generative-adversarial-network10
dcgan10
cython10
testing10
mnist9
deep-learning9
tensorflow8
computer-vision7
Programming languages (7)
Github contributions (5)
tjwei/GANotebooks
Dec 2016 - Feb 2018
wgan, wgan2(improved, gp), infogan, and dcgan implementation in lasagne, keras, pytorch
Role in this project:
ML Engineer
ML EngineerContributions:88 commits, 79 pushes, 2 branches in 1 year 2 months
Contributions summary:Tzer-jen implemented and modified a series of notebooks, primarily focusing on the implementation of generative adversarial networks (GANs) and related architectures, including WGAN, InfoGAN, and DCGAN. Their contributions involved porting and experimenting with these models in different frameworks, particularly Lasagne, Keras, and PyTorch. The user's commits demonstrate a deep understanding of GAN training processes, loss functions, and the application of these techniques to the MNIST dataset.
pytorchinfogancycleganwganimproved
cython/cython
Jul 2015 - Jul 2015
The most widely used Python to C compiler
Role in this project:QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:5 commits, 2 PRs, 3 comments in 21 days
Contributions summary:Tzer-jen primarily focused on enhancing the testing infrastructure within the Cython repository. Their commits involved adding tests for core Python data structures like lists, sets, and dictionaries, ensuring correct type handling by the `jedi-typer` tool. Furthermore, the user made adjustments to the testing framework to support newer versions of the jedi library and improved type annotations, contributing to robust and accurate type analysis within the project.
cpython-extensionscpppythonpython-bindingsbig-data
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.