Shuyu Cheng is an engineer with a decade of experience specializing in deep learning and unsupervised learning, holding an M.S. in Computer Science from National Central University and active membership in CILAB. Currently at MediaTek in Hsinchu, she blends research-grade probabilistic modeling skills with practical engineering, having contributed AIS evaluation and HMC improvements to the zhusuan Bayesian deep learning library. Her background includes migrating legacy systems to Python and working with Oracle databases, reflecting versatility across research and production codebases. A geography enthusiast outside work, she brings a data-driven, curious approach to machine learning problems and a track record of making complex probabilistic models more reusable and performant.
A probabilistic programming library for Bayesian deep learning, generative models, based on Tensorflow
Role in this project:
ML Engineer
Contributions:76 commits, 10 PRs, 65 pushes in 2 years 5 months
Contributions summary:Shuyu added an AIS (Annealed Importance Sampling) evaluation for the LNTM (Logistic Normal Topic Model) model, which is a probabilistic programming library for Bayesian deep learning. This involved modifying the code to include the AIS evaluation framework within the existing LNTM model and its associated dependencies. Furthermore, the user made additional changes to improve reusability and HMC sampling, ensuring the model's functionality and performance. The user's changes focused primarily on the probabilistic modeling components of the project.
Contributions:13 commits, 2 PRs, 11 pushes in 1 year 1 month
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.