Teaching
CSE 5835: Machine Learning for Physical Sciences and Systems
A graduate-level course that builds foundational skills in applied machine learning for the physical sciences. Topics include methods for small, noisy, and imbalanced data; feature selection and representation learning; model selection and assessment; interpretable machine learning; and uncertainty quantification. The course also introduces current AI for science research, including data-driven learning of dynamical systems, generative materials design, and self-driving labs, with applications in materials, chemistry, physics, and manufacturing.
CSE 4820/5819: Introduction to Machine Learning
A first course in machine learning, covering supervised and unsupervised learning: classification, regression, clustering and dimensionality reduction. Students derive classical methods such as logistic regression, ordinary least squares, k-means clustering and principal component analysis, and explore support vector machines, decision trees and neural networks. The course also covers machine learning best practices for model selection and model evaluation.
CSE 4939W and CSE 4940: Senior Design
Qian Yang works with UConn School of Computing senior design teams as a faculty advisor, project sponsor, or both, frequently on projects in computing for science.
- Bridging the Gap Between Developers and Scientists via Technical Support for Self-Driving Labs
- GUI Development for Machine Learning-Enabled Inverse Analysis of Scattering Experiments
- Building a Machine Learning Model to Interpret Virtual X-ray Diffraction Patterns
- Light Scattering Automation
- Solubility Data Management
Other projects
Only projects with a public page on UConn’s Senior Design Day site are listed here.
- Language Interface and Learning Platform for Accessible Quantum Programming
- The Daily Digital Campus: UConn and the World, At Your Fingertips
- NUWC Signal Collection Device
Other selected teaching
- CSE 3666: Introduction to Computer Architecture, UConn (Fall 2018)
- Monte Carlo Methods, Army High Performance Computing Research Center Summer Institute, Stanford (2015, 2016; Best Instructor Award, 2016)