Introduction to Machine Learning
Machine learning foundations, model evaluation, and practice.
Courses and research supervision in AI, robotics, graphics, and multimodal systems.
At UW Tacoma, I teach courses that connect core computer science foundations with current advances in AI, robotics, computer graphics, and multimodal systems. My teaching emphasizes technical depth, hands-on implementation, empirical evaluation, reproducible experimentation, and open-ended project work.
I develop and refine my courses through student feedback, peer input, curriculum-level review, and faculty development activities, including the Student Experience Project and Teaching@UW.
Current UW students across Seattle, Tacoma, and Bothell can enroll through UW cross-campus registration, subject to course capacity, prerequisites, registration periods, and home-campus requirements. Undergraduate students must satisfy UW home-campus credit and registration-period requirements for cross-campus registration; graduate students have no cross-campus registration restrictions.
Official course descriptions are available through the UW Course Descriptions.
Machine learning foundations, model evaluation, and practice.
Algorithm design, analysis, complexity, and problem solving.
Robot perception, localization, planning, control, and embodied AI.
Rendering, geometry, image synthesis, and visual computing.
Vision-language modeling and multimodal foundation models.
Selected special topics may vary by quarter. Students should consult the UW Time Schedule for official registration information.
I also mentor undergraduate and M.S. students through the Multimodal Intelligence Lab (MILab), independent study, supervised research, thesis projects, and capstone projects. My mentoring philosophy emphasizes rigorous scientific thinking, reproducible research, technical communication, collaborative problem solving, and the development of deployable AI systems with real-world impact.
Current UW students across Seattle, Tacoma, and Bothell can pursue research credit through the appropriate TCSS pathway, such as TCSS 499, TCSS 600, TCSS 700, or TCSS 702, depending on student level, project type, and degree requirements. Students interested in research supervision should contact me before registration to discuss research fit, project scope, supervision capacity, expected deliverables, quarter timeline, and credit pathway. Individualized research credits require instructor approval and may require a faculty number or departmental registration support.
Supervised undergraduate research in MILab.
Graduate independent study or research credit.
M.S. thesis research supervision.
Capstone supervision for applied research projects.