Outreach
Mentor for Young Scholars Senior Summit Program
In Summer 2021, I hosted a virtual research site for two minority scholars of the Young Scholars Senior Summit (YSSS), a three-week high school scholar research program hosted by Uconn since 2018 and funded by the Jack Kent Cooke Foundation. Please read this article for more information about this program.
The title of my research site is "Multi-Agent Reinforcement Learning for Connected and Autonomous Vehicles". In particular, the young scholars participated research with PhD students, and learn about how machine learning and control technologies will change future connected and autonomous vehicles (CAV). They learn about basic concepts of machine learning, especially reinforcement learning, and control theories. They also run experiments through simulators (such as CARLA or F1/10th racing car simulator) or F1/10th racing car testbed to demonstrate CAV research results.
Teaching
Spr 2021 CSE5095/SE5201 Embedded/Networked Systems Modeling Abstractions
The goals of this course are to familiarize students with designing, implementing and verifying embedded systems, and to provide skills necessary to specify requirements and perform platform-based design, analysis and modeling of embedded and networked systems. These models will be motivated by applications from industry which demonstrate embedded systems design challenges of satisfying time-critical, event-driven, and data-centric requirements.
Fall 2020 CSE4820/CSE5819 Introduction to Machine Learning
The objective of the course is to introduce basic concepts in machine learning to undergraduate students, and enable them to use machine learning methods and algorithms in real-life applications. This course covers basic topics of machine learning, such as supervised learning (logistic regression and naive bayes for classification, linear and polynomial regression, support vector machine, etc), unsupervised learning (K-means clustering) and some advanced topics, such as kernel and deep learning. Because of the diversity in machine learning topics, the materials covered in this course may vary among semesters. The course consists of lectures, programming-involving and non-programming assignments and exams. Lectures will serve as the vehicle for the instructor to introduce concepts and knowledge to students. Exams are used to test if certain basic concepts have been mastered. Programming-involving assignments will be used for students to get profound hands-on experience by programming certain machine learning algorithms identified from the recent literature.