- Research Program Mentor
MS at Johns Hopkins University
Any topic in data science (machine learning, applied math, statistics), web development, or chemistry.
BioI have loved math and science since I was a kid; I participated in my first science fair when I was in 6th grade, and I continued until I graduated high school. When I was an undergrad at University of Michigan, I joined an organometallic chemistry lab, where we studied palladium-catalyzed alkene difunctionalization reactions. I decided to switch gears and focus data science for my master's because I wanted to do more math and programming. Data science is my true passion because its principles can be applied in any scientific discipline — data scientists get to dabble in everything! In my spare time, I work on a lot of DIY projects including designing websites, creating my own IPTV network, and training AI to play games. I enjoy playing Magic and D&D, and I host a small Minecraft server for family and friends. I also like to stay active; I'm a second-degree black belt in Japanese-style jujutsu, and I'm learning how to swing dance.
Impacts of the COVID-19 Pandemic on Education
This project will investigate how changes imposed by COVID-19 affect several metrics of educational quality, including changes in GPA, levels of stress, etc. Some examples of predictor variables include a student's region of residence (and vaccination rate in that region), their types of hobbies or extracurriculars, and the mode of instruction they received during the height of the pandemic. To accomplish this project, you will need to create and broadcast a survey to gather the data, which you will interrogate using machine learning and statistical analysis techniques.
Build Your Own Website (Self-Host a Web Server)
Use Reinforcement Learning to Play a Game
In this project, you will delve into the world of artificial intelligence by using reinforcement learning techniques to teach a computer program to play a game. You'll begin by selecting a game, such as a classic Atari game or a simple board game, and set up a suitable environment for training your AI agent. You will then learn about the fundamentals of reinforcement learning, including concepts like Q-learning, Deep Q-Networks (DQN), and exploration-exploitation trade-offs. You'll implement a training algorithm that enables the AI agent to learn game strategies and improve its performance over time. As the project progresses, you will analyze the agent's performance, identify areas for improvement, and fine-tune your model.