-
-
This is a mock up of what the platform will look like for students where they will be able to see their edu. material and suggested learning
Inspiration
The inspiration for this project comes from the simple fact that the current educational system is in urgent need of innovation at all levels. My passion for pursuing this idea has allowed me to gather insights and envision a tool that can be useful to improve students' learning experience. I thought about the amazing reservoir of online learning content and lectures that are waiting to be consumed, but that are locked behind a language barrier and therefore difficult to access. I seek to utilize AI in order to make it easier for students to learn a new and difficult concept, even in a language unfamiliar to them.
What it does
Currently, the application functions as a Chrome extension that activates whenever you watch a YouTube video. At any time, you can rate your current understanding or grasp of the focus topic, which will guide our application's recommendations on what videos and material to study next. I additionally have a website that functions as a main hub for the extension, tracking your progress of learning any given subject and suggesting how to continue learning.
How we built it
The Chrome extension runs on a Flask application server, utilizing both YouTube's and OpenAI's APIs to guide the recommendations. The web application utilizes a Flask backend with a React frontend. The learning model that was implemented is GPT-3 due to its efficiency in using deep learning to produce human-like text.
Challenges we ran into
The application involves multiple moving parts, including a Flask backend server, a React frontend website, and a Chrome extension script. The biggest challenge was working out how those components could all work together in harmony, setting up the integration between GPT-3 and Youtube in order to make the best possible content recommendation was one that really stood out. We had to be careful with the way in which the parameters were passed to be used by the ML models to process the data and make an accurate suggestion.
Accomplishments that we're proud of
We are proud of both sides of our application that we have created: the Flask + React web server that hosts the main web hub for the application, and the Chrome extension that utilizes AI to offer a functional product on its own. These components have huge potential even independently, so we can't wait to see the possibilities of combining their capabilities.
What I learned
Throughout the process of bringing this idea to life I have learned about what it takes to pursue a project that is truly going to have an impact on the world. I also learned that the challenges that I come across are not impossible to overcome, especially when utilizing the resources such as the many talented people that surround me.
What's next for Romulus.
I have gotten selected to participate in an MIT one month incubator this winter where I will be working alongside two other MIT CS seniors to create an MVP for Romulus. From now until then we will be doing research regarding what is the best approach to the solution we believe will help countless students.
Log in or sign up for Devpost to join the conversation.