In addition to each of our subteam specific projects, we also take on many projects as an entire team. These are open to anyone regardless of subteam and usually incorporate many different aspects of software engineering, data science, and machine learning.
The Bias Lab at Cornell
Machine learning is a once-in-a-generation technological shit that will transform how our society works. It’s even been described as the fourth industrial revolution; this advance is creating huge value by unlocking insights from data and touches almost every aspect of our lives from choosing the music we listen to, what vacation trips we take, and even who will get hired for their dream job. But algorithmic bias is still a major concern as these systems become even more widespread. Unless careful care is taken with these ML systems, they can have significant harmful impacts on underrepresented groups and lead to ineffective products. Our more technical objective is to explore these biases within a variety of models, and attempt to mitigate them. Beyond the technical material, we hope to educate our local community as much as possible to be knowledgeable and informed when discussing these problems along with potential solutions.
Self Driving Car
CDS Self-Driving Car aims to demonstrate tight integration of a camera based vision algorithm to navigate a car safely. We utilize a SLAM system to localize ourselves, and an additional lane recognition pipeline to see the road. This is all built upon a Python control loop and will leverage robotics to directly actuate the steering wheel to augment a normal car.
CoalescenceML is an open-source MLOps framework to quickly, and easily set up your data/ml pipelines. We want to provide an end-to-end machine learning development process to design, build and manage reproducible, testable, and evolvable ML-powered software integrating with a host of tools on the market, or allowing you to extend our tool to meet your needs.
MyCourseIndex acts as an essential search engine for Cornell students and their courses with the initial goal to improve the Piazza search user experience. This search gathers all information from Piazza/EdStem posts to Textbook and Notes Resources (even lecture videos!) and returns valid results for the student to utilize. The team is currently working to expand the current search capabilities to answer questions automatically!
This was a cross-team collaboration project with members across Education, Insights, Data Engineering, and Intelligent Systems. The team was tasked with investigating epidemiology within a data science context. This culminated in a 7 page research paper submitted to the competition.