COMPSCI 596E Machine Learning Applied to Child Rescue
3 Credits
Meetings: Monday and Wednesdays 1130-1245
Instructors:
Prasanna Lakkur Subramanyam
Brian Levine
Description: Students will work collaboratively to construct production-grade software used to advance the goal of Child Rescue. This course is a group-based, guided independent study. Our goal is to build practical machine learning software to be used by professionals dedicated to rescuing children from abuse. Students will be encouraged to design and build their own diagnostic and machine learning tools, while also learning from professionals in the fields of digital forensics and law enforcement. An emphasis is placed on practicing real world professional software engineering skills, such as dealing with limiting scope, production concerns, and working in the presence of poorly defined problems. The entire student group will meet twice a week to share progress via short presentations. Open to senior Computer Science majors, MS-CMPSCI majors, and CS PhD students. 3 credits
In fall 2025, the goal of the class will be to provide a single open-source application that unifies all student work called RescueBox. Each team will either: improve an existing or introduce a new ML-based plug-in, contribute to the RescueBox front-end; or contribute to the RescueBox backend.
Detailed information about the course, and instructions on how to apply to enroll, are on this page for fall 2025.