COMS E6998 (Spring 2024)

Lecture Details

Instructor: Suman Jana
Office: Mudd 412
Office hours: by appointment
Classroom: 1127 Seeley W. Mudd Building
Class hours: Thursday (1:10-3:40 pm)

Description

This class is going to focus on application of data-driven ML models trained on code for program reasoning and approximation tasks.

Note:There will be no assigned textbook for the class and you are expected to read the assigned articles/papers/slides carefully, and take notes.

Prerequisite

There is no formal prerequisite for this class but you should be generally comfortable with ML. Feel free to send me an email if you have any specific questions.

Grading

• Project - 60%
• Presentations - 30%
• Class participation - 10%

Please find the class notes here: Google drive .

Schedule

Date	Topics	Lecture notes & Reading
Jan 18	Intro
Jan 25	Neural Program Repair	Survey
Feb 1	Natural language to program generation	Program Synthesis with LLMs
Feb 8	Robustness of program generation	ReCode: Robustness Evaluation of Code Generation Models