Grad AI
Overview
What?
This course is targeted at graduate students who need to learn about current-day research, and about how to perform current-day research, in Artificial Intelligence—the discipline of designing intelligent decision-making machines.
Students entering the class should have a pre-existing working knowledge of linear algebra, calculus, algorithms and data structures, and basic knowledge of computational complexity though the class has been designed to allow students with a strong numerate background to catch up and fully participate. Students should also be able to program in C, C++, Java, Python, or Ruby.
The course textbook is Artifical Intelligence: A Modern Approach, 3rd edition, by Russell and Norvig. This is not a required purchase. We will supplement readings in this book with timely research papers posted to the course website.
Who?
The course is taught by professors Martial Hebert (RI) and Ariel Procaccia (CSD). The teaching assistant is John Dickerson (CSD). The course is open to graduate students in the School of Computer Science; interested and qualified undergraduates and other students should contact the professors for permission to join.
When and where?
We meet most Mondays and Wednesdays from 12:00pm to 1:20pm in GHC 4215. The first lecture will be held on Wednesday, January 18. Check the lecture schedule below for details!
The TAs will also hold weekly informal recitations at 5:00pm on Thursdays in GHC 4303. Weekly office hours will be held at the following times and locations:
| Name | Day | Hours | Location |
| John Dickerson | Wednesdays | 5:00–6:00pm | GHC 9219 |
| Martial Hebert | Thursdays | 9:00–10:00am | EDSH 224 |
| Ariel Procaccia | Fridays | 9:00–10:00am | GHC 9021 |
| Felipe Trevizan | Tuesdays | 9:00–10:00am | GHC 8223 |
Lectures
All lecture and homework dates and topics are subject to change. This is a rough outline of the topics we will be covering this semester.
Schedule
Homework
Homeworks are due at the begining of class, unless otherwise specified. You will be allowed 5 total late days without penalty for the entire semester. Each late day corresponds to 24 hours or part thereof. Once those days are used, you will be penalized according to the policy below: Homework is worth full credit at the beginning of class on the due date. For the next 24 hours, it will be graded so that the highest possible score is equal to the 70th percentile of the distribution of scores of the on-time homeworks. For example, if your raw score is 80 out of 100 points, but the 70th percentile of the HW distribution is 85/100, then you will get credit for 80 * (85/100) = 68 points. For the following 24 hours, it will be graded out of the 40th percentile of the on-time homeworks. Thereafter, it will be worth nothing. You must turn in all of the homeworks, even if for reduced credit, in order to pass the course.
Schedule
| HW | Release Date | Due Date | Subjects Covered | Link | Notes |
|---|---|---|---|---|---|
| #2 | 2/15/2012 | 2/29/2012 | MDPs and classical search | — | Out soon! |
| #1 | 1/30/2012 | 2/13/2012 | Probabilistic inference | Extra data: |
Project
In lieu of a final exam, students will complete a course project. We encourage students to combine techniques from AI with their own research for these projects. Projects will be accompanied by a 6-8 page paper due at the end of the semester and a poster presentation session at a date and time to be determined.
Project proposals are due on February 22, and should consist of a short but well-researched summary of your project idea accompanied by a plan of execution. Students are allowed (and encouraged) to work in groups; however, the expectations we will have for your project rise proportional to the group size! We'll post some project ideas in the future.
Bureaucratic Miscellania
Grades
Grades are based on Class Participation (10%), Homeworks (35%), Final Project (35%) and the Midterm (20%).
Auditing the class
Interested students should first register, then fill out an audit form and have one of the instructors sign it. Auditors are required to complete a class project, but no homeworks or exams: that way they can choose to focus their efforts on whichever area of AI most interests them.
To those outside CMU
Feel free to use the slides and materials available online here! If you use our slides, an appropriate attribution is requested. Please email the instructors with any corrections or improvements.
