Graduate Artificial Intelligence
This course is targeted at graduate students who are interested in learning about artificial intelligence. The focus is on modern AI techniques. The course also covers techniques from the intersection of AI and other disciplines such as integer programming, continuous optimization, and game theory. The course content is profiled so as to not have too much overlap with narrower specialized AI courses offered at CMU.
There are no formal pre-requisites for the course, but students should have previous programming experience (programming assignments will be given in Python), as well as some general CS background. Please see the instructors if you are unsure whether your background is suitable for the course.
|J. Zico Kolterfirstname.lastname@example.org||TBA||GHC 7115|
|Ariel Procacciaemail@example.com||TBA||GHC 7002|
|Brandon Amosfirstname.lastname@example.org||TBA||GHC 9221|
|Shayan Doroudiemail@example.com||TBA||GHC 8127|
|Anson Kahngfirstname.lastname@example.org||TBA||GHC 6207|
|Kijung Shinemail@example.com||TBA||GHC 9005|
|1/18||Introduction||Kolter+Procaccia||slides 1||video 1|
|2/6||Integer Programming 1: Theory||Kolter|
|2/8||Integer Programming 2: Applications||Procaccia|
|2/13||Machine Learning 1: Regression and Classification||Kolter|
|2/15||Machine Learning 2: Nonlinear Methods||Kolter|
|2/20||Computational Learning Theory||Procaccia|
|2/22||Deep Learning 1: Neural Networks||Kolter|
|2/27||Deep Learning 2: Backpropagation||Kolter|
|3/6||Deep Learning 3: Convolutional and Recurrent Models||Kolter|
|3/8||Probabilistic Modeling 1: Bayesian Reasoning||Kolter|
|3/20||Probabilistic Modeling 2: Probabilistic Inference||Kolter|
|3/22||Probabilistic Modeling 3: MCMC||Kolter|
|3/27||Deep Learning 4: Generative Models||Kolter|
|3/29||Game Theory 1: Basics||Procaccia|
|4/3||Game Theory 2: Zero-sum Games and No-regret Learning||Procaccia|
|4/5||Game Theory 3: Stackelberg and Security||Procaccia|
|4/10||Game Theory 4: Extensive Form||Procaccia|
|4/12||Social Choice 1: Basics||Procaccia|
|4/17||Social Choice 2: Statistical Approaches||Procaccia|
|4/19||Social Choice 3: Advanced Statistical Approaches||Procaccia|
|4/24||AI and Education 1||Doroudi|
|4/26||AI and Education 2||Doroudi|
|5/1||AI and Education 3||Doroudi|
There will be four assignments (not including HW 0): they will involve both written answers and programming assignments. Written questions will involve working through algorithms presented in the class, deriving and proving mathematical results, and critically analyzing the material presented in class. Programming assignments will involve writing code in Python to implement various algorithms presented in class.
Please submit your assignments on Autolab here. Scan handwritten parts of your homework and include them in your autolab submission.
|Homework 0||search.py||January 27, 11:59pm|
Students will also complete a course project. Late days may not be used on the course project.
Homework is due on autolab by the posted deadline. Assignments submitted past the deadline will incur the use of late days.
You have 5 late days, but cannot use more than 2 late days per homework. No late days may be used for HW 0. No credit will be given for homework submitted more than 2 days after the due date. After your 5 late days have been used you will receive 20% off for each additional day late.
You can discuss the exercises with your classmates, but you should write up your own solutions. If you find a solution in any source other than the material provided on the course website or the textbook, you must mention the source. You can work on the programming questions in pairs, but theoretical questions are always submitted individually. Make sure that you include a README file with your andrew id and your collaborator's andrew id.
The class includes a midterm exam, tentatively scheduled for March 1st.