Graduate Artificial Intelligence
This course provides a broad perspective on AI, covering (i) classical approaches of search and planning useful for robotics, (ii) integer programming and continuous optimization that form the bedrock for many AI algorithms, (iii) modern machine learning techniques including deep learning that power most recent AI applications, (iv) game theory and social choice that capture interactions between multiple agents, and (v) issues of bias and unfairness in AI. In addition to understanding the theoretical foundations, we will also study modern algorithms in the research literature.
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.
|Stephanie Rosenthalemail@example.com||By appointment on Zoom|
|Nihar B. Shahfirstname.lastname@example.org||By appointment on Zoom|
|Sophie (Yue) Guoemail@example.com||Thursdays 11a-12p|
|Carlos Martinfirstname.lastname@example.org||Tuesdays 9p-10p|
|Minji Yoonemail@example.com||Mondays 1p-2p|
To schedule an appointment with Prof. Rosenthal or Prof. Shah, please send an email with your availability, as well as the topics you would like to discuss (e.g., specific lectures or project content).
You are encourages to reach out with discussion/questions on Diderot.
Videos for all classes are available on Panopto
|2/1||Introduction + Search||Rosenthal|
|2/10||Linear Programming I: Basics||Rosenthal|
|2/15||Linear Programming II: Duality||Rosenthal|
|2/17||Integer Programming I: Theory||Rosenthal|
|2/22||Integer Programming II: Branch and Bound||Rosenthal|
|2/24||Integer Programming III: Applications||Shah|
|3/1||Machine Learning I||Shah|
|3/3||Machine Learning II||Shah|
|3/8||Machine Learning III||Shah|
|3/10||Machine Learning IV||Shah|
|3/15||Machine Learning V||Shah|
|3/17||Machine Learning VI||Shah|
|3/22||Paper Dissection Presentations||Teams Present|
|3/24||Probabilistic Modeling I: Basics||Rosenthal|
|3/29||Probabilistic Modeling II: Probabilistic Inference||Rosenthal|
|3/31||Probabilistic Modeling III: MCMC||Rosenthal|
|4/5||Game Theory I||Rosenthal|
|4/7||Game Theory II||Rosenthal|
|4/12||Game Theory III||Rosenthal|
|4/19||Social Choice I: Basics||Shah|
|4/21||Social Choice II: Manipulation||Shah|
|4/26||Social Choice III: Statistical Approaches||Shah|
|4/28||Humans and AI I: Fairness||Shah|
|5/3||Humans and AI II: Applications||Shah|
|5/5||Paper Dissection Presentations||Teams Present|
There will be eight assignments: 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.
Assignments will be released and due on Diderot. Scan handwritten parts of your homework, if any, and include them in your autolab submission.
Solutions will be released after the deadline and late dates.
Each homework is worth 5% of your final grade.
Homework is due on Diderot by the posted deadline.
You can use no more than 3 late days per assignment. These late days can and should be used in the event that something comes up that you did not plan for. You do not need to notify the course staff if you plan to use them. No credit will be given for assignments submitted more than 3 days (72 hours) after the posted deadline.
You can discuss both the programming and written portions with other students, but all final submitted work (code and writeups) must be done entirely on your own, without looking at any notes generated during group discussions. Be sure to mention your collaborators' names and Andrew IDs in your writeup.
Can search the internet for references but you are not allowed to post the questions on stackoverflow or anywhere else.
If you reference any code or sources other than the materials provided on the course website or the textbook, you must mention the source. If you have any questions about whether or not you can use a source, please ask.
The course paper dissections will be completed in randomly assigned groups. Groups will choose a paper to read, describe, and then dissect to further their understanding by implementing algorithms novel benchmarks or by relaxing assumptions on theoretical contributions. Paper dissections will culminate in presentations to the class. Detailed information about the paper dissections including requirements and guidelines will be available on Diderot.
We will be using Zoom for lectures, and Diderot for discussion, assignments and lecture polls. We very strongly encourage you to attend lectures live. Live attendance has been shown to increase student participation and interaction with the course material. If you cannot attend on Zoom for any reason, the recorded lectures will be available within a few hours of classes and you will have until Friday afternoon each week participate in online polls on Diderot (see Participation Grades). As always, the professors and TAs are happy to answer questions about lectures via posts on the lecture slides on Diderot or Zoom office hours or via email.
Participation will be based a combination of lecture polling questions answered and the quality of the feedback given to your peers' paper presentations. The lecture polling questions will be posted during lecture and remain open until the end of the week on Friday afternoon after which time we will close them and release the answers. You will be graded for accuracy on the questions you answer, and will receive 0 points for those unanswered. More details about the presentation feedback will be provided on Diderot.
The class includes a final exam worth 20% of the course grade, which will be distributed during final exams week.
If you have a disability and have an accommodations letter from the Disability Resources office, we encourage you to discuss your accommodations and needs with us as early in the semester as possible. We will work with you to ensure that accommodations are provided as appropriate. If you suspect that you may have a disability and would benefit from accommodations but are not yet registered with the Office of Disability Resources, we encourage you to visit their website.
Take care of yourself. Do your best to maintain a healthy lifestyle this semester by eating well, exercising, getting enough sleep, and taking some time to relax. This will help you achieve your goals and cope with stress.
All of us benefit from support during times of struggle. There are many helpful resources available on campus and an important part of the college experience is learning how to ask for help. Asking for support sooner rather than later is almost always helpful.
If you or anyone you know experiences any academic stress, difficult life events, or feelings like anxiety or depression, we strongly encourage you to seek support. Counseling and Psychological Services (CaPS) is here to help: call 412-268-2922 and visit their website at http://www.cmu.edu/counseling/. Consider reaching out to a friend, faculty or family member you trust for help getting connected to the support that can help.
If you have questions about this or your coursework, please let us know. Thank you, and have a great semester.
We must treat every individual with respect. We are diverse in many ways, and this diversity is fundamental to building and maintaining an equitable and inclusive campus community. Diversity can refer to multiple ways that we identify ourselves, including but not limited to race, color, national origin, language, sex, disability, age, sexual orientation, gender identity, religion, creed, ancestry, belief, veteran status, or genetic information. Each of these diverse identities, along with many others not mentioned here, shape the perspectives our students, faculty, and staff bring to our campus. We, at CMU, will work to promote diversity, equity and inclusion not only because diversity fuels excellence and innovation, but because we want to pursue justice. We acknowledge our imperfections while we also fully commit to the work, inside and outside of our classrooms, of building and sustaining a campus community that increasingly embraces these core values.
Each of us is responsible for creating a safer, more inclusive environment.
Unfortunately, incidents of bias or discrimination do occur, whether intentional or unintentional. They contribute to creating an unwelcoming environment for individuals and groups at the university. Therefore, the university encourages anyone who experiences or observes unfair or hostile treatment on the basis of identity to speak out for justice and support, within the moment of the incident or after the incident has passed. Anyone can share these experiences using the following resources:
All reports will be documented and deliberated to determine if there should be any following actions. Regardless of incident type, the university will use all shared experiences to transform our campus climate to be more equitable and just.