A Graduate Course in Artificial Intelligence
TR 9.35am-10.55am, Instructional Center 109
Professor: Thad Starner
Thad: 6-7:30pm on Mondays TSRB 239
Office Hours: 3-8pm on Fridays TSRB 239
Office Hours: 1-5pm on Wednesdays CCG lab outside TSRB 239
This is a graduate class. Having taken an AI class before will definitely make the class easier, but motivated students will be able to survive by self-study of the foundational material, which I will not lecture on in detail. Rather, you will be asked to review or self-study the basic material prior to each module (see below).
Communication about the class:
All communication from me will be done through T-square. Please read all announcements and email promptly.
If you want to email any of the instructors, please put “CS6601” in the subject line.
The desired learning outcomes for the students are:
•Foundation: Having a strong foundation in AI techniques
•Skills: Being able to propose, evaluate, and implement solutions to problems requiring AI techniques
•Integration: Be aware of where AI intersects with other disciplines, primarily machine learning, vision, and robotics.
•Assessment: Exposure to different flavors of problems and solutions, and develop a taste for some, and having confidence in how and where AI can be applied in problems relevant to society
There are several activities designed to achieve the learning outcomes above:
1)Foundation: there will be 8 assignments on foundational material, due at the beginning of each module (see below).
2)Skills and Integration: There are two mini-projects in which you will choose, propose and research a problem that you might encounter in your future career (be it in academia, industry, or government), propose a solution, implement it, and describe it in a mini-conference paper. Projects should be done in teams of 2 students, and each of the two projects must be completed with a different partner.
3)Assessment: The content in the midterm and final provide a guide to the operating knowledge a researcher in AI should have when working in the field. While many detailed algorithms and processes can always be referenced in a textbook, being able to reason from principles on-the-fly is critical for discussions with colleagues.
More details will be communicated at appropriate times throughout the course, including grading criteria and standards.
Structure and Sequence of Class Activities
This course is probably different from many other courses you have taken at Georgia Tech, in that it does not follow the usual lecture pattern. Instead, while there are also conventional lectures, the course is different in two major aspects:
1)You are expected to review or study the foundational material outside class time. You will be asked to (re-)read the chapters in AIMA before the start of each module, as indicated on the schedule. Reading textbook material can be tedious, but it is necessary for you to acquire this foundation if you have not previously taken an AI class, or review it if you did. To motivate you and at the same time reward you with a grade for your hard work, an assignment based on this reading material is due the day we start with the in-depth discussions needing those foundational chapters.
2)The lectures will be reserved for advanced topics and active learning activities. Research has shown that students are happier and retain material better if they participate actively in the learning rather than simply taking notes in lectures. In this course, in particular, I built in two mini-projects described above that will have substantial in-class activities associated with them. In particular, on the due date of each project proposal, we will assemble review panels in class to review and give feedback on each proposal. On the due date of the project paper, we will similarly form mini area chair meetings in which the best papers are singled out for presentation in class.
A detailed schedule, subject to change, can be found on the schedule page.
I will be using the blackboard a lot, rather than powerpoint. Students are expected to take notes and consult the primary sources on the material, available from the website.
Collaboration on assignments is encouraged at the "white board interaction" level. That is, share ideas and technical conversation, but write your own code. Students are expected to abide by the Georgia Tech Honor Code. Honest and ethical behavior is expected at all times. All incidents of suspected dishonesty will be reported to and handled by the office of student affairs.
Foundation: Assignments 40%. When the extra problem is done so as to turn in the assignment one class period late, 50% of the grade will be on the extra problem and 50% will be on the assignment.
Skills: Mini-Projects 50%
•Project 1 (20%): proposal 1%, proposal panel review 1%, revised proposal 3%, paper 4%, paper panel review 1%, revised paper 8%, presentation 2%
•Project 2 (30%): proposal 1%, proposal panel review 1%, revised proposal 3%, paper 5%, paper panel review 1%, revised paper 15%, presentation 4%
Assessment: mid-term 5%; final 5%