Foundations of Artificial Intelligence

AIAA 5032, Spring 2023

Instructors: Junwei Liang


Home Schedule

Lecture:
Date and Time: 04:30PM - 05:50PM, Wednesday and Friday
Location: Rm 134, E1
Websites: Canvas

Course Description:
This course aims to provide students with an overview of Artificial Intelligence principles and techniques. Key topics include machine learning, search, game theories, Markov decision process, constraint satisfaction problems, Bayesian networks, etc. Through this course, students will learn and practice the foundational principles, techniques and tools to tackle new AI problems.

Target Audience/ Prerequisites: This is a graduate course primarily for graduate students. Basic Python programming and linear algebra knowledge is required.

Course Work:
Grading      Grading will be based on three assignments (50%) and a course project (45%). Note that 5% of your grade is assigned to attendance.
Assignments
  • The goal of the assignments is to make sure that the fundamentals of AI are understood by all participants.
  • There are 3 homework assignments over the semester, where you will typically have two weeks' time to work on each. (Tentative credit distribution: 15%/15%/20%)
  • Submission will be on Kaggle and Canvas.
  • We will post performance cutoffs for HIGH and OK for Kaggle competitions. There will be a leaderboard for each assignment to encourage trying extra things. Submissions above OK will get full credit. Submissions above HIGH will get an extra 2% credit for each assignment.
  • Homework assignments and course project results are worth full credit on the due date. Unless granted an extension in advance, it is worth at most 75% credit for the next 48 hours, at most 50% credit after that. If you need an extension, please ask for it as soon as the need for it is known. Extensions that are requested promptly can be granted more liberally. You must turn in all assignments.
  • Each homework is an individual assignment.
Project
  • The goal of the course project is to define and perform a small-scale experiment on your own, in order to gain hands-on experience which can then be scaled and generalized to other AI tasks.
  • Can be done in groups, defined at the beginning.
  • Topic ideas will be provided, but you can suggest your own (if suitable)
  • The project is worth 45% of your grade. These points are distributed as follows: 10% - Proposal Report (one-page); 15% - Project Presentation (midterm and final); 20% - Project report.
  • May involve virtual machines, AWS, Colab and Kaggle.

Instructors:
Junwei Liang
Rm 304, E4
Office hours: Wednesday 03:00PM - 04:00PM

Teaching Assistants:
TBD
TBD
Office hours: TBD
Collaboration among Students: We encourage collaboration between students and studying materials in groups when the purpose of this is to facilitate learning, not to circumvent problems. It is allowed to seek help from other students in understanding the material needed to solve a particular problem. However, students must submit individual material and solutions, unless otherwise specified. Students should declare any collaboration on the first page of homework assignments (or equivalently on exercises). If the instructors believe the collaboration is improper, your grade may be affected.