This course covers a broad range of AI-related topics at a fast pace including machine learning, search algorithms, Markov decision process, games, constraint satisfaction problem, graphical models, and logic. This course focuses on understanding the fundamental concepts and principles on each topic. Accordingly, programming assignments will be implementing the core ideas with native python rather than blindly using AI libraries or tools.

- Prerequisites: CSED233 Data structure, mathematical backgrounds in calculus, linear algebra, and probability & statistics, and some level of programming skills.
- 수강 정원이 찼을 경우, POSTECH 컴공과 학부생 및 컴공지망 무은재학부생만 추가 등록 가능.

HW 28%
Midterm 36%
Final 36%

There will be two exams – midterm and final exams.
Each exam will be held offline in class (TuTh 3:30pm~4:45pm).
Exams will test you how well you understand the lecture materials and how well you did HWs by yourself.

Related topics are also discussed in the following books, but require much more time to read and understand the same concepts.

Russell and Norvig. Artificial Intelligence: A Modern Approach. A comprehensive reference for all the AI topics that we will cover.
Koller and Friedman. Probabilistic Graphical Models. Covers factor graphs and Bayesian networks.
Sutton and Barto. Reinforcement Learning: An Introduction. Covers Markov decision processes and reinforcement learning. (Available free online)
Hastie, Tibshirani, and Friedman. The elements of statistical learning. Covers machine learning. (Available free online)
Tsang. Foundations of constraint satisfaction. Covers constraint satisfaction problems. (Available free online)

W1. AI Introduction (HW1 out)
W2. ML1: Linear predictor, Loss minimization, Stochastic Gradient Descent (SGD)
W3. ML2 & 3: Features, Neural network, kNN, Generalization, Unsupervised learning (HW2 out)
W4. Search1: Tree search, Dynamic programming, Uniform cost search
W5. Search2: Learning costs, A* (HW3 out)
W6. MDP1: Markov Decision Process
W7. MDP2: Reinforcement Learning (HW4 out)
W8. Midterm
W9. Games1&2 (HW5 out)
W10. CSP1
W11. CSP2 (HW6 out)
W12. Bayes1
W13. Bayes2&3 (HW7 out)
W14. Logics
W15. Conclusion (HW8 out)
W16. Final exam

- This semester, face-to-face classes will be held in the classroom, except for the first two weeks of online lectures using PLMS Zoom.
- There is no required textbook for this class, so it is important to take notes during class.
- Lecture notes will be posted to the PLMS prior to class.
- There will be biweekly (written and programming) assignments which require a significant amount of time to complete, so start early!
- Programming assignments must be written in Python 3.x, not lower (Python 2.x) version. We recommend that you use a UNIX environment (e.g., Linux or OS X) for programming assignments.

You must write up HWs and code from scratch independently. The following are considered to be honor code violations:
Looking at the writeup or code of another student.
Showing your writeup or code to another student.
Discussing homework problems in such detail that your solution (writeup or code) is almost identical to another student's answer.
Uploading your writeup or code to a public repository (e.g. github, bitbucket, pastebin) so that it can be accessed by other students.
Looking at solutions from previous years' homeworks - either official or written up by another student.
When debugging code together, you are only allowed to look at the input-output behavior of each other's programs (so you should write good test cases!). It is important to remember that even if you didn't copy but just gave another student your solution, you are still violating the honor code, so please be careful.
We periodically run similarity-detection software over all submitted student programs, including programs from past semesters and any solutions found online on public websites. Anyone violating the honor code will get F no matter what.