This course introduces the characteristics and fundamental principles of artificial intelligence (AI) problems, as well as the basic theories and methodologies required to solve them. Specific topics include Machine Learning theory, Search algorithms, Markov Decision Process, Reinforcement Learning, Games, Factor graph and CSP, Bayesian network, and Logic. Through practical AI implementation exercises, students develop the ability to tackle real-world AI problems.

Prerequisites:
- CSED233 Data structure
- Mathematical backgrounds in calculus, linear algebra, and probability & statistics
- Some level of programming skills.

If the class is full, additional registration will be limited to current or prospective POSTECH computer science undergraduates.
수강 정원이 찼을 경우, POSTECH 컴공과 학부생 및 컴공지망 무은재학부생만 추가 등록 가능.

Reasons you must not audit:
- Attending a lecture is not the same as mastering the material. Without assignments and exams, you may feel like you’re learning, but the knowledge rarely moves into long-term memory.
- Why do the heavy lifting of a course for free? If you’re doing the assignments and taking the exams, take the credit too.

The course content and assignments closely align with Stanford’s CS221. To reinforce your learning, we recommend working through the Python exercises available on the Stanford course website and their lecture GitHub repository:
https://stanford-cs221.github.io/autumn2025/
https://github.com/stanford-cs221/autumn2025-lectures

Related topics are also discussed in the following books.
- 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. IntroAI, ML1 (HW1 out)
W2. ML2
W3. ML3 (HW2 out)
W4. Search1
W5. Search2 (HW3 out)
W6. Markov Decision Process
W7. Reinforcement Learning (HW4 out)
W8. Midterm
W9. Games (HW5 out)
W10. Factor graph and CSP 1
W11. Markov networks (HW6 out)
W12. Bayesian networks 1
W13. Bayesian networks 2 (HW7 out)
W14. Logic
W15. Conclusion (HW8 out)
W16. Final exam

Class format:
- Face-to-face classes will be held in the classroom.

Course materials:
- Lecture slides will be posted on the PLMS prior to each class.
- As there is no textbook and the material is abstract, note-taking during class is strongly recommended.
- This course covers many topics quickly. Pre-study will enhance your understanding and active participation in class. Use your class time mainly for Q&A.

Assignments:
- Biweekly programming assignments: These assignments require significant time and effort. Start early to avoid falling behind.
- Programming language: Assignments must be written in Python 3.x.
- Development environment: A UNIX environment (e.g. Linux) is recommended for development.

You must write up HWs and code by yourself. 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.