4190.428 Introduction to Machine Learning – Seoul National University

Overview

Machine learning systems have broad applications across humanities, arts, science and engineering disciplines, consumer electronics, and modern computing systems. In this course, students will learn the fundamental concepts and principles of machine learning, including supervised, unsupervised and reinforcement learning. The course introduces the underlying model architectures, algorithms, and mathematical foundations of these learning paradigms.

Designed as an introductory course, it covers classical methods for pattern recognition, probabilistic modeling and sequential decision‑making, while also introducing recent advances in representation learning and scalable generative modeling.

Logistics

Lectures: Tuesdays and Thursdays, 5:00–6:15 pm in Rm 209, Bldg 302.

Instructor office hours: Mondays 11:30 am–12:00 pm in Rm 321, Bldg 302; discussion about course material and projects.

TA office hours: questions about homework and lectures.
Yujin's OH: Tuesdays 6:15–7:15 pm in Rm 209, Bldg 302 (the lecture room).
Jinwoo's OH: Thursdays 4:00–5:00 pm in Rm 209, Bldg 302 (the lecture room).
To contact the TAs, please email ml-fall-2026-teaching-staff@reality.snu.ac.kr.

Textbook: There is no required textbook for the course; links to readings and course notes are provided in the Schedule.

Contact: Course announcements and general information will be posted on the course forum on eTL. To contact the teaching staff, please email ml-fall-2026-teaching-staff@reality.snu.ac.kr.

Schedule

The table below outlines the weekly topics and key milestones. Slides and readings will be linked here as the course progresses.

Wk	Date	Event	Description	Files
1	9/1	Lecture 1	Introduction, Overview, Fast Forward	[slides]
1	9/3	Lecture 2	Supervised learning, gradient descent	[slides] [model vis.] [GD vis.]
2	9/8	Lecture 3	Generalized linear models, regression
2	9/10	Lecture 4	Multi-class classification, feature representation
3	9/15	Lecture 5	Kernel methods
	9/17	Lecture 6	Support vector machines
	9/18	HW 1 out
4	9/22	Lecture 7	K-means clustering, EM, GMMs
4	9/24	No class	Chuseok holiday (추석)
5	9/29	Lecture 8	Principal component analysis
	10/1	Lecture 9	Neural network architectures
	10/2	HW 1 due	Homework 1 due at 11:59 pm
	10/2	HW 2 out
6	10/6	Lecture 10	Neural network training
6	10/8	Lecture 11	Generalization, regularization
7	10/13	Lecture 12	Generalization, regularization
	10/15	Lecture 13	Deep learning
	10/16	HW 2 due	Homework 2 due at 11:59 pm
8	10/20	Midterm	In-class exam (closed book)
8	10/22	Lecture 14	Discussion on midterm
9	10/27	Lecture 15	Machine learning applications
9	10/29	Lecture 16	Variational auto-encoder
10	11/3	Lecture 17	Generative modeling
	11/5	Lecture 18	Diffusion models
	11/6	HW 3 out
11	11/10	Lecture 19	Flow matching
11	11/12	Lecture 20	Representation learning, embeddings and contrastive learning
12	11/17	Lecture 21	Sequential models
	11/19	Lecture 22	Transformers
	11/20	HW 3 due	Homework 3 due at 11:59 pm
	11/20	HW 4 out
13	11/24	Lecture 23	Reinforcement learning
13	11/26	Lecture 24	Guest lecture Sungyoon Kim (Stanford University)
14	12/1	Lecture 25	Reinforcement learning
	12/3	Lecture 26	Guest lecture Dr. Wanhee Lee (Tesla)
	12/4	HW 4 due	Homework 4 due at 11:59 pm
15	12/8	Lecture 27	Non-parametric methods
15	12/10	Final Exam	In-class exam (closed book)
16	12/15	Lecture 28	Discussion on final Last day of class

Coursework

Helpful Background

Coding Experience (especially Python): All assignments will be in Python. Even though we don't assume prior experience in Python, you should familiarize yourself, for example by working through some online Python tutorials.
Calculus, Linear Algebra: Basic understanding of matrix algebra (e.g., least squares, orthogonality, eigendecomposition, SVD) will be helpful (e.g., 공학수학1/2, 선형대수학).
Probability and Statistics: Familiarity with probability theory, random variables and Bayes' theorem (e.g., 확률과정의 기초, 확률그래프모델).

eTL

All assignments should be submitted on eTL. Course announcements, lecture materials and the discussion forum also live there.

Assignments (10%)

There will be 4 homework assignments (see Schedule) in this class, each worth 25% of the assignment grade. These assignments contain theoretical questions as well as implementations of techniques that we discuss in class. Please refer to the assignment writeups (available in the Files column of the Schedule) for details. After you finish, submit your code and report on eTL.

Collaboration Policy: Students are permitted to work together on homework assignments in small groups. However, while students can discuss the assignments together, they must compose their solutions individually. Students must not view or copy code of other students or solutions available on the internet. Names of collaborators must be listed on submitted assignments. Submitting plagiarized solutions is an academic offense and can have severe penalties.

AI Assistants Policy: Generative AI may be used as a supplementary learning tool in this course. Students may use generative AI to explore ideas or topics needed to complete assignments and to analyze data. However, if generative AI is used to complete an assignment, the name of the tool used, the process of its use, and the generated content must be clearly stated in the assignment.

Midterm (45%)

There will be an in-class, closed-book midterm on October 20.

Final Exam (45%)

There will be an in-class, closed-book final exam on December 10.

Attendance

Attendance does not count toward your grade. However, by university policy, students who are absent for more than 1/3 of class days will receive an “F” or “U” grade. If you do not expect to be able to meet this requirement, we recommend that you not take this course; please contact the teaching staff in advance.

4190.428: Introduction to Machine Learning