Skip to main content

Spring 2026

Topics in Machine Learning (기계학습특론) - Graduate Course

Instructor: Dr. Muhammad Syafrudin

Course information

The objectives of this course are to explore different topics in machine learning, such as Regression, Deep Learning, Convolutional Neural Networks and Self-Attention, Transformers, Generative Models, Explainable AI, and Meta Learning. Through this class, students will gain new insights into recent developments in machine learning, allowing them to deepen their knowledge in areas of interest. Additionally, the course aims to foster research exchange and facilitate discussions among students.

Lecture

Thu 목13:00-16:00 KST at 광902호

Office hours

Appointment by email (Office at 김원관 419호)

Prerequisites

Prior knowledge of Calculus, Linear Algebra, and Probability will be advantageous but NOT required.

Notes


General Information
* All lectures are conducted in English.
* Weekly topics may change based on the class’s level of understanding.

Presentation Requirements
* Each student will give a 25–30 minute presentation.
* Each presentation is followed by a 10–15 minute Q&A session.
* Active participation is mandatory for all students during every Q&A.

Paper Selection
* Select your paper at least two weeks before your presentation date.
* Announce your paper on eCampus using this format:
"[Your Name] presents [Paper Title]."
* You may propose a different but relevant paper with instructor approval.

Paper Critique Assignment
- You must write a 1–2 page paper critique for each paper presented by your classmates.
- Each critique must include:
* 3 main points (topic, problem, solution)
* 3 strengths (novelty, impact, good aspects)
* 3 possible improvements (weaknesses or extensions)
* 3 questions about the paper

Submission Instructions
* Submit the paper critique before class (soft and/or hard copy) as assignments.
* Upload your presentation slides and paper critique to eCampus before your presentation.

Important Reminder: This course is research-based. Preparation and active participation are essential for success.


Schedule

주차(Week)강의내용(Class Topic & Contents)강의활동유형(Class Type)
1Course introduction (3/5)Lecture and discussion
2Intro to ML - regression (3/12)Lecture and discussion
3What is Deep Learning? (3/19)Lecture and discussion
4Convolutional Neural Networks & Self-Attention (3/26)Lecture and discussion
5Transformer (4/2)Lecture and discussion
6Generative Model (4/9)Lecture and discussion
7Explainable AI (4/16)Lecture and discussion
8Midterm exam (4/23)시험 (Exam)
9Meta Learning (4/30)Lecture and discussion
10Paper presentation and discussion - round one (5/7)Student presentation and discussion
11Paper presentation and discussion - round one (5/14)Student presentation and discussion
12Paper presentation and discussion - round one (5/21)Student presentation and discussion
13Paper presentation and discussion - round two (5/28)Student presentation and discussion
14Paper presentation and discussion - round two (6/4)Student presentation and discussion
15Paper presentation and discussion - round two (6/11)Student presentation and discussion
16Lecture Feedback and Wrap-Up (6/18)Tentative

Grading

The final grade will be calculated using the following weights:

#Final Grade Weight
Attendance15%
Assignment (Paper Critiques)15%
Mid exam30%
Paper Presentations & Discussions40%
Total100%

Assignment

There might be one or two student presentations, and in addition, paper critiques for other students' presentations will be assigned and evaluated.

Submitting an assignment

Instructions for turning in assignments will be posted when the semester starts (in ecampus).

Getting help

For questions about homework, course content, installation, and after you have tried to troubleshoot yourselves, the process to get help is: Post the question in ecampus/group chat and hopefully your peers will answer. Note that in ecampus questions are visible to everyone. For private matters send an email to helpline: udin [at] sju [dot] ac [dot] kr.

Course Policies

Collaboration policy

We encourage you to talk and discuss the assignments with your fellow students (and on ecampus), but you are not allowed to look at any other students assignment or code outside of your pair. Discussion is encouraged, copying is not allowed.

Late day policy

Homework is due before each class. Late submission are not allowed.

Communication to students

Class announcements will be through ecampus. All homework and quizzes will be posted in ecampus. Also all feedback forms. Important note: make sure you have your settings set so you can receive emails from ecampus.

Academic honesty

We give a strong emphasis to Academic Honesty. As a student your best guidelines are to be reasonable and fair. We encourage teamwork for problem sets, but you should not split the homework and you should work on all the problems together.

Presented Papers

TBD.