Machine Learning | Sundong Kim

Time: Tue/Thu 10:00am-12:00pm (Spring 2026)
Venue: GIST College Building C (N6), Room 104
Codes: AI5100 / EC4224 / AI4100 / EC5402
Size: 53 (18 undergraduates, 35 graduates)

Notice

The first class will be on March 3, 10:00am.

Useful Links

Access the AI5100/EC4224 Ed Discussion forum.
If you haven’t already been added to the Ed discussion, use this invitation link.
- Use your full name in the format “Firstname Lastname” with the first letter of each name capitalized (e.g., Sundong Kim).
- Don’t forget to use your valid email address (gm.gist.ac.kr).
Submit your assignments at the AI5100/EC4224 Gradescope (Entry Code: J4G3BR). Make sure to enter your correct student ID.
- Use the same name format as for Ed Discussion: “Firstname Lastname” with the first letter of each name capitalized.
- Make sure to enter your correct student ID.

Textbooks

Syllabus

This course will utilize presentation slides by the textbook authors.

(Tentative schedule - NOT FIXED YET)

Date	Description	Readings	Homeworks
3/3	Introduction	ISLP Ch.1
3/5	Statistical Learning	ISLP Ch.2, (ESL 2.5)
3/10	Linear Regression	ISLP Ch.3
3/12	Linear Regression
3/17	Classification (Discriminative)	ISLP Ch.4
3/19	Classification (Generative)		HW1 (Due: 3/22)
3/24	Resampling Methods	ISLP Ch.5
3/26	Hands-on session (TBD)
3/31	Tree-Based Methods	ISLP Ch.8
4/2	Tree-Based Methods
4/7	Support Vector Machines	ISLP Ch.9
4/9	Moving Beyond Linearity	ISLP Ch.7	HW2 (Due: 4/12)
4/14	Linear Model Selection and Regularization	ISLP Ch.6
4/16	Linear Model Selection and Regularization
4/21	No class (Exam week)
4/23	Midterm Exam
🏁 🏁
4/28	Deep Learning	ISLP Ch.10
4/30	Deep Learning
5/5	Children’s day		HW3 (Due: TBD)
5/7	Survival Analysis and Censored Data	ISLP Ch.11
5/12	Survival Analysis and Censored Data
5/14	Unsupervised Learning	ISLP Ch.12
5/19	Unsupervised Learning
5/21	Multiple Testing	ISLP Ch.13
5/26	Multiple Testing		HW4 (Due: TBD)
5/28	Project / Advanced Topic on ML
6/2	Project / Advanced Topic on ML
6/4	Project / Advanced Topic on ML
6/9	Project / Advanced Topic on ML
6/11	Project / Advanced Topic on ML		HW5 (Due: TBD)
6/16	No class (Exam week)
6/18	Final Exam
🏁 🏁

Staffs

Communication: The course schedule and all resources (e.g. lecture slides) will be posted on this course website. All class discussions, announcements and communication will take place via Ed Discussion. Students are strongly encouraged to post their questions as public posts so that everyone in the class can benefit from the discussion. Only in cases of truly personal matters should private posts be used. Course-related emails will not be checked, so please do not send emails to the instructors or TAs. All questions and communications should be made through Ed, and we aim to respond within two business days, often sooner. In addition, you are welcome to visit the TAs during office hours.

Sundong Kim

Instructor

QnA: Available after class (Lecture room)
Office: AI Building (S7), Room 204

Seojin Hwang

Mon 4:00-5:30pm
Office: AI Building (S7), Room 206

Hyunseok Ryu

Fri 2:00-3:00pm
Office: AI Building (S7), Room 107

Jungeun Choi

Wed 4:00-5:00pm
Office: MSE Building (S5), Room 409

Hyun Park

Tue 4:00-5:00pm
Office: College B Building (N5), Room 217

Gradings

You will earn A if (but not only if) your score is at least \(80\times(1-ε_1)\), B if your score is at least \(60\times(1-ε_2)\), C if your score is at least \(40\times(1-ε_3)\), for some \(ε_i ≥ 0\) to be determined later. All participants in the course (Undergraduate and graduate students) are evaluated equally, regardless of the course codes.

Homeworks (50%)
Midterm (25%)
Final Exam (25%)
Some bonus points for active participants

Homeworks

Submit your assignments at the AI5100/EC4224 Gradescope. Homework will be released at least two weeks before the deadline.

HW 1 is due Sunday, Mar 22 at 11:59PM [TeX]
HW 2 is due TBD
HW 3 is due TBD
HW 4 is due TBD
HW 5 is due TBD

Homeworks take 50% of your grades. Here are the tentative plans:

Two homeworks (5% each) will be problem-solving assignments similar in style to the exams. HW1 is one of them. Grading will be based simply on submission completion.
One homework (15% of your grade) will ask you to record a 15–20 minute YouTube video teaching key concepts from the book. You should select one topic, explain the material in your own words, and solve the associated problem as if you’re the instructor.
Two homeworks (25% of your grade combined) will be Kaggle-style data challenges (topic: TBD).
The order of these assignments has not been finalized yet.

Late policy for homeworks: If assignments are late, they are increasingly penalized as follows: within 24 hours, you lose 10%; within 48 hours, you lose 20%; within 72 hours, you lose 40%. More than three days late, you can no longer hand-in the assignment.

Grading will be completed within two weeks after the deadline, and students will then have five days to request a regrading on Gradescope.

Exams

There will be two closed-book exams. You are allowed to bring one handwritten A4 crib sheet (both sides), printed sheets or those created by iPad are not allowed. Submit your crib sheet with your exam sheet for bonus points. For the exams, you may only bring: your student ID, pen, pencil, eraser, and your handwritten crib sheet. No other materials are allowed.(e.g., mobile phone, iPad, laptop, calculator, smart watch, books).

The midterm will take place on TBD (est. Thursday, Apr 23, 09:00am) (Venue: Our lecture hall, 120 minutes)
The final exam will take place on TBD (est. Thursday, Jun 18, 09:00am) (Venue: Our lecture hall, 120 minutes)

Exams will cover material from lecture, homework, book, and equivalent. (Coverage will be announced later)

For midterm, ISLP Ch.1-9 and relevant materials will be covered. (Could be changed)
For finals, ISLP Ch.10-13, and relevant materials will be covered. (Could be changed)

Exam Conflicts and Makeups: Exam makeups will only be scheduled for approved conflicts. If you have a conflict with any of the exams, let us know as soon as possible. Examples include:

Acceptable reasons: Presenting at a major academic conference, family emergencies (e.g., illness or passing of a close relative), or other serious unforeseen circumstances.
Unacceptable reasons: Having a heavy exam schedule on the same day.

Collaboration Policy & Honor Code

Study groups are allowed. It is also OK to get clarification (but not solutions) from books, online resources, or AI tools such as ChatGPT and Claude, after you have thought about the problems on your own. However, we expect students to understand and complete their own assignments. Each student must write down the solution independently and hand in one assignment per student — this means you write your solution after closing the book and all your notes, without help from your colleagues or AI assistants.

If you studied together as a group, please cite your collaborators fully and completely in your assignment. Likewise, if you used an AI tool for clarification, please disclose this.

If elements of two or more assignments are determined to be clearly very similar, whether through copying from each other or from reproducing AI-generated output verbatim, all students involved will face the following consequences:

First offense: Course grade reduced by one letter grade, and a score of 0 on the assignment.
Second offense: Course grade of F.

This applies to all parties involved, including both those who provided and those who received the work. Cheating on exams will lead to severe consequences ranging from an F in the course to suspension from the University.