Please send email to cs570.uilab@gmail.com regarding any class-related issues, instead of the professor’s email.
We will not reply to any emails about course addition. Please refer to the section “Course Addition” for detailed information.
According to the policy of South Korea government and KAIST against the COVID-19 spreading throughout the nation, we have decided to deliver a lecture online for the first two weeks. For students who have trouble due to the postponed course closing, please refer to the notice in KLMS after the semester starts.
This section is only for those who failed at registering this course on the system. If succeeded already, you can take this course no matter which department you belong to.
We will not reply to any emails about course addition.
Considering a huge demand for course addition, we decide to only approve requests from 1st or 2nd year MS/MS-PhD/PhD students at School of Computing. There will be no exceptions/changes in our policy. When applicable, you should apply for course addition in the Academic System during the course add/drop period (Link). The professor will approve every qualified request, NOT on a first come first served basis. The request from every other students will not be approved (e.g. undergraduate students, graduate students in EE and AI). We ask for your kind understanding regarding this matter.
수강 추가 기간에 많은 수요가 예상되어, 전산학부 석사/석박통합/박사 1, 2년차 학생들은 대상에 한해 증원 신청을 받을 예정입니다. 안타깝지만 해당 자격을 갖추지 않은 학생들의 경우 추가 신청을 하더라도 허가를 받을 수 없습니다.(하지만 이미 수강 신청을 완료한 학생이라면 수강하실 수 있습니다.) 만약 해당 자격을 갖춘 학생이라면 수강신청변경 기간동안 학사시스템을 통해 신청(Link)하시면 교수님께서 승인해 주실 예정입니다.(선착순 X).
Please send email to cs570.uilab@gmail.com. We will not consider any class-related email arriving in our personal accounts. When you send emails, please put “[CS570]” to the title. (e.g., [CS570] Do we have a class on MM/DD?)
| week | Day | Type | Topic | notes | Project |
|---|---|---|---|---|---|
| 1 | 03/16, 03/18 | - | Introduction, Supervised Learning | Online Lecture | |
| 2 | 03/23, 03/25 | Lecture 1 Activity 0,1 | Logistic Regression, Linear Regression | Activity 0 deadline (03/25 10:29:59 am, KST) | |
| 3 | 03/30, 04/01 | Lecture 2 Activity 2 | Naive Bayes | ||
| 4 | 04/06, 04/08 | Lecture 3 Activity 3 | GDA, Exponential Family,SVM, Kernels | ||
| 5 | 04/13, |
Project | ML project description | 04/15 Holiday | Introduction, Team matching |
| 6 | 04/20, 04/22 | Lecture 4 Activity 4 | PCA, ICA, K-means clustering | ||
| 7 | 04/27, 04/29 | Lecture 5 Activity 5 | Gaussian Mixture Model, EM | ||
| 8 | 05/04, 05/06 | - | No midterm | No Class | Proposal, Peer-review |
| 9 | 05/11, 05/13 | Lecture 6 Activity 6 | Neural networks, Deep Learning Basics | ||
| 10 | 05/18, 05/20 | Lecture 7 Activity 7 | Regularization, Feature/Model selection, Deep Learning Advanced | ||
| 11 | 05/25, 05/27 | Lecture 8 Lecture 9 | CART, Boosting, Reinforcement Learning | ||
| 12 | 06/01, 06/03 | Lecture 10 Lecture 11 | Computer Vision, NLP | Progress Update, Peer-review | |
| 13 | 06/08, 06/10 | Lecture 12 Lecture 13 | Ethics in NLP/ML, Course Wrap-Up | ||
| 14, 15 | 06/15, 06/17 06/22, 06/24 | - | Project Team Meetings with Teaching Staff | No Class | |
| 16 | 06/29, 07/01 | - | No final | No Class | Final presentation Peer-review |
Team work: 5%
Note that any team may get up to -25%p for project score if there is a serious problem with teamwork.