Data Engineering
Spring 2023
- Code: AI5308 / AI4005
-  Schedule: Tue/Thu 1:00pm-2:30pm
 
- Location: GIST College Building A, Room 227 (N4)
- Instructor: Sundong Kim
- TAs: Sanha Hwang, Sungkyu Yang, Hongyiel Suh
- Discord Channel (Discussion and Q&A, Team Collaboration)
- Contact: Students are encouraged to ask all course-related questions on Discord, where you can also find announcements.
- Class Overview, Logistics and Grading: See this page
- Final Project: See this page
Textbook & References
- Books - PDF available at LMS and GIST library, Courtesy by O’Reilly
- Reference
Notice
-  You can find a detailed description of the project, its challenges, solutions, and overall journey at the following link: [Project outcomes]. 
-  Second quiz will be on Jun 1, which covers all class material including invited talks. 
-  Project page is updated (May 19) — Mid review III and final preparation, demo day schedule! 
-  Project page is updated (May 11) — Demo day and final report announcement! 
-  Project page is updated (May 2) — Mid review II announcement! 
-  Homework released (March 27) - Write your first critique and submit here. 
-  Homework released (March 17) - Make your webpage & CV and submit here. 
-  I invited several speakers to GIST AI colloquium regarding to our course. Check this page and attend them. 
Schedule
Herebelow, you can find the schedule of the course.
| Date | Description | Readings | Homeworks | 
|---|---|---|---|
| Feb 28 | Introduction | Sign-up form | |
| Mar 2 | Overview of Machine Learning Systems | DMLS Ch.1 | |
| Mar 7 | Introduction to Machine Learning Systems Design | DMLS Ch.2, Slides | |
| Mar 9 | Class Logistics, Homework Releases | Slides | |
| Mar 14 | Project Announcement | Slides | Final project | 
| Mar 16 | Introduction to Machine Learning Systems Design | DMLS Ch.2, Slides | HW - Webpage (Mar 17) | 
| Mar 21 | Data Engineering 101 | DMLS Ch.3, Slides | Team formation (Mar 20) | 
| Mar 23 | Data Engineering 101, Training data | DMLS Ch.3-4, Slides | |
| Mar 28 | Training data | DMLS Ch.4, Slides | HW - Critique 1 (Mar 27) | 
| Mar 30 | Critique 1 discussion | Slides | Invited talk (Wonyoung Shin) | 
| Apr 4 | Pop Quiz | Slides | |
| Apr 6 | Data Imbalance and Data Augmentation | DMLS Ch.4, Slides | Invited talk (Byeongjo Kim and Shengzhe Li) | 
| Apr 11 | Feature Engineering | DMLS Ch.5, Slides | |
| Apr 13 | Feature Engineering | DMLS Ch.5, Slides | |
| Apr 18 | No Lecture (Midterm Period) | ||
| Apr 20 | No Lecture (Midterm Period) | ||
| Apr 25 | Feature Engineering | DMLS Ch.5, Slides | HW - Critique 2 (Apr 24) | 
| Apr 27 | Model development and offline evaluation | DMLS Ch.6, Slides | |
| May 2 | Project Review (Presentation) | ||
| May 4 | Project Comments | DMLS Ch.7, Slides | |
| May 9 | Brainstorming the Demo Day | ||
| May 11 | Demo day and Report Announcement | Project page | |
| May 16 | Study W&B and MLFlow | Invited talk (Junbum Lee - KoAlpaca) | |
| May 18 | Project Review (Discussion) | Invited talk (Sungwon Han - Responsible AI, 4pm) | |
| May 23 | Critique 3 discussion + Human Side of ML | DMLS Ch.11 | HW - Critique 3 (May 22) | 
| May 25 | Continual Learning | DMLS Ch.8-9, Slides | Invited talk (Youngsub Lim - MLOps in MakinaRocks, 4pm) | 
| May 30 | Project Review (Play demos) | ||
| Jun 1 | Quiz | ||
| Jun 6 | No Lecture (National Holiday) | ||
| Jun 8 | Project review (Demo Setup & Draft Report Critique, AI Building 1F) | ||
| Jun 13 | Demo day (AI Building 1F, from 12:00pm) | Message | Photos | 
| Jun 15 | No Lecture (Finals week) | Reference | HW - Team report (due: Jun 16) | 
