AIC3100:
Intro to Deep Learning and Applications

Course Information

Instructor: Seong Jae Hwang (seongjae@yonsei.ac.kr)

Instructor Office: 공학원 439b

Lecture Upload Date: Wednesday

TA: 

• Donghyun Kim / 김동현 

• Changyoung Kim / 김찬영 

• Gayoon Choi / 최가윤

• Seil Kang / 강세일

• Youngjun Jun / 전영준

• Taejin Jeong / 정태진

• Woojung Han / 한우정

Online TA Office Hours: TBA

Course Description

This course introduces the fundamentals of deep learning and discusses relevant applications. This introductory course is for those with little to no background in artificial intelligence or deep learning. Thus, the course covers the very basics of varying topics including linear algebra, artificial intelligence, machine learning, computer vision, and deep learning, mostly at a high level to introduce the audience to this field. Some recent trends in deep learning will be covered in the latter part of the course.

Pre-requisites

Linear algebra is useful but not necessary

Programming languages (tentative)

Python. Coding assignments in Jupyter Notebook file (.ipynb) in an open-source IDE Jupyter Notebook or Jupyter Lab. Other IDEs are also allowed as long as you can use .ipynb.

Useful but not necessary textbooks

Deep Learning: Ian Goodfellow, Yoshua Bengio, Aaron Courvile

Each week on learnus, you will see:

• Slides

• Lectures

Exams

• Midterm and Final Exams 

• NOT in person

• Details to be updated

Discussion Board [NEW THIS YEAR]: 

LearnUs anonymous Q&A.

• Search for similar questions. You may find the answers you need in other Q&A.

• Freely ask questions anonymously and publicly to help you and others.

• Freely answer questions anonymously.

• Instructor and TAs will try their best to respond within 48 hours.

Course Policies

Grading for AIC3100.01-00 (tentative)

• Attendance (5%)

• Quizzes / Hands-on Assignments (15%)

• Midterm (40%)

• Final (40%)

Grading for AIC3100.GD-00 (tentative)

• Attendance (30%)

• Quizzes / Hands-on Assignments (10%)

• Midterm (30%)

• Final (30%)

Attendance

• Online-attendance (i.e., play the lecture videos).

  1. We use LearnUs' auto attendance system. This is done by simply watching the video.

  2. Notes: You may face unexpected errors such as not correctly tracking your view. Therefore, we HIGHLY encourage you to

     1. double check whether your session has been correctly counted towards the attendance

     2. finish the session under stable internet connection

  3. LearnUs keeps very detailed logs (e.g., when you log in, start video, click on links, etc.), so it 

• You have 1 week to watch the lecture video (must complete >90%)

• -0.5 for each absence

Collaboration Policy and Academic Honesty

• You will do your work (exams and homework) individually. 

• The work you turn in must be your own work. 

• You are allowed to discuss the assignments with your classmates, but do not look at the code they might have written for the assignments, or at their written answers. 

• You are not allowed to search for code on the internet, use solutions posted online unless you are explicitly allowed to look at those, or to use Python's implementation if you are asked to write your own code. 

• When in doubt about what you can or cannot use, ask the instructor!

• Posting and asking HW questions online (e.g., Stack Overflow) is NOT allowed. This will be considered as cheating.

• A first offense will cause you to get 0% credit on the assignment. A report will be filed with the school. 

• A second offense will cause you to fail the class and receive a disciplinary penalty. 

Note on Disabilities

If you have a disability for which you are or may be requesting accommodation, you are encouraged to contact your instructor ASAP.