Grading

Quiz (30%)


  • Quizzes are regularly administered at the start of each class, with intervals of one to three weeksbased on class progress and project sessions.
  • Attendance is crucial, as missing over one-third of the quizzes without a valid excuse may fail.
  • The final score is calculated by averaging the scores of all quizzes taken, excluding the lowestand highest scores.
  • Quizzes may be considered in place of the attendance score.

    		•

    Project (proposal 30% + final 40% = 70%)


  • Develop a new research idea for multimodal deep learning.
  • Each team consists of two to three collaborators to prepare two (proposal and final) presentations.
  • Presentation must include the following contents: problem statement, data collection or preparation, model architecture, and theoretical and experimental analysis.
  • Rubrics for the assessments are as follows (link). Please refer to the document to prepare your project.
  • Recording is only permitted for conference or workshop presenters.

    		•

    Students absent for over 1/3 of the quiz will receive a grade of 'F' or 'U' for the course.
    (Exceptions can be made when the cause of absence is deemed unavoidable by the course instructor.)

    Textbooks


    There is no official textbook.

    FAQ

    Can I audit the course?

    Please talk to the course instructors in person during the first week of class.


    The course seems to require proficienty in the Korean language to listen to talks, but my Korean isn't quite good. Maybe I shouldn't take it?

    Please note that while the class content is primarily in English, the instruction will be in Korean. If this presents an issue, we suggest considering other class options. We apologize for any inconvenience.