Meta Learning
(데이터사이언스 특강: 메타러닝)

Instructor: Taesup kim

Goals

Deep Learning, and Meta Learning

Content

1. Introduction and deep learning

2. Multitask learning and transfer learning

3. Meta learning and few-shot learning

4. Optimization based meta learning

5. Model based meta learning

6. Meta reinforcement learning 1

7. Meta reinforcement learning 2

8. Project proposal

9. Online and continual learning

10.Modularization

11. Advanced meta learning 1

12. Advanced meta learning 2

13. Guest lecture

14. Project poster session

15. Project report submission and discussion

Textbook

Deep Learning (https://www.deeplearningbook.org), Dive into Deep Learning (https://d2l.ai)

Grading Policy

– Assignment: 30%
– Project: 50%
– Random Evaluation: 20%

 

Attendance Policy : Students who are absent for over 1/3 of the class 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).

Prerequisite

Probabilistic Data Analysis, Machine Learning and Deep Learning for Data Science, Python programming