3. 강의목표
This is an introductory course on deep learning. This course is designed for any graduate-level students with some background in Calculus, Linear Algebra and Probability. The topics include, but not limited to, machine learning, deep neural network, regularization, optimization, graph learning and generative models. The students who successfully finish this course will gain knowledge on representation learning via deep learning.
4. 강의선수/수강필수사항
Calculus, Linear Algebra, Probability
5. 성적평가
Quiz: 30%
Assignments: 15%
Final Project: 50%
Class participation: 5%
*The criteria above is subject to change.
6. 강의교재
도서명 |
저자명 |
출판사 |
출판년도 |
ISBN |
Deep Learning
|
Ian Goodfellow
|
The MIT Press
|
0000
|
|
7. 참고문헌 및 자료
https://www.deeplearningbook.org/
8. 강의진도계획
Week 1. Course logistics / Introduction
Week 2. Linear Algebra
Week 3. Probability Theory
Week 4. Numerical Computation
Week 5. ML basics
Week 6. Artificial Neural Network (ANN)
Week 7. Regularization
Week 8. Optimization
Week 9. Mid-term exam week (no class)
Week 10. Recurrent Neural Network (RNN)
Week 11. Convolution Neural Network (CNN)
Week 12. Graph Neural Network (GNN)
Week 13. Transformer / Autoencoder
Week 14. Generative models
Week 15. Representation learning
Week 16. Final presentation
9. 수업운영
- The course will be taught offline, face-to-face.
- Grading will be based on 1) three quiz, 2) a few assignments (mostly reading) and 3) final project and presentation (in groups)
11. 장애학생에 대한 학습지원 사항
- 수강 관련: 문자 통역(청각), 교과목 보조(발달), 노트필기(전 유형) 등
- 시험 관련: 시험시간 연장(필요시 전 유형), 시험지 확대 복사(시각) 등
- 기타 추가 요청사항 발생 시 장애학생지원센터(279-2434)로 요청