2025년도 2학기 특강: 딥러닝 구현 (CSED490F-01) 강의계획서

1. 수업정보

학수번호 CSED490F 분반 01 학점 3.00
이수구분 전공선택 강좌유형 강의실 강좌 선수과목
포스테키안 핵심역량
강의시간 월, 수 / 11:00 ~ 11:50 / 제2공학관 강의실 [107호] | 수 / 17:00 ~ 18:40 / 제2공학관 강의실 [107호] 성적취득 구분 G

2. 강의교수 정보

박은혁 이름 박은혁 학과(전공) 인공지능대학원
이메일 주소 hyek90@postech.ac.kr Homepage
연구실 공학 2동 323호 전화 054-279-2247
Office Hours

3. 강의목표

This course covers deep learning from both theoretical and practical perspectives. Students will build neural networks, convolutional networks, recurrent networks, and transformers from scratch while learning about optimization algorithms, regularization techniques, and model acceleration strategies.
• The primary goal is to enable students to:
1. Understand and explain key deep learning concepts and architectures.
2. Implement deep learning models
3. Optimize model performance for efficient training and inference.
4. Apply learned skills to real-world projects and research settings.

4. 강의선수/수강필수사항

Artificial Intelligence / Computer Architecture

5. 성적평가

• Assignments: 30%
• Midterm Exam: 20%
• Final Exam: 20%
• Final Project: 30%

6. 강의교재

도서명 저자명 출판사 출판년도 ISBN
Selected research papers and lecture notes 0000

7. 참고문헌 및 자료

Deep Learning, Ian Goodfellow, Yoshua Bengio, Aaron Courville, MIT Press, 2016, ISBN: 978-0262035613
Dive into Deep Learning, Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola (online free textbook)

8. 강의진도계획

1. Introduction & Neural Network Basics / Matrix Multiplication
2. Convolution Neural Networks / High-rank Tensor Operations
3. Forward & Backward Propagation / Differentiable Operation & Operator Graph Building
4. Automatic Differentiation & Optimization / PyTorch Basics & Build Training Pipeline
5. ML Frameworks / Distributed Data Parallel with NVIDIA DALI
6. Computing System for DNNs / Profiling & Performance Analysis
7. Computing System for DNNs & Compilation / Design Custom Operator on PyTorch
8. Midterm exam
9. CUDA & Triton Language / Accelerating Custom Operators
10. Transformer and Large Language Models / LLM Frameworks -1
11. Computing System for LLMs / LLM Frameworks -2
12. Advanced Generative Models & Multimodal Models / Fine-tuning with LoRA
13. Distributed Training / Final Project -1
14. Model Optimization / Final Project -2
15. Reserved / Final Project -3
16. Final exam / Project Demonstration

9. 수업운영

Lecture, Hands-on Implementation, and Team Projects

10. 학습법 소개 및 기타사항

Active participation in lectures and coding sessions is crucial.
Students are encouraged to explore advanced topics for their final projects.
S/U policy will not be allowed

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