2023년도 2학기 인공지능 특론: 신뢰할 수 있는 기계학습 (CSED703L-01) 강의계획서

1. 수업정보

학수번호 CSED703L 분반 01 학점 3.00
이수구분 전공선택 강좌유형 강의실 강좌 선수과목
포스테키안 핵심역량
강의시간 화, 목 / 14:00 ~ 15:15 / 제2공학관 강의실 [107호] 성적취득 구분 G

2. 강의교수 정보

박상돈 이름 박상돈 학과(전공) 인공지능대학원
이메일 주소 sangdon@postech.ac.kr Homepage https://sangdon.github.io/
연구실 HTTPS://ML.POSTECH.AC.KR/ 전화 054-279-2396
Office Hours

3. 강의목표

As machine learning and deep learning models are impacting on real world environments (e.g., ChatGPT), concerns on the trustworthiness of machine-learned models are rising. In this course, we explore whether popular machine-learned models are trustworthy and then study various learning methods to enchant the models to be trustworthy. To this end, we will learn basic knowledge on machine learning theory, uncertainty learning via conformal prediction, adversarial examples/learning, machine unlearning, differentially private learning, fairness in learning, and miscellaneous topics on trustworthy generative AI.

4. 강의선수/수강필수사항

- 선수과목: 확률및통계
- 필수과목: 기계학습

5. 성적평가

Discussion: 50%
Final presentation: 50%

6. 강의교재

도서명 저자명 출판사 출판년도 ISBN

7. 참고문헌 및 자료

- Learning theory: Foundation of Machine Learning (https://cs.nyu.edu/~mohri/mlbook/)
- Conformal prediction: A Tutorial on Conformal Prediction (https://arxiv.org/pdf/0706.3188.pdf)
- Differential Privacy: The Algorithmic Foundations of Differential Privacy (https://www.cis.upenn.edu/~aaroth/Papers/privacybook.pdf)
- Fairness: FAIRNESS AND MACHINE LEARNING (https://fairmlbook.org/pdf/fairmlbook.pdf)

8. 강의진도계획

Tentative Schedule
[Week 1-3] Preliminaries on machine learning theory
- Introduction
- Concentration inequalities
- Probably approximately correct (PAC) learning under finite hypotheses and realizable case
- Learning under infinite hypotheses and unrealizable case
- Statistical query (SQ)
- Online learning
[Week 4-5] Uncertainty Learning: Conformal Prediction
- Introduction
- Conformal prediction
- PAC conformal prediction and its applications
- Adaptive conformal prediction and its applications
[Week 6-7] Adversarial Example and Learning
- Introduction
- Adversarial example generation
- Heuristic adversarial learning
- Certified adversarial learning
[Week 8] Machine unlearning
- Introduction
- SQ review
- Unlearning with SQ
[Week 9-10] Differentially private learning
- Introduction
- differential privacy (DP)
- DP in SQ
- Applications of DP in large language models (LLMs)
[Week 11-12] Fairness in learning
- Introduction
- Fairness definitions
- Fairness in practice
[Week 13-14] Miscellaneous topics on trustworthy generative AI
- Vulnerabilities in generated code
- Prompt tuning
- Copyright issue
[Week 15-16] Final presentation

9. 수업운영

10. 학습법 소개 및 기타사항

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