Recent Advances in Deep Learning (AI602, Spring 2022)

Deep learning is a new area of machine learning research, which have demonstrated states-of-the-art performance on many artificial intelligence tasks, e.g., computer vision, speech recognition and natural language processing. In this lecture, I will cover some of recent advances in this area.

Announcement

• The maximum number of course registrations is around 80, and we cannot accept more now (do not send an email to Instructor or TA).

• Paper presentation schedule is released.

• You should attend at least 18 classes out of 26 classes (from 3/7).

Schedule

• Lecture 0: Introduction to AI602

• Lecture 1: Advanced optimizers for neural networks

• Lecture 2: Advanced deep spatial models (e.g., for image recognition)

• Lecture 3: Advanced deep temporal models (e.g., for language modeling)

• Lecture 4: Advanced deep spatial-temporal models (e.g., for video recognition)

• Lecture 5: Advanced deep generative models I: Implicit density models

• Lecture 6: Advanced deep generative models II: Explicit density models

• Lecture 7: Self-supervised learning

• Lecture 8: Neural fields

• Lecture 9: Transfer and continual learning

• Lecture 10: Meta learning

• Lecture 11: Robustness

• Lecture 12: Fairness and bias in AI

Contact

Instructor: Jinwoo Shin (jinwoos@kaist.ac.kr)
TA: Junsu Kim (junsu.kim@kaist.ac.kr), Seong Hyeon Park (seonghyp@kaist.ac.kr), Seojin Kim (osikjs@kaist.ac.kr) and Minkyu Kim (kimmk135@kaist.ac.kr)