Instructor: Sungwoong Kim
TA: Donghwan Chi, Hyomin Kim
Time: Fri 12:00 - 14:45 (break time: 13:15 - 13:30)
Room: Woojung 604
Contact: swkim01@korea.ac.kr or khmiee@korea.ac.kr or LMS
This course will cover advanced algorithms and models in machine learning and deep learning to understand how cutting-edge AI models are being developed. In particular, it introduces not only theoretical contents but also practical implementation methods, including hands-on projects for actual implementation of training and evaluation codes. Furthermore, it focuses on generative modeling, which is central to recent machine learning and AI development, exploring how the algorithms and underlying technologies of different generative models are related and how they are applied to real-world data such as natural language and images.
Throughout the course, students will learn the backgrounds and key factors of advanced machine learning algorithms and models focusing on generative modeling. In particular, the course will cover a foundation modeling, neural process, generative modeling, Bayesian modeling, and current trend based on diffusion modeling and GPT-based language modeling. Eventually, the course aims students to have enough knowledge and moreover an insight and practical implementation skills for the corresponding developments and researches.
Basic knowledges in probability, machine learning, and deep learning is strictly required. Without prior knowledge or coursework in these areas, it will be difficult to keep up with this course.
Lecture notes will be the main material of the course, and these do not come from a single textbook. However, the following reference text books will be useful.
Toni Ramchandani, “A Generative Journey to AI: Mastering the foundations and frontiers of generative deep learning”, BPB Publications, 2024.
Mark Liu, "Learn Generative AI with PyTorch", MANNING, 2024.
There will be no specific assignment. The evaluation will be based on the attendance, participation, team project, midterm and final exams. With regard to the team project, every team will be required to give a presentation and submit a report including codes.
Attendance (15%)
Participation (10%)
Team Project (25%)
Midterm Exam (25%)
Final Exam (25%)