MMI714 GENERATIVE MODELS FOR MULTIMEDIA
| Course Code: | 9090714 |
| METU Credit (Theoretical-Laboratory hours/week): | 3 (3.00 - 0.00) |
| ECTS Credit: | 8.0 |
| Department: | Multimedia Informatics |
| Language of Instruction: | English |
| Level of Study: | Graduate |
| Course Coordinator: | Assoc.Prof.Dr. ERDEM AKAGÜNDÜZ |
| Offered Semester: | Spring Semesters. |
Course Objectives
Via this course and by the successful completion thereof, the students will:
- Learn a general problem definition of generative modeling
- Learn details and use of autoregressive models
- Learn generation-related concepts, such as latent spaces, latent codes, and encoding
- Learn generative neural models.
- Learn diffusion-based generation.
- Learn various evaluation criteria for generative models
Course Content
This advanced deep learning course offers a comprehensive introduction to the principles and practice of generative modeling. Beginning with a review of the mathematical foundations required for the course, students will gain an understanding of the conventional autoregressive methods used in generative modeling, as well as more contemporary techniques such as deep generative neural models and diffusion models. The course covers all fundamental concepts related to generating media, including latent spaces, latent codes, and encoding.
Throughout the course, students will have access to a wide range of resources, including lectures, readings, and hands-on projects. In addition, a thorough review of recent state-of-the-art studies in the field will be provided each year to ensure students are up to date with the latest advances. By the end of the course, students will have gained the skills and knowledge necessary to tackle real-world generative modeling challenges and become proficient practitioners in this field.
Course Learning Outcomes
Program Outcomes Matrix
| Level of Contribution | |||||
| # | Program Outcomes | 0 | 1 | 2 | 3 |
| 1 | Having acquired in-depth knowledge in at least one of: computer graphics, audio signal processing, game physics, artificial intelligence, modelling and simulation, human-computer interaction, or computational aesthetics, | ✔ | |||
| 2 | Having acquired working knowledge on the components of computer games, virtual reality applications, simulators, and educational applications, | ✔ | |||
| 3 | Having the necessary expertise to apply theoretical concepts in addition to having practical experience, | ✔ | |||
| 4 | Having the ability to produce novel ideas and solutions, | ✔ | |||
| 5 | Having the necessary skills to carry out research and implement the results thereof in practice, | ✔ | |||
| 6 | Having the ability to work as a member of inter- and multi-disciplinary teams and take up leadership roles in such teams when necessary, | ✔ | |||
| 7 | Having excellent written and verbal skills as well as the capacity to efficiently communicate ideas, | ✔ | |||
| 8 | Having acquired the knowledge that is independent of current development tools and the ability to use this body of knowledge for learning new tools, | ✔ | |||
| 9 | Having acquired the skills for lifelong learning and ways of reaching new information when necessary, | ✔ | |||
| 10 | Having the skills to follow both theoretical and practical scientific and technological developments in the field, | ✔ | |||
| 11 | Having awareness of engineering and academic ethics, knowing and adopting the fundamental principles thereof. | ✔ | |||
0: No Contribution 1: Little Contribution 2: Partial Contribution 3: Full Contribution