Description

Generative AI has revolutionized how we create and manipulate visual data, enabling machines to generate images, videos, and 3D models that are increasingly indistinguishable from reality. This course delves into the cutting-edge techniques and models that drive generative AI in the visual domain, such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and diffusion models. Students will explore the core mathematical and computational concepts behind generative AI, including deep learning and probability theory. The course also emphasizes practical implementation, allowing students to build generative models that can synthesize images, enhance existing visual content, and even create novel, realistic objects. By the end of the course, students will not only have a deep understanding of how generative models are designed and trained but will also critically assess their applications and limitations in various fields.Students are expected to have a good mathematical foundation and programing skills. Foundational Mathematical Courses (i.e., CS103 or CS105) will be an advantage but are not insisted on. The primary programming language of the course is python. Having a good GPU at home will help with course work.

Learning Outcomes

Graduate Learning Outcomes

Disciplinary Knowledge, Multidisciplinary Knowledge, Critical thinking & problem solving, Self-directed learning

Competencies

Computational Modelling, Computer Vision Technology, Pattern Recognition Systems, Research, Software Testing