Topic outline

  • All course material is maintained as a public Github repository:

    Machine Learning (ML) and deep neural networks are emerging as a general purpose computation platform for art & design, ranging from easier motion capture for film (e.g., inferring full-body movement from a single video) to intelligent game characters and algorithmic creation for visual art, music, and industrial design.

    What has been lacking is an accessible course that empowers artists and designers to utilize the techniques, e.g., to boost their innovation capabilities through mixed-initiative co-creation (AI & ML as idea/design generators), and to rapidly evaluate and test their designs using AI agents. The course Intelligent Computational Media includes advanced practical and theoretical content on the application of AI and ML techniques to various forms of media. Examples include but are not limited to algorithmic generation of video game content, computational music, sound installations, automatic testing and balancing of games, and intelligent image and 3D content editing. The course will utilise interactive visualizations / explorable explanations, and practical exercises & examples with source code, based on machine learning frameworks such as Tensorflow, PyTorch, and Unity Machine Learning Agents.

    By the end of the course, students will have practiced advanced computational methods in manipulating, analyzing, and synthesizing various forms of media, and further applying the methods to artistic or design projects. This is a project-based course, with a focus on visual explanations rather than mathematics in order to make the material accessible. References to scientific papers and other supplementary material will be provided for those who want to learn more. 

    The only prerequisites are some experience in programming (e.g., Python, Javascript, or Unity C#) and basic high-school math. No university-level mathematics is required.