DOM-E5129 – Intelligent Computational Media

By Perttu Hämäläinen and Koray Tahiroglu

AI and deep learning soon will become general purpose computation for arts, design and game content generation, for building anything as these computational features became more accessible and modular, allowing us to interface with any new media content. They are open source, free to use.

What is 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 new MA course  Intelligent Computational Media will provide advanced practical and theoretical content regarding both generative and discriminative algorithms applied 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 and PyTorch.

Students will learn overall models of networks behind deep learning and Artificial Intelligence, start building AI with their familiar computational tools. The course will focus on computational tools  and applications with only minimal mathematical formalism.  The course will provide application code templates built as packages in Python and in TensorFlow,  interfaced more fluidly with the common computational platforms that arts, design and game students are familiar with such as, Pure Data, Unity. Students will use these templates to work on the course exercises as well as to build their artistic, design and game projects.

Students will learn the foundations of deep learning and procedural artistic and design content generation, understand how to build an AI, make a case study to determine how AI functions in arts, design and games; utilising computational tools that are self-aware, perceive their own states and the state of the surrounding environment and are able to make decisions related to content generation processes.

By the end of the course, students will know powerful ways to use advanced computational methods to manipulate data and to deploy advanced data tools for interaction ( arts, design, game) content analysis and synthesis.  Students will be skilled enough to build AI adaptable to any arts, design game environment in real life.

This is a project based course, students will be learning by doing, working on specific projects, receiving instant and customised feedback  on their work. References to scientific papers  will be provided for those who want to go deeper into the math.