The current Department of Media courses DOM-E5115 Computational Intelligence in Games (by Perttu Hämäläinen) and and DOM-E5100 Procedural Audio (by Koray Tahiroğlu) represent initial steps towards making AI and ML accessible for others than engineers – this pilot aims to unify and extend the courses in the form of a new course we tentatively call Intelligent Computational Media, aimed for whole Aalto ARTS.
The proposed course will provide advanced practical and theoretical content regarding both generativeand 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 testingand balancing of games, and intelligent image and 3D content editing. The proposed course will utilize a flipped classroom format, with online materials: interactive visualizations / explorable explanations, and practical exercises examples with source code, based on machine learning frameworks such as Tensorflow and PyTorch.
Note that we don’t consider afully automated online course feasible for the target audience, as their technical backgrounds are highly diverse and some students will require hands-on guidance. However, the online materials allow a wide audience to get an overview of the topic and to try out at least some exercises on their own.
Platforms and tools
Python, Unity, Pure Data
Flipped classroom, interactive visualizations / explorable explanations, contact teaching, practical exercises and examples with source code.
School of Arts, Design and Architecture, Department of Media, Media Lab