Step into the future during this week-long workshop that surveys the application of machine learning to new media art. We engage in a broad overview of emerging techniques for processing multimedia data toward the creation of AI-assisted generative art and interactive installation. Current technical skills and practical resources for implementation are facilitated by distributing a collection of readymade software tools. Students produce novel artworks within the specific contexts they care about during the week. Practical training is supplemented by more theoretical explanation and discussion of critical issues for introducing the field at large.
We learn how to apply classification and regression to image, sound and text data. Some techniques are real-time and interactive, such as webcam image classification and audio clustering and navigation, while others are non-real-time, including procedural algorithms for generative art. Basic computer science skills such as navigating a terminal and deploying cloud computation are also covered.
Daily activities center around tutorials about carrying out simple and advanced tasks from supervised and unsupervised machine learning interspersed with short lectures about the underlying theory. The second half of the class focuses on practice, with students applying small- and medium-sized experiments with the software, and brainstorming larger projects.
Gene Kogan is an artist who is interested in generative systems, artificial intelligence and software for creativity and self-expression. He is a collaborator within numerous open-source software projects, and leads workshops and demonstrations on topics at the intersection of code and art. Gene initiated ml4a, a free book about machine learning for artists, activists and citizen scientists. www.genekogan.com