Collaborative Artistic Production with Generative Adversarial Networks
The social and cultural significance of machine learning is often defined by polarised perspectives. Machine-learning might be seen as opening exciting new pathways for creativity, or as a fundamental threat to the role of the artist. The development of Generative Adversarial Networks (GANs) as a classification and production mechanism represents a new opportunity for artists and humanities scholars to re-examine fundamental aspects of creativity. Recent publications in 3D mesh-generating GANs suggest that such systems might have profound impacts for sculpture and design practice. These impacts might challenge basic principles of form, function and aesthetics, and the creative use of such technologies might result in new and novel forms of data encryption. Given the rapid acceleration in the capacity and variety of these systems, it is critical that humanities scholars engage from both practical and theoretical level. We use a four-stage structure, where each stage is directed by one team member relative to their specialisation, and each stage builds upon knowledge gained in the previous stage. We work in close collaboration with an external consultant and two research assistants from the fields of computer science and anthropology/humanities to develop new creative tools and new datasets with research and cultural heritage value. Our project engages three technical challenges - developing a GAN system that can convert works of literature into 3D models of trees, developing a GAN system that can improvise 3D models of non-existent human hand tools, and developing a GAN system for collaborative musical performance. Each of these three technical elements will be combined into a single multimedia performance and presentation as well as a series of peer-reviewed journal publications. The reflective ethnographic part of the project makes use of the research team’s privileged access to and involvement in the development and implementation of the machine-learning system to offer an analysis of GAN and machine learning from a cultural perspective.
Students will need the computer science literacy required to collaborate on the implementation of our GAN systems for generating 3D mesh objects and music, as well as help develop English language academic publications.
Co - Principal Investigators