Searching for an (un)stable equilibrium: experiments in training generative models without data
This work addresses artistic creation for generative art practitioners, but it is incremental as it applies existing machine learning toolkits to a new creative context without data.
The paper explores training generative models without data, akin to traditional generative art, by experimenting with dynamical systems to produce artistic works called (un)stable equilibrium, detailing implementation and future possibilities.
This paper details a developing artistic practice around an ongoing series of works called (un)stable equilibrium. These works are the product of using modern machine toolkits to train generative models without data, an approach akin to traditional generative art where dynamical systems are explored intuitively for their latent generative possibilities. We discuss some of the guiding principles that have been learnt in the process of experimentation, present details of the implementation of the first series of works and discuss possibilities for future experimentation.