(un)stable equilibrium 1:1, (2019)
This piece is part of a series of works training generative adversarial networks without any data. In this current configuration, two generator networks are trying to generate images that imitate each other while not being imitated by the other network. At the same time, they are also competing to have more variation in the colours they produce. In this arrangement, the networks quickly converge into creating these abstract composition.
This piece was selected as the winning submission of all the artworks at the 2019 ICCV Computer Vision Art Gallery