Terence Broad

(un)stable equilibrium featured image

(un)stable equilibrium (2019) is an ongoing series of works where generative neural networks are trained without any data. This practice is akin to traditional generative art, where dynamic systems are built and the role of the artist is to influence the process through aesthetic exploration. In this practice, modern machine learning toolkits and generative architectures are explored intuitively for their latent generative possibilities.For the works in Series 1, two generator networks are trained to have their outputs recognised as the output of the other’s, while both competing to produce more colours than the other network. The networks quickly converge into producing these abstract compositions.