Unsupervised is part of Machine Hallucinations, Refik Anadol Studio’s ongoing project exploring data aesthetics based on collective visual memories. The exhibition processes 138,151 pieces of metadata from the vast collection of The Museum of Modern Art in the mind of a machine. Using StyleGAN2 ADA to capture the machine’s transformative “hallucinations” of modern art in a multi-dimensional space, Anadol trains a unique AI model with subsets of the archive of MoMA’s collection of artworks, creating embeddings in 1024 dimensions. The sorted image datasets are then clustered into thematic categories to better understand the semantic context of data. This expanding data universe not only represents the interpolation of data as synthesis, but also becomes a latent cosmos in which hallucinatory potential arises from a novel form of artistic creativity interpreting MoMA’s unparalleled collection of modern and contemporary art. —Refik Anadol

Feral File — Unsupervised

“Unsupervised — Data Universe — MoMA” is a global AI data painting that simulates a latent walk among the museum’s digitized collection. The artist and his team used MoMA archives to construct the seven dimensions of the artwork: x, y, z, r, g, b, and time. It combines Anadol’s vision of handling data within a universe that it creates for itself with his approach to data visualization’s latent space as a locus for never-ending, self-generating contemplation. Researcher Leland McInnes, the inventor of the UMAP technique that Anadol has used for “Unsupervised — Data Universe — MoMA” wrote, “I have always found beauty in mathematics, but to see what Refik has done with mathematics and these algorithms to create art is something else again: bringing together rich threads of information and data to weave amazing visual works. I never imagined that my work in mathematics could have such far reaching impacts.”

Unsupervised — Data Universe — MoMA #947

What is the value?

Details