“Unsupervised MoMA NFT Collection” Teaser by Refik Anadol

Refik Anadol, media artist and director in Los Angeles: “What would a machine mind dream of after ‘seeing’ the vast collection of The Museum of Modern Art? In other words, if the corpus of images of the MoMA collection had been accomplished by a single artist, what would their dreams look like?

“Emerging from Machine Hallucinations, our Studio’s multi-year research project that investigates data aesthetics based on collective visual memories of humanity, Unsupervised — Machine Hallucinations — MoMA processes 138,151 images from MoMA’s collection in the mind of a machine.

“For the works in this collection, we processed the entire digitized archive of MoMA through StyleGAN2, an algorithm developed by NVIDIA researchers with adaptive discriminator augmentation (ADA).



“We then explored a latent space with custom software called a Latent Space Browser, which we have been developing since 2017.

“We then trained a unique AI model with subsets of the collection, creating embeddings in 1024 dimensions. When idle and unsupervised, the AI re-generates the MoMA archive, constructing new aesthetic images and color combinations through unique lines drawn by algorithmic connections.

“The vast data set collected from the MoMA archive was synthesized into ethereal data pigments, and eventually into a representational form of fluid-inspired movements with the help of generative algorithms and Latent Space Browser.”
Client: MoMA

Production: Refik Anadol Studio
Director: Refik Anadol