https://editor.p5js.org/giav2030/sketches/KvrbzIJUi

Unsupervised (Machine Hallucinations)

Unsupervised is a machine learning project/art exhibition that created by Refik Anadol in collaboration with the Museum of Modern Art (MoMa).

Refik Anadol Studio’s multi-year research project that investigates data aesthetics based on collective visual memories of humanity

What type of machine learning models did the creator use?

He used StyleGAN2, an algorithm developed by NVIDIA researchers with adaptive discriminator augmentation (ADA).

What data might have been used to train the machine learning model?

He used about 200 years of human art. He used 138,151 images from MoMA’s collection in the mind of a machine. For the works in this collection, Anadol processed the entire digitized archive of MoMA (Anadol’s Website).

Why did the creator of the project choose to use this machine learning model?

GANs have captured the world’s imagination. Their ability to dream up realistic images of landscapes, cars, cats, people, and even video games, represents a significant step in artificial intelligence.

He used a GAN (Generative Adversarial Network) model because of it’s ability to generate/imagine/hallucinate new images by recognizing patterns from a dataset.