Refik Anadol: Unsupervised - CODAworx

Refik Anadol: Unsupervised

Client: The Museum of Modern Art, New York

Location: New York , NY, United States

Completion date: 2022

Project Team

Refik Anadol Studio

Refik Anadol Studio

The Museum of Modern Art, NY



What would a machine mind dream of after “seeing” the vast collection of The MoMA? Unsupervised uses artificial intelligence to answer this question by interpreting and transforming more than 200 years of art at MoMA. For this meditation on technology, creativity, and modern art, Refik Anadol Studio trained a sophisticated machine-learning model to interpret the publicly available data of MoMA’s collection. As the model “walks” through its conception of this vast range of works, it reimagines the history of modern art and what might be to come.

For Unsupervised, Anadol synthesized the vast data collected from the MoMA’s publicly available metadata archive into ethereal data pigments, and eventually into a representational form of fluid-inspired movements, with the help of generative algorithms and a custom software called Latent Space Browser, which the studio has been developing since 2017. Thus, the Studio’s signature fluid dynamics algorithm infinitely dreams about the MoMA archive.


AI is often used to classify, process, and generate realistic representations of the world. In contrast, Unsupervised is visionary: it explores fantasy, hallucination, and irrationality, creating an alternate understanding of art-making itself. Unsupervised not only pulls the viewer into a strange world of collective art histories as imagined by a dreaming machine, but also provides a moment of meditation on new modes of perception and sensation. As it unfolds, you can see it speculating about, for instance: How to create an abstract picture. How to render volume and depth in new ways. How to deal with inventing new colors. And even the question, Why?—because these are the problems that artists confronted in the past two centuries. The AI Data Painting also incorporates site-specific input from the environment of the Museum’s Gund Lobby—changes in light, movement, acoustics, and the weather outside—to affect the continuously shifting imagery and sound.


Organized by Michelle Kuo, The Marlene Hess Curator of Painting and Sculpture, and Paola Antonelli, Senior Curator of Architecture and Design and Director of Research and Development, with Lydia Mullin, Curatorial Assistant, Department of Painting and Sculpture.

With thanks to Refik Anadol Studio (Alex Morozov, Carrie He, Christian Burke, Daniel Seungmin Lee, Dave Hunt, Efsun Erkılıç, Imaginary Friends, Kerim Karaoglu, Linda Berke, Mert Cobanov, Pelin Kivrak, Ho Man Leung, Kyle McLean, Nidhi Parsana, Raman K. Mustafa, Rishabh Chakrabarty, Simon Burke, Toby Heinemann, Yufan Xie), Casey Reas, Sean Moss-Pultz, and Michael Nguyễn.

Additional Information

Casey Reas, American artist and Professor of Media Arts, described the innovative impact of the project in the following statement: "Let’s imagine we’re in Paris, it’s sometime in the early 20th century. And there are a few dozen artists who are making work and they’re all looking at each other’s work. And they’re all influenced by each other. And then, of course, there were a lot of things that were possible, but that were never made. And so what I find really interesting about Refik’s project with MoMA’s dataset, with your collection, is that it speculates about possible images that could have been made, but that were never made before."