Casey Reas: Making Pictures with Generative Adversarial Networks

In this first non-technical introduction to emerging AI techniques, artist Casey Reas explores what it's like to make pictures with generative adversarial networks (GANs), specifically deep convolutional generative adversarial networks (DCGANs).

This text is imagined as a primer for readers interested in creative applications of AI technologies. Ideally, readers will explore the strategies of this emerging field as outlined, and remix them to suit their desires. We hope to inspire future research and collaboration, and to encourage a rigorous discussion about art in the age of machine intelligence.

Casey Reas is an artist and educator. His software, prints, and installations have been featured in numerous solo and group exhibitions at museums and galleries around the world. His work ranges from small works on paper to urban-scale installations, and he balances solo work in the studio with collaborations with architects and musicians. Reas' work is in a range of private and public collections, including the Centre Georges Pompidou, the San Francisco Museum of Modern Art, and the Whitney Museum of American Art.

Reas is a professor at the University of California, Los Angeles. He holds a master's degree in Media Arts and Sciences from the Massachusetts Institute of Technology, and a bachelor's degree from the College of Design, Architecture, Art, and Planning at the University of Cincinnati. With Ben Fry, Reas initiated Processing in 2001; Processing is an open-source programming language and environment focused on the visual arts.

Reas co-wrote and designed the book 10 PRINT CHR$(205.5+RND(1)); GOTO 10 (MIT Press, 2013). Reas and Fry published Processing: A Programming Handbook for Visual Designers and Artists, (MIT Press, 2007/2014) a comprehensive introduction to programming within the context of visual media. With Chandler McWilliams and LUST, Reas published Form+Code in Design, Art, and Architecture (Princeton Architectural Press, 2010), a non-technical introduction to the history, theory, and practice of software in the visual arts. Reas' Process Compendium 2004 - 2010 documents six years of his work exploring the phenomena of emergence through software.