Research Projects:
Art & Artificial Intelligence Lab at Rutgers
I am currently collaborating with other members of the lab on projects using computational means to answer style and creativity questions about art. The mission statement of the lab: The Art and Artificial Intelligence Laboratory at Rutgers is conducting research on the intersection between the two disciplines. Our aim is to push the envelope of computer vision and artificial intelligence by investigating perceptual and cognitive tasks related to human creativity. We are focused on developing artificial intelligence and computer vision algorithms in the domain of art. Machine Learning and Art History
|
AI and the Making of Art
CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms Ahmed Elgammal, Bingchen Liu, Mohamed Elhoseiny, Marian Mazzone Original paper on ArXiv: https://arxiv.org/abs/1706.07068 My comments on AI and art making are also in my Blog on this site. Press Reactions to the Paper: Chris Baraniuk, “Artificially Intelligent Painters Invent New Styles of Art,” New Scientist, June 29, 2017 https://www.newscientist.com/article/2139184-artificially-intelligent-painters-invent-new-styles- of-art/ Michael Andor Brodeur, “Can Art be Created by Algorithms?” Boston Globe August 4, 2017 https://www.bostonglobe.com/arts/2017/08/03/can-art-created- algorithms/2MGWapvSfJVJOl8Sq1OIPO/story.html Rene Chun, “It’s Getting Hard to Tell If a Painting Was Made by a Computer or a Human,’ Artsy, September 21, 2017 https://www.artsy.net/article/artsy-editorial-hard-painting-made-computer-human Daley, Jason, “Smart News: AI Project Produces New Styles of Art,” Smithsonian.com, July 3, 2017 https://www.smithsonianmag.com/smart-news/ai-system-produces-new-styles-art-180963912/ Evans, Katy, “AI Creates Art That Critics Can’t Distinguish from Human-Created Work,” IFLScience!, June 30, 2017 http://www.iflscience.com/technology/ai-creates-rather-wonderful-art-that-fools-critics-its-not- humanmade/ Macdonald, Cheyenne, The AI Artist That Can Create its Own Painting Style (and Critics Even PREFER Some of its Work to Human Efforts), June 29, 2017 Dailymail.co.uk http://www.dailymail.co.uk/sciencetech/article-4652460/The-AI-artist-create-painting-style.html MIT Technology Review, Emerging Technology from the arXiv, “Machine Creativity Beats Some Modern Art,” June 30, 2017 https://www.technologyreview.com/s/608195/machine-creativity-beats-some-modern-art/ Claire Voon, “Humans Prefer Computer-Generated Paintings to those at Art Basel,” Hyperallergic, July 31, 2017 https://hyperallergic.com/391059/humans-prefer-computer-generated-paintings-to-those-at-art- basel/ Andy Warhol Digital Project This work culminates in an article "Andy Warhol: Computational Thinking, Computational Process." JA version for Leonardo here: https://www.mitpressjournals.org/doi/abs/10.1162/LEON_a_01574 Abstract: This article positions Warhol as a model for computational thinking (CT) and art making, linking him to concepts in new media art. Warhol’s work is analyzed for its variability in form generation and output, both in painting and on the early Amiga computer. His work becomes a simulation of the abstraction of process and methods of production familiar to us in electronic computational art of today. Rather than banal mass production on the modern assembly line, Warhol’s work can be seen as inspiration for new media arts practitioners. How the project began: Focusing on Andy Warhol's series of Flower paintings from the mid 1960s, my student researchers (Thomas Brady and Gene Johnson) explored various digital tools and analysis techniques to learn new things about this series. Part of the work is concerned with computer vision, such as formulas for detecting and finding the patterns in color selections within size groups and then throughout the entire series, and another aspect of the work is focused on pattern analysis of price differentials and exchange patterns among dealers and collectors of the works. We were fortunate to be able to present some of our preliminary work at a recent conference "American Art History and Digital Scholarship: New Avenues of Exploration", sponsored by he Smithsonian (see conference website here: http://www.aaa.si.edu/symposium/schedule2013) Thomas has since graduated, Gene Johnson came on board next to help refine some of the code, and make comparative data possible. Gene graduated last year. I keep losing my computer science students! Used some of the data from this project in a presentation at the SECAC 2015 conference in Pittsburgh, PA 'Fey Aesthetics' vs. American Mass Culture: How Andy Warhol Re-made Consumer Objects into Art." |
Click to set custom HTML