An artist just starting out might first imitate the styles of others, and if all goes well, the process of learning those styles will lead them to a style of their own. But how does one learn something like an artistic style in a way that isn't simply imitative? Artificial intelligence, and especially the current developments in making computers not just think but learn, will certainly shed some light in the process — and produce, along the way, such fascinating projects as the video above, a re-envisioning of Disney's Alice in Wonderland in the styles of famous artists: Pablo Picasso, Georgia O'Keeffe, Katsushika Hokusai, Frida Kahlo, Vincent van Gogh and others.
The idea behind this technological process, known as "style transfer," is "to take two images, say, a photo of a person and a painting, and use these to create a third image that combines the content of the former with the style of the later," says an explanatory post at the Paperspace Blog.
"The central problem of style transfer revolves around our ability to come up with a clear way of computing the 'content' of an image as distinct from computing the 'style' of an image. Before deep learning arrived at the scene, researchers had been handcrafting methods to extract the content and texture of images, merge them and see if the results were interesting or garbage."
Deep learning, the family of methods that enable computers to teach themselves, involves providing an artificial intelligence system called a "neural network" with huge amounts of data and letting it draw inferences. In experiments like these, the systems take in visual data and make inferences about how one set of data, like the content of frames of Alice in Wonderland, might look when rendered in the colors and contours of another, such as some of the most famous paintings in all of art history. (Others have tried it, as we've previously featured, with 2001: A Space Odyssey and Blade Runner.) If the technology at work here piques your curiosity, have a look at Google's free online course on deep learning or this new set of courses from Coursera— it probably won't improve your art skills, but it will certainly increase your understanding of a development that will play an ever larger role in the culture and economy ahead.
Here's a full list of painters used in the neural networked version of Alice:
Vincent van Gogh
Saloua Raouda Choucair
Elaine de Kooning
Based in Seoul, Colin Marshall writes and broadcasts on cities and culture. He’s at work on the book The Stateless City: a Walk through 21st-Century Los Angeles, the video series The City in Cinema, the crowdfunded journalism project Where Is the City of the Future?, and the Los Angeles Review of Books’ Korea Blog. Follow him on Twitter at @colinmarshall or on Facebook.