One popular way of doing machine learning is with neural networks that are very loosely modeled on the brain’s system of connections. ML, as it is often abbreviated, is a way of programming computers to teach themselves how to do various tasks, usually by feeding them labeled data to “train” on. Machine learning is the broadest term for the tools Google has adopted. Magenta is one of Google’s wilder attempts to organize and understand a particular human domain. Last year, Google CEO Sundar Pichai declared the company “artificial intelligence-first.” AI, for Google, is a natural extension of its original mission “to organize the world's information and make it universally accessible and useful.” What’s changed is that now the information is being organized for artificial intelligences, which then make it accessible and useful for people. “From a young age, we develop the ability to communicate what we see by drawing on paper with a pencil or crayon.”Īnd if humans can do it, Google would like machines to be able to do it. “Humans … do not understand the world as a grid of pixels, but rather develop abstract concepts to represent what we see,” Eck and Ha argue in their paper describing the work. ![]() This is a core insight of the Magenta team. “I don’t want to say ‘so human,’ but they feel so right in a way that these pixel-generation things don’t.” The outputs of SketchRNN, however, don’t feel uncanny at all. They are interesting because they make images that are sort of like, but not exactly like, human perception of the real world. These projects all feel, subjectively, to humans, uncanny. ![]() This is distinct from the kind of photograph-based work that’s inspired so many news stories, like when a machine can render a photograph in the style of Van Gogh or the original DeepDream, or drawing any shape and having it fill in with “ catness.” Each class of drawing-cat, yoga, rain-can be used to train a particular kind of neural network using Google’s open-source TensorFlow software library. It is these simple strokes that are the underlying dataset for SketchRNN. When we sketch, we compress the rich, colorful, noisy world into just a few movements of a (digital) pen. ![]() Google built a game called, “ Quick, Draw!” which, as people played, generated a large database of human drawings of all kinds of stuff: pigs and rain, firetrucks and yoga poses, gardens and owls. Learn how to draw pigs and maybe you learn something about the human ability to synthesize pigness. That is to say, there is a connection between how our brains store “pigness” and how we draw pigs. They sketch the generalized concept of “pig,” not any particular animal. The implicit argument is that when humans draw, they make abstractions of the world. They want to create a machine that can recognize and output “pigness,” even if it is fed prompts, like a truck, which don’t belong in the barnyard. The point of SketchRNN, as he and Google collaborator David Ha have written, is not only to learn how to draw pictures, but to “generalize abstract concepts in a manner similar to humans.” They don’t want to create a machine that can sketch pigs. in computer science from the University of Indiana in 2000, and has spent the intervening years working on music and machine learning, first as a professor at the University of Montreal (a hotbed for artificial intelligence) and then at Google, where he worked at Google Music before heading to Google Brain to work on Magenta.Įck’s drive to create AI tools for making art began as a rant, “but after a few cycles of thinking,” he said, “it became, ‘Of course we need to do this, this is really important.’” Eck is clever, casual, and self-effacing. Last week, I visited Eck at Google Brain team’s offices in Mountain View, where Magenta is housed. It’s called Project Magenta, and it’s led by Doug Eck. This pig truck is actually the output of a fascinating artificial intelligence system called SketchRNN, a part of a new effort at Google to see if AI can make art. Until recently, only human beings could have pulled off this sort of conceptual twist, but no more. If you’d drawn it, I, a fellow human, would subjectively rate this a creative interpretation of the prompt “pig truck.” ![]() The wheels have turned hoof-like, or alternatively, the pig legs have turned wheel-like. Note the little squiggly pig tail, the slight rounding of the window in the cab, which recalls an eye.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |