Group items tagged

"The researchers, Tero Karras, Samuli Laine, and Timo Aila, came up with a new way of constructing a generative adversarial network, or GAN. GANs employ two dueling neural networks to train a computer to learn the nature of a data set well enough to generate convincing fakes. When applied to images, this provides a way to generate often highly realistic fakery. The same Nvidia researchers have previously used the technique to create artificial celebrities (read our profile of the inventor of GANs, Ian Goodfellow)."

"What Hamilton and his colleagues found surprising was that this approach could also be applied to helping find problems with existing deep networks, related to the surge of "deepfakes" that have recently cropped up. They applied this data structure to find areas where probabilistic models, such as the generative adversarial networks (GANs) that are often used to create deepfakes, break down. They coined these problematic areas "blind spots," and note that they give us insight into how GANs can be biased. Such blind spots further show that GANs struggle to represent particular areas of a dataset, even if most of their fakes can fool a human. "

"At their core, GANs consist of two networks: the generator and discriminator. These computer programs compete against each other millions-upon-millions of times to refine their image generating skills until they're good enough to create the full-fledged pictures."

"The underlying theory is that art evolves "through small alterations to a known style that produce a new one," which, as Ian Bogost (previously) points out, is "a convenient take, given that any machine-learning technique has to base its work on a specific training set.""