Visualizing an AI model's blind spots

Anyone who has spent time on social media has probably noticed that GANs, or generative adversarial networks, have become remarkably good at drawing faces. They can predict what you'll look like when you're old and what you'd look like as a celebrity. But ask a GAN to draw scenes from the larger world and things get weird. A new demo by the MIT-IBM Watson AI Lab reveals what a model trained on scenes of churches and monuments decides to leave out when it draws its own version of, say, the Pantheon in Paris, or the Piazza di Spagna in Rome. The larger study, Seeing What a GAN Cannot Generate, was presented at the International Conference on Computer Vision this week. "Researchers typically focus on characterizing and improving what a machine-learning system can do -- what it pays attention to, and how particular inputs lead to particular outputs," says David Bau, a graduate student at MIT's Department of Electrical Engineering and Computer Science and Computer Science and Artificial Science Laboratory (CSAIL).