See allHide authors and affiliations As neural nets push into science, researchers probe back Researchers have created neural networks that, in addition to filling gaps left in photos, can identify flaws in an artificial intelligence. Jason Yosinski sits in a small glass box at Uber’s San Francisco, California, headquarters, pondering the mind of an artificial intelligence.

An Uber research scientist, Yosinski is performing a kind of brain surgery on the AI running on his laptop. Like many of the AIs that will soon be powering so much of modern life, including self-driving Uber cars, Yosinski’s program is a deep neural network, with an architecture loosely inspired by the brain.

And like the brain, the program is hard to understand from the outside: It’s a black box. No one trained this network to identify faces.

Humans weren’t labeled in its training images. Yet learn faces it did, perhaps as a way to recognize the things that tend to accompany them, such as ties and cowboy hats.

The network is too complex for humans to comprehend its exact decisions. Yosinski’s probe had illuminated one small part of it, but overall, it remained opaque. Read more from science.sciencemag.org…

thumbnail courtesy of sciencemag.org