The first artificial neural networks weren't abstractions inside a computer, but actual physical systems made of whirring motors and big bundles of wire. Here I'll describe how you can build one for yourself using SnapCircuits, a kid's electronics kit. I'll also muse about how to build a network that works optically using a webcam. And I'll recount what I learned talking to the artist Ralf Baecker, who built a network using strings, levers, and lead weights. I showed the SnapCircuits network last year to John Hopfield, a Princeton University physicist who pioneered neural networks in the 1980s, and he quickly got absorbed in tweaking the system to see what he could get it to do. I was a visitor at the Institute for Advanced Study and spent hours interviewing Hopfield for my forthcoming book on physics and the mind. The type of network that Hopfield became famous for is a bit different from the deep networks that power image recognition and other A.I. systems today.

A team of researchers at the Google Brain office have been working on a project that involved creating three separate neural networks that between them have the ability to create and send encrypted messages. This type of machine learning will become more prominent in the world of AI over the next few years, particularly when it comes to handling private or sensitive information. Two of the researchers involved, Martin Abadi and David Anderson, wrote in their paper that "The learning does not require prescribing a set of cryptographic algorithms, nor indicating ways of applying these algorithms: it is based only on a secrecy specification represented by the training objectives." After several thousand simulations, Alice and Bob were each able to send and decrypt messages securely. Eve on the other hand, was unable to fully decrypt the messages.