I Built My Own Artificial Neural Network
The 2024 Nobel Prize in Physics was awarded today to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.” In 2019, Hopfield helped Nautilus contributing editor George Musser design his own simple artificial neural network. We’re reposting Musser’s 2020 article because it serves as a wonderful introduction to Hopfield’s breakthrough science.
T he 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 J. 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, Putting Ourselves Back in the Equation: Why Physicists Are Studying Human Consciousness and AI to Unravel the Mysteries of the Universe.
