Enlarge / Each of these layers shapes the light that reaches the one behind it, performing calculations in the process. (credit: Ozcan Lab, UCLA)

Neural networks have a reputation for being computationally expensive. But only the training portion of things really stresses most computer hardware, since it involves regular evaluations of performance and constant trips back and forth to memory to tweak the connections among its artificial neurons. Using a trained neural network, in contrast, is a much simpler process, one that isn’t nearly as computationally complex. In fact, the training and execution stages can be performed on completely different hardware.

And there seems to be a fair bit of flexibility in the hardware that can be used for either of these two processes. For example, it’s possible to train neural networks using a specialized form of memory called a memristor or execute trained neural networks using custom silicon chips. Now, researchers at UCLA have done something a bit more radical. After training a neural network using traditional computing hardware, they 3D printed a set of panels that manipulated light in a way that was equivalent to processing information using the neural network. In the end, they got performance at the speed of light—though with somewhat reduced accuracy compared to more traditional hardware.

Lighten up

So how do you implement a neural network using light? To understand that, you have to understand the structure of a deep-learning neural network. In each layer, signals from an earlier one (or the input from a source) are processed by “neurons,” which then take the results and forward signals on to neurons in the next layer. Which neurons they send it to and how strong a signal they pass on are determined by the training they’ve undergone.