"Deep Learning With Light"
When asking a smart home device for the weather forecast, the device takes several seconds to respond. One reason for this latency is that connected devices lack the amount of memory and power to store and run the massive Machine Learning (ML) models required for the device to understand what a user is asking of it. The model is stored in a data center hundreds of miles away, where the solution is computed and sent to the device. MIT researchers developed a new method for computing directly on these devices that significantly reduces latency. Their method shifts the memory-intensive steps of running an ML model to a central server where components of the model are encoded onto light waves. The waves are transmitted to a connected device via fiber optics, which allows massive amounts of data to be sent quickly across a network. The receiver then employs a simple optical device that performs computations quickly using the components of a model carried by those light waves. When compared to other methods, this technique improves energy efficiency by more than a hundredfold. It may also improve security because a user's data is not transferred to a central location for computation. This article continues to discuss the MIT researchers' new method that uses optics to accelerate ML computations on smart speakers and other low-power connected devices, as well as increase security.