Optical convolutional neural network accelerator for machine learning

Here we report on a prototype optical convolutional neural network accelerator capable of processing large amounts of information, on the order of petabytes, per second. Unlike the current paradigm in electronic machine learning hardware that processes information sequentially, this processor uses the Fourier optics, a concept of frequency filtering which allows for performing the required convolutions of the neural network as much simpler element-wise multiplications using the digital mirror technology. To achieve a breakthrough in this optical machine learning system, we replace spatial light modulators with digital mirror-based technology, thus developing a system over 100 times faster. This innovation, which harnesses the massive parallelism of light, heralds a new era of optical signal processing for machine learning with numerous applications, including in self-driving cars, 5G networks, data-centers, biomedical diagnostics, data-security and more.