Parallel convolutional processing using an integrated photonic tensor core
Machine learning and artificial intelligence applications make use of vast troves of data. Our data is increasing exponentially and using this data to create information requires computer processing. The capabilities of conventional computer processors are not sufficient to keep up with this demand.
Members of Professor Harish Bhaskaran's Advanced Nanoscale Engineering Group, Johannes Feldman and Xuan Li, along with an international research team, have developed a new approach and processor architecture which provides a potential avanue to perform these tasks at high throughput - essentially by combining processing and data storage functionalities into a single chip - so called in-memory processors, but using light.
The team implemented a hardware accelerator for so-called matrix-vector multiplications. Such operations form the backbone of neural networks (a series of algorithims which simulate the human brain) that are used to compute machine learning algorithims. Using light allowed the team to use multiple wavelengths of light to do parallel calculations since light has the amazing property of having different colours that do not interfere. However, to do this, they used yet another recent invention, a chip-based frequency comb, as a light source. Once the chips were designed and fabricated, the researchers used a convolution neural network for the recognition of handwritten numbers.
The full paper can be read in Nature.