The Royal Institution for the Advancement of Learning/McGill University

Published purpose

Novel optimization techniques like nanophotonic inverse design are promising tools to significantly reduce the size of passive Silicon photonic components while maintaining their functionality and performance. Although published results demonstrate various proof of concept miniaturized devices with pre-determined size and aspect ratio, their performances as of now are inferior to the state of the art and the designs are highly non-interpretable. In this respect, AI tools can help identify patterns in the high-dimensional design space through the analysis of a dataset of simulated designs that guide the search for better performing designs and shed light on the behavior of the design space, revealing its specificities and limitations. Ultimately, the use of AI tools will bring the miniaturization of Silicon integrated photonic components to the next level, without compromising on their performance and manufacturability.