AI-assisted miniaturization of integrated photonic components project

 

Novel optimization techniques such as nanophotonic inverse design are promising tools to significantly reduce the size of silicon photonic components while maintaining their functionality and performance. Such techniques, on the other hand, generate discrete designs that are characterized by a large number of variables, requiring computation-intensive design process. AI tools can help identify patterns in the high-dimensional design space through the analysis of a dataset of simulated designs. Those patterns can further guide the search for better performing designs and shed light on the behavior of the design space as a whole, revealing its specificities and limitations. Use of various machine learning methods to identify such patterns will be investigated, in particular in the context of designing in-plane devices such as mode and frequency (de)multiplexers. This project is a collaboration between McGill University and the NRC. McGill University will provide experience in the designs of photonic integrated devices and circuits while the NRC will provide expertise in machine learning and photonics.

Project team

Dr. Odile Liboiron-Ladouceur

Dr. Odile Liboiron-Ladouceur is Canada Research Chair in Photonic Interconnects at McGill University. She is currently working on the development of device integration and energy-efficient interconnection architectures that use photonic (or optical) technologies. This will allow large amounts of data to be transferred at the speed of light. Dr. Liboiron-Ladouceur is internationally recognized as an experimentalist developing proof-of-concept prototypes of novel integrated photonic devices and subsystems for data communication.

Find out more about Dr. Liboiron-Ladouceur.

Dr. Yuri Grinberg

Dr. Yuri Grinberg is an associate research officer with the National Research Council and is an expert in applied and theoretical machine learning and reinforcement learning. His primary research interests are in advancing the machine learning state of the art to address problems in physics and engineering. In particular, he is interested in development of appropriate AI methodologies for the design of efficient, small-footprint, easy-to-fabricate photonic components with significantly reduced human effort.

Find out more about Dr. Grinberg's research interests and his publications.