TR2018-180

Deep Neural Network Inverse Design of Integrated Photonic Power Splitters


    •  TaherSima, M., Kojima, K., Koike-Akino, T., Jha, D., Wang, B., Lin, C., Parsons, K., "Deep Neural Network Inverse Design of Integrated Photonic Power Splitters", Tech. Rep. TR2018-180, Mitsubishi Electric Research Laboratories, Cambridge, MA, December 2018.
      BibTeX Download PDF
      • @techreport{MERL_TR2018-180,
      • author = {TaherSima, M. and Kojima, K. and Koike-Akino, T. and Jha, D. and Wang, B. and Lin, C. and Parsons, K.},
      • title = {Deep Neural Network Inverse Design of Integrated Photonic Power Splitters},
      • institution = {MERL - Mitsubishi Electric Research Laboratories},
      • address = {Cambridge, MA 02139},
      • number = {TR2018-180},
      • month = dec,
      • year = 2018,
      • url = {http://www.merl.com/publications/TR2018-180/}
      • }
  • MERL Contacts:
  • Research Areas:

    Artificial Intelligence, Communications, Electronic and Photonic Devices


Predicting physical response of an artificially structured material is of particular interest for scientific and engineering applications. Here we use deep learning to predict optical response of artificially engineered nanophotonic devices. In addition to predicting forward approximation of transmission response for any given topology, this approach allows us to inversely approximate designs for a targeted optical response. Our Deep Neural Network (DNN) could design compact (2.6x2.6 um 2) silicon-on-insulator (SOI)-based 1x2 power splitters with various target splitting ratios in a fraction of a second. This model is trained to minimize the reflection (to smaller than ~ -20 dB) while achieving maximum transmission efficiency above 90% and target splitting specifications. This approach paves the way for rapid design of integrated photonic components relying on complex nanostructures.