TR2018-183

Deep Neural Network Inverse Modeling for Integrated Photonics


    •  TaherSima, M., Kojima, K., Koike-Akino, T., Jha, D., Wang, B., Lin, C., Parsons, K., "Deep Neural Network Inverse Modeling for Integrated Photonics", Tech. Rep. TR2018-183, Mitsubishi Electric Research Laboratories, Cambridge, MA, December 2018.
      BibTeX Download PDF
      • @techreport{MERL_TR2018-183,
      • 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 Modeling for Integrated Photonics},
      • institution = {MERL - Mitsubishi Electric Research Laboratories},
      • address = {Cambridge, MA 02139},
      • number = {TR2018-183},
      • month = dec,
      • year = 2018,
      • url = {http://www.merl.com/publications/TR2018-183/}
      • }
  • MERL Contacts:
  • Research Areas:

    Communications, Electronic and Photonic Devices, Machine Learning


We propose a deep neural network model that instantaneously predicts the optical response of nanopatterned silicon photonic power splitter topologies, and inversely approximates compact (2.6 x 2.6 um2) and efficient (above 92%) power splitters for target splitting ratios.