Generative Deep Learning Model for Inverse Design of Integrated Nanophotonic Devices
Yingheng Tang
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
School of Electrical and Computer Engineering and Birck Nanotechnology Center, Purdue University, West Lafayette, IN, 47907 USA
Search for more papers by this authorCorresponding Author
Keisuke Kojima
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
E-mail: [email protected]
Search for more papers by this authorToshiaki Koike-Akino
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorYe Wang
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorPengxiang Wu
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorYouye Xie
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorMohammad H. Tahersima
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorDevesh K. Jha
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorKieran Parsons
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorMinghao Qi
School of Electrical and Computer Engineering and Birck Nanotechnology Center, Purdue University, West Lafayette, IN, 47907 USA
Search for more papers by this authorYingheng Tang
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
School of Electrical and Computer Engineering and Birck Nanotechnology Center, Purdue University, West Lafayette, IN, 47907 USA
Search for more papers by this authorCorresponding Author
Keisuke Kojima
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
E-mail: [email protected]
Search for more papers by this authorToshiaki Koike-Akino
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorYe Wang
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorPengxiang Wu
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorYouye Xie
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorMohammad H. Tahersima
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorDevesh K. Jha
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorKieran Parsons
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA
Search for more papers by this authorMinghao Qi
School of Electrical and Computer Engineering and Birck Nanotechnology Center, Purdue University, West Lafayette, IN, 47907 USA
Search for more papers by this authorAbstract
A novel conditional variational autoencoder (CVAE) model for designing nanopatterned integrated photonic components is proposed. In particular, it is shown that prediction capability of the CVAE model can be significantly improved by adversarial censoring and active learning. Moreover, generation of nanopatterned power splitters with arbitrary splitting ratios and 550 nm broadband optical responses from 1250 to 1800 nm are demonstrated. Nanopatterned power splitters with footprints of 2.25 × 2.25 m2 and 20 × 20 etch hole positions are the design space, with each hole position assuming a radius from a range of radii. Designed nanopatterned power splitters using methods presented herein demonstrate an overall transmission of about 90% across the operating bandwidth from 1250 to 1800 nm. To the best of authors' knowledge, this is the first time that a state-of-the-art CVAE deep neural network model is successfully used to design a physical device.
6 Conflict of Interest
The authors declare no conflict of interest.
References
- 1D. Mrowca, C. Zhuang, E. Wang, N. Haber, L. F. Fei-Fei, J. Tenenbaum, D. L. Yamins, in Advances in Neural Information Processing Systems (NIPS), Curran Associates, Red Hook, NY 2018, pp. 8799–8810.
- 2E. S. Spelke, K. Breinlinger, J. Macomber, K. Jacobson, Psychol. Rev. 1992, 99, 605.
- 3J. B. Tenenbaum, C. Kemp, T. L. Griffiths, N. D. Goodman, Science 2011, 331, 1279.
- 4M. McCloskey, A. Caramazza, B. Green, Science 1980, 210, 1139.
- 5K. A. Smith, E. Vul, Top. Cogn. Sci. 2013, 5, 185.
- 6E. S. Spelke, Cogn. Sci. 1990, 14, 29.
- 7M. B. Chang, T. Ullman, A. Torralba, J. B. Tenenbaum, arXiv preprint, arXiv:1612.00341, 2016.
- 8A. Lerer, S. Gross, R. Fergus, arXiv preprint, arXiv:1603.01312, 2016.
- 9P. Battaglia, R. Pascanu, M. Lai, D. J. Rezende, K. Kavukcuoglu, in Advances in Neural Information Processing Systems (NIPS), Curran Associates, Red Hook, NY 2016, pp. 4502–4510.
- 10A. D. Sendek, E. D. Cubuk, E. R. Antoniuk, G. Cheon, Y. Cui, E. J. Reed, arXiv preprint, arXiv:1808.02470, 2018.
- 11R. Gómez-Bombarelli, J. N. Wei, D. Duvenaud, J. M. Hernández-Lobato, B. Sánchez-Lengeling, D. Sheberla, J. Aguilera-Iparraguirre, T. D. Hirzel, R. P. Adams, A. Aspuru-Guzik, ACS Cent. Sci. 2018, 4, 268.
- 12J. Ghaboussi, J. H. Garrett Jr., X. Wu, J. Eng. Mech. 1991, 117, 132.
- 13A. Radovic, M. Williams, D. Rousseau, M. Kagan, D. Bonacorsi, A. Himmel, A. Aurisano, K. Terao, T. Wongjirad, Nature 2018, 560, 41.
- 14M. H. Tahersima, K. Kojima, T. Koike-Akino, D. Jha, B. Wang, C. Lin, K. Parsons, Sci. Rep. 2019, 9, 1368.
- 15D. Liu, Y. Tan, E. Khoram, Z. Yu, ACS Photon. 2018, 5, 1365.
- 16W. Ma, F. Cheng, Y. Liu, ACS Nano 2018, 12, 6326.
- 17I. Malkiel, M. Mrejen, A. Nagler, U. Arieli, L. Wolf, H. Suchowski, in 2018 IEEE International Conference on Computational Photography (ICCP), IEEE, Piscataway, NJ 2018, pp. 1–14.
- 18J. Peurifoy, Y. Shen, L. Jing, Y. Yang, F. Cano-Renteria, B. G. DeLacy, J. D. Joannopoulos, M. Tegmark, M. Soljačić, Sci. Adv. 2018, 4, eaar4206.
- 19Y. Sun, Z. Xia, U. S. Kamilov, Opt. Express 2018, 26, 14678.
- 20Z. Liu, D. Zhu, S. P. Rodrigues, K.-T. Lee, W. Cai, Nano Lett. 2018, 18, 6570.
- 21T. Asano, S. Noda, Opt. Express 2018, 26, 32704.
- 22A. M. Hammond, R. M. Camacho, Opt. Express 2019, 27, 29620.
- 23W. Ma, F. Cheng, Y. Xu, Q. Wen, Y. Liu, arXiv preprint, arXiv:1901.10819, 2019.
- 24K. Kojima, B. Wang, U. Kamilov, T. Koike-Akino, K. Parsons, in Integrated Photonics Research, Silicon and Nanophotonics (IPR), OSA, Washington DC 2017, paper ITu1A.4.
- 25M. Teng, K. Kojima, T. Koike-Akino, B. Wang, C. Lin, K. Parsons, in Optical Fiber Communications Conference and Exposition (OFC), OSA, Washington DC 2018, paper Th2A.8.
- 26S. An, B. Zheng, H. Tang, M. Y. Shalaginov, L. Zhou, H. Li, T. Gu, J. Hu, C. Fowler, H. Zhang, arXiv preprint, arXiv:1908.04851, 2019.
- 27K. Sohn, H. Lee, X. Yan, in Advances in Neural Information Processing Systems (NIPS), Curran Associates, Red Hook, NY 2015, pp. 3483–3491.
- 28Y. Wang, T. Koike-Akino, D. Erdogmus, arXiv preprint, arXiv:1805.08097, 2018.
- 29G. Lample, N. Zeghidour, N. Usunier, A. Bordes, L. Denoyer, M. Ranzato, in Advances In Neural Information Processing Systems (NIPS), Curran Associates, Red Hook, NY 2017, pp. 5967–5976.
- 30O. Özdenizci, Y. Wang, T. Koike-Akino, D. Erdoğmuş, in, 99th Int. IEEE/EMBS Conf. on Neural Engineering (NER), IEEE, Piscataway, NJ 2019, pp. 207–210.
- 31M. H. Tahersima, K. Kojima, T. Koike-Akino, D. Jha, B. Wang, C. Lin, K. Parsons, in CLEO: Science and Innovations, OSA, Washington DC 2019, paper SW4J.6.
- 32C. M. Lalau-Keraly, S. Bhargava, O. D. Miller, E. Yablonovitch, Opt. Express 2013, 21, 21693.
- 33A. Y. Piggott, J. Lu, K. G. Lagoudakis, J. Petykiewicz, T. M. Babinec, J. Vučković, Nat. Photonics 2015, 6, 374.
- 34K. Wang, X. Ren, W. Chang, L. Liu, D. Liu, M. Zhang, Photonics Res. 2020, 8, 528.
- 35Y. Zhang, S. Yang, A. E.-J. Lim, G.-Q. Lo, C. Galland, T. Baehr-Jones, M. Hochberg, Opt. Express 2013, 21, 1310.
- 36K. Xu, L. Liu, X. Wen, W. Sun, N. Zhang, N. Yi, S. Sun, S. Xiao, Q. Song, Opt. Lett. 2017, 42, 855.
Citing Literature
