Artificial Synapse with Mnemonic Functionality using GSST-based Photonic Integrated Memory

Authors

  • Mario Miscuglio Department of Electrical and Computer Engineering George Washington University Washington DC 20052, USA
  • Jiawei Meng Department of Electrical and Computer Engineering George Washington University Washington DC 20052, USA
  • Armin Mehrabian Department of Electrical and Computer Engineering George Washington University Washington DC 20052, USA
  • Volker J. Sorger Department of Electrical and Computer Engineering George Washington University Washington DC 20052, USA
  • Omer Yesiliurt Birck Nanotechnology Center School of ECE, Purdue University West Lafayette, IN 47907, USA,
  • Ludmila J. Prokopeva Birck Nanotechnology Center School of ECE, Purdue University West Lafayette, IN 47907, USA,
  • Alexander V. Kildishev Birck Nanotechnology Center School of ECE, Purdue University West Lafayette, IN 47907, USA,
  • Yifei Zhang Department of Materials Science & Engineering Massachusetts Institute of Technology Cambridge, MA, USA
  • Juejun Hu Department of Materials Science & Engineering Massachusetts Institute of Technology Cambridge, MA, USA

Keywords:

GSST, phase change memories, photonic memories

Abstract

Here we present a multi-level discrete-state nonvolatile photonic memory based on an ultra-compact (<4μm) hybrid phase change material GSST-silicon Mach Zehnder modulator, with low insertion losses (3dB), to serve as node in a photonic neural network. Emulating an opportunely trained 100 × 100 fully connected multilayered perceptron neural network with this weighting functionality embedded as photonic memory, shows up to 92% inference accuracy and robustness towards noise when performing predictions of unseen data.

References

D. A. B. Miller, “Optical interconnects to electronic chips,” Appl. Opt., AO, vol. 49, no. 25, pp. F59-F70, Sep. 2010. doi: 10.1364/AO.49.000F59.

G. Heinze, C. Hubrich, and T. Halfmann, “Stopped light and image storage by electromagnetically induced transparency up to the regime of one minute,” Phys. Rev. Lett., vol. 111, no. 3, p. 033601, July 2013. doi: 10.1103/PhysRevLett.111.033601.

L. Ma, O. Slattery, and X. Tang, “Optical quantum memory based on electromagnetically induced transparency,” J. Opt., vol. 19, no. 4, Apr. 2017. doi: 10.1088/2040-8986/19/4/043001.

M. Stegmaier, C. Ríos, H. Bhaskaran, C. D. Wright, and W. H. P. MISCUGLIO, MENG, MEHRABIAN, SORGER, YESILIURT, ET AL.: ARTIFICIAL SYNAPSE WITH MNEMONIC FUNCTIONALITY 1448 Pernice, “Nonvolatile all-optical 1 × 2 switch for chipscale photonic networks,” Advanced Optical Materials, vol. 5, no. 1, p. 1600346, Jan. 2017. doi: 10.1002/adom.201600346.

P. Xu, J. Zheng, J. K. Doylend, and A. Majumdar, “Low-loss and broadband nonvolatile phase-change directional coupler switches,” ACS Photonics, vol. 6, no. 2, pp. 553-557, Feb. 2019. doi: 10.1021/acsphotonics.8b01628.

L. Waldecker, et al., “Time-domain separation of optical properties from structural transitions in resonantly bonded materials,” Nature Materials, vol. 14, no. 10, pp. 991-995, Oct. 2015. doi: 10.1038/nmat4359.

R. E. Simpson, et al., “Interfacial phase-change memory,” Nature Nanotechnology, vol. 6, no. 8, pp. 501-505, Aug. 2011. doi: 10.1038/nnano.2011.96.

M. Rudé, et al., “Optical switching at 1.55 μ m in silicon racetrack resonators using phase change materials,” Appl. Phys. Lett., vol. 103, no. 14, p. 141119, Sep. 2013. doi: 10.1063/1.4824714.

Y. Zhang, et al., “Broadband transparent optical phase change materials for high-performance nonvolatile photonics,” Nat. Commun., vol. 10, no. 1, pp. 1-9, Sep. 2019. doi: 10.1038/s41467-019-12196-4.

M. Delaney, I. Zeimpekis, D. Lawson, D. W. Hewak, and O. L. Muskens, “A new family of ultralow loss reversible phase-change materials for photonic integrated circuits: Sb2S3 and Sb2Se3,” Advanced Functional Materials, vol. 30, no. 36, p. 2002447, 2020. doi: 10.1002/adfm.202002447.

L. J. Prokopeva, et al., “Time domain modeling of bi-anisotropic media and phase change materials with generalized dispersion (Conference Presentation),” in Metamaterials, Metadevices, and Metasystems 2019, Sep. 2019, vol. 11080, p. 1108006. doi: 10.1117/12.2529097.

R. Amin, et al., “0.52 V mm ITO-based mach-zehnder modulator in silicon photonics,” APL Photonics, vol. 3, no. 12, p. 126104, Dec. 2018. doi: 10.1063/1.5052635.

M. Miscuglio and V. J. Sorger, “Photonic tensor cores for machine learning,” Applied Physics Reviews, vol. 7, no. 3, p. 031404, July 2020. doi: 10.1063/5.0001942.

N. C. Harris, et al., “Efficient, compact and low loss thermo-optic phase shifter in silicon,” Opt. Express, vol. 22, no. 9, p. 10487, May 2014. doi: 10.1364/OE.22.010487.

R. Amin, et al., “ITO-based electro-absorption modulator for photonic neural activation function,” APL Materials, vol. 7, no. 8, p. 081112, Aug. 2019. doi: 10.1063/1.5109039.

A. Mehrabian, M. Miscuglio, Y. Alkabani, V. J. Sorger, and T. ElGhazawi, “A Winograd-based integrated photonics accelerator for convolutional neural networks,” IEEE Journal of Selected Topics in Quantum Electronics, vol. 26, no. 1, pp. 1-12, Jan. 2020. doi: 10.1109/JSTQE.2019.2957443.

Downloads

Published

2020-11-07

How to Cite

Mario Miscuglio, Jiawei Meng, Armin Mehrabian, Volker J. Sorger, Omer Yesiliurt, Ludmila J. Prokopeva, Alexander V. Kildishev, Yifei Zhang, & Juejun Hu. (2020). Artificial Synapse with Mnemonic Functionality using GSST-based Photonic Integrated Memory. The Applied Computational Electromagnetics Society Journal (ACES), 35(11), 1447–1448. Retrieved from https://journals.riverpublishers.com/index.php/ACES/article/view/7649

Issue

Section

Articles