Silicon photonics integration technologies for future computing systems

Integrated photonics technology offers great potential for applications in neuromorphic systems. We discuss two examples; integrated photonic non-volatile optical weights and a photonic non-volatile memory based analog accelerator for the inference and training of deep neural networks.

[1]  Juerg Leuthold,et al.  Large Pockels effect in micro- and nanostructured barium titanate integrated on silicon , 2018, Nature Materials.

[2]  Pritish Narayanan,et al.  Equivalent-accuracy accelerated neural-network training using analogue memory , 2018, Nature.

[3]  B. J. Offrein,et al.  Non-Volatile Photonic Weights and their Impact on Photonic Reservoir Computing Systems , 2019, 2019 Conference on Lasers and Electro-Optics Europe & European Quantum Electronics Conference (CLEO/Europe-EQEC).

[4]  Gökmen Tayfun,et al.  Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices: Design Considerations , 2016, Front. Neurosci..

[5]  Bernard H. Soffer,et al.  Holographic neurocomputer utilizing laser diode light source , 1995, Optics & Photonics.

[6]  Jean Fompeyrine,et al.  Multi-Level Optical Weights in Integrated Circuits , 2017, 2017 IEEE International Conference on Rebooting Computing (ICRC).

[7]  Yannick Baumgartner,et al.  CMOS-embedded lasers for advanced silicon photonic devices , 2017, 2017 19th International Conference on Transparent Optical Networks (ICTON).

[8]  Daniel Brunner,et al.  Parallel photonic information processing at gigabyte per second data rates using transient states , 2013, Nature Communications.

[9]  Paul R. Prucnal,et al.  Spike processing with a graphene excitable laser , 2016, Scientific Reports.