Cascadable all-optical NAND gates using diffractive networks

Owing to its potential advantages such as scalability, low latency and power efficiency, optical computing has seen rapid advances over the last decades. A core unit of a potential all-optical processor would be the NAND gate, which can be cascaded to perform an arbitrary logical operation. Here, we present the design and analysis of cascadable all-optical NAND gates using diffractive neural networks. We encoded the logical values at the input and output planes of a diffractive NAND gate using the relative optical power of two spatially-separated apertures. Based on this architecture, we numerically optimized the design of a diffractive neural network composed of 4 passive layers to all-optically perform NAND operation using the diffraction of light, and cascaded these diffractive NAND gates to perform complex logical functions by successively feeding the output of one diffractive NAND gate into another. We demonstrated the cascadability of our diffractive NAND gates by using identical diffractive designs to all-optically perform AND and OR operations, as well as a half-adder. Cascadable all-optical NAND gates composed of spatially-engineered passive diffractive layers can serve as a core component of various optical computing platforms.

[1]  Yi Luo,et al.  Analysis of Diffractive Optical Neural Networks and Their Integration With Electronic Neural Networks , 2018, IEEE Journal of Selected Topics in Quantum Electronics.

[2]  A. Ozcan,et al.  Spectrally encoded single-pixel machine vision using diffractive networks , 2021, Science Advances.

[3]  A. Ozcan,et al.  Scale-, shift- and rotation-invariant diffractive optical networks , 2020, ACS Photonics.

[4]  Aydogan Ozcan,et al.  Computational imaging without a computer: seeing through random diffusers at the speed of light , 2021, eLight.

[5]  Qianfan Xu,et al.  All-optical logic based on silicon micro-ring resonators. , 2007, Optics express.

[6]  Pierre Ambs,et al.  Optical Computing: A 60-Year Adventure , 2010 .

[7]  Yun Tian,et al.  Energy consumption and emission mitigation prediction based on data center traffic and PUE for global data centers , 2020 .

[8]  L. Belkhir,et al.  Assessing ICT global emissions footprint: Trends to 2040 & recommendations , 2018 .

[9]  Yi Luo,et al.  All-optical machine learning using diffractive deep neural networks , 2018, Science.

[10]  Ryan Hamerly,et al.  Large-Scale Optical Neural Networks based on Photoelectric Multiplication , 2018, Physical Review X.

[11]  Hong Wei,et al.  Cascaded logic gates in nanophotonic plasmon networks , 2011, Nature communications.

[12]  Jian Xu,et al.  Performing optical logic operations by a diffractive neural network , 2020, Light: Science & Applications.

[13]  Somaye Serajmohammadi,et al.  All-Optical NAND Gate Based on Nonlinear Photonic Crystal Ring Resonators , 2016 .

[14]  Aydogan Ozcan,et al.  All-Optical Information Processing Capacity of Diffractive Surfaces , 2020, ArXiv.

[15]  Tanay Chattopadhyay,et al.  All optical design of binary adders using semiconductor optical amplifier assisted Mach-Zehnder interferometer , 2015, Microelectron. J..

[16]  A. Ozcan,et al.  Misalignment resilient diffractive optical networks , 2020, Nanophotonics.

[17]  J. Feldmann,et al.  All-optical spiking neurosynaptic networks with self-learning capabilities , 2019, Nature.

[18]  Q. Gong,et al.  Silicon photonic crystal all-optical logic gates , 2013 .

[19]  Farhad Mehdizadeh,et al.  All optical NOR and NAND gate based on nonlinear photonic crystal ring resonators , 2014 .

[20]  Yufeng Ding,et al.  Broadband Multifunctional Plasmonic Logic Gates , 2018 .

[21]  Demetri Psaltis,et al.  Optical Computing: Past and Future , 2016 .

[22]  Xiaorui Tian,et al.  Quantum dot-based local field imaging reveals plasmon-based interferometric logic in silver nanowire networks. , 2011, Nano letters.

[23]  Yi Luo,et al.  Class-specific differential detection in diffractive optical neural networks improves inference accuracy , 2019, Advanced Photonics.

[24]  K L Hall,et al.  100-Gbit/s bitwise logic. , 1998, Optics letters.

[25]  Muhammed Veli,et al.  Terahertz pulse shaping using diffractive surfaces , 2020, Nature communications.

[26]  H. John,et al.  Why future supercomputing requires optics , 2010 .

[27]  Y.T. Byun,et al.  All-optical NAND gate using cross gain modulation in semiconductor optical amplifiers , 2005, 2005 Quantum Electronics and Laser Science Conference.

[28]  Yi Luo,et al.  Design of task-specific optical systems using broadband diffractive neural networks , 2019, Light, science & applications.

[29]  Dirk Englund,et al.  Deep learning with coherent nanophotonic circuits , 2017, 2017 Fifth Berkeley Symposium on Energy Efficient Electronic Systems & Steep Transistors Workshop (E3S).

[30]  A. Boes,et al.  11 TOPS photonic convolutional accelerator for optical neural networks , 2021, Nature.

[31]  Aydogan Ozcan,et al.  All-optical synthesis of an arbitrary linear transformation using diffractive surfaces , 2021, Light, science & applications.

[32]  Paul R. Prucnal,et al.  A Laser Spiking Neuron in a Photonic Integrated Circuit. , 2020, 2012.08516.

[33]  K. Zoiros,et al.  On the feasibility of ultrafast all-optical NAND gate using single quantum-dot semiconductor optical amplifier-based Mach–Zehnder interferometer , 2012 .

[34]  D. Miller,et al.  Are optical transistors the logical next step , 2010 .

[35]  Md Sadman Sakib Rahman,et al.  Computer-Free, All-Optical Reconstruction of Holograms Using Diffractive Networks , 2021, ACS Photonics.