Ferreira de Lima Thomas, Doris Eli A, Bilodeau Simon, Zhang Weipeng, Jha Aashu, Peng Hsuan-Tung, Blow Eric C, Huang Chaoran, Tait Alexander N, Shastri Bhavin J, Prucnal Paul R
Department of Electrical and Computer Engineering, Princeton University, Princeton 08544, NJ, USA.
Department of Electrical Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China.
Nanophotonics. 2022 Apr 11;11(17):3805-3822. doi: 10.1515/nanoph-2022-0049. eCollection 2022 Sep.
Neuromorphic photonic processors based on resonator weight banks are an emerging candidate technology for enabling modern artificial intelligence (AI) in high speed analog systems. These purpose-built analog devices implement vector multiplications with the physics of resonator devices, offering efficiency, latency, and throughput advantages over equivalent electronic circuits. Along with these advantages, however, often come the difficult challenges of compensation for fabrication variations and environmental disturbances. In this paper, we review sources of variation and disturbances from our experiments, as well as mathematically define quantities that model them. Then, we introduce how the physics of resonators can be exploited to weight and sum multiwavelength signals. Finally, we outline automated design and control methodologies necessary to create practical, manufacturable, and high accuracy/precision resonator weight banks that can withstand operating conditions in the field. This represents a road map for unlocking the potential of resonator weight banks in practical deployment scenarios.
基于谐振器权重库的神经形态光子处理器是一种新兴的候选技术，可用于在高速模拟系统中实现现代人工智能（AI）。这些专门设计的模拟设备利用谐振器设备的物理特性实现矢量乘法，与等效的电子电路相比，具有效率、延迟和吞吐量优势。然而，伴随着这些优势而来的往往是补偿制造变化和环境干扰的艰巨挑战。在本文中，我们回顾了实验中的变化和干扰源，并从数学上定义了对它们进行建模的量。然后，我们介绍了如何利用谐振器的物理特性对多波长信号进行加权和求和。最后，我们概述了创建能够承受现场操作条件的实用、可制造且高精度/高精密谐振器权重库所需的自动化设计和控制方法。这代表了在实际部署场景中释放谐振器权重库潜力的路线图。
