Deep neural networks (DNN) consist of layers of neurons interconnected by synaptic weights. A high bit-precision in weights is generally required to guarantee high accuracy in many applications. Minimizing error accumulation between layers is also essential when building large-scale networks. Recent demonstrations of photonic neural networks are limited in bit-precision due to crosstalk and the high sensitivity of optical components (e.g., resonators). Here, we experimentally demonstrate a record-high precision of 9 bits with a dithering control scheme for photonic synapses. We then numerically simulated the impact with increased synaptic precision on a wireless signal classification application. This work could help realize the potential of photonic neural networks for many practical, real-world tasks.
@article{arxiv.2104.01164,
title = {Silicon microring synapses enable photonic deep learning beyond 9-bit precision},
author = {Weipeng Zhang and Chaoran Huang and Hsuan-Tung Peng and Simon Bilodeau and Aashu Jha and Eric Blow and Thomas Ferreira De Lima and Bhavin J. Shastri and Paul Prucnal},
journal= {arXiv preprint arXiv:2104.01164},
year = {2022}
}