Deep learning is one of the most advancing technologies in various fields. Facing the limits of the current electronics platform, optical neural networks (ONNs) based on Si programmable photonic integrated circuits (PICs) have attracted considerable attention as a novel deep learning scheme with optical-domain matrix-vector multiplication (MVM). However, most of the proposed Si programmable PICs for ONNs have several drawbacks such as low scalability, high power consumption, and lack of frameworks for training. To address these issues, we have proposed a microring resonator (MRR) crossbar array as a Si programmable PIC for an ONN. In this article, we present a prototype of a fully integrated 4 ${\rm \times}$ 4 MRR crossbar array and demonstrated a simple MVM and classification task. Moreover, we propose on-chip backpropagation using the transpose matrix operation of the MRR crossbar array, enabling the on-chip training of the ONN. The proposed ONN scheme can establish a scalable, power-efficient deep learning accelerator for applications in both inference and training tasks.

中文翻译：

---

用于光学神经网络的片上推理和训练的硅微环谐振器纵横阵列

深度学习是各个领域最先进的技术之一。面对当前电子平台的局限性，基于 Si 可编程光子集成电路 (PIC) 的光神经网络 (ONN) 作为具有光域矩阵向量乘法 (MVM) 的新型深度学习方案引起了相当多的关注。然而，大多数提出的用于 ONN 的 Si 可编程 PIC 都有几个缺点，例如低可扩展性、高功耗和缺乏训练框架。为了解决这些问题，我们提出了一种微环谐振器 (MRR) 交叉阵列作为 ONN 的 Si 可编程 PIC。在本文中，我们展示了一个完全集成的 4 ${\rm \times}$ 4 MRR crossbar 阵列的原型，并演示了一个简单的 MVM 和分类任务。而且，我们建议使用 MRR 交叉阵列的转置矩阵运算进行片上反向传播，从而实现 ONN 的片上训练。所提出的 ONN 方案可以为推理和训练任务中的应用程序建立一个可扩展、节能的深度学习加速器。