Scholarlink

<p>Optical neural networks (ONNs) promise computing efficiency beyond microelectronics for modern artificial intelligence (AI). Current ONNs using analog matrix-vector multiplication (MVM) implementations are fundamentally limited in numerical precision due to accumulated noise in electro-optical processing. We propose a digital-analog hybrid MVM architecture that achieves a high numerical precision without sacrificing computing efficiency. Our fabricated proof-of-concept hybrid optical processor (HOP) achieves 16-bit precision in high-definition image processing, with a pixel error rate of 1.8 × 10<sup>−3</sup> at a signal-to-noise ratio of 18.2 dB, and shows no accuracy loss in MNIST digit recognition. We further explore applying the HOP processor in You Look Only Once (YOLO) object detection and demonstrate sufficient numerical precision is crucial for high confidence detection in real-world neural networks. The hybrid optical computing concept may be applied to various photonic MVM implementations to enable accurate optical computing architectures.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Digital-analog hybrid matrix multiplication processor for optical neural networks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月12日

查看全文
  • Xiansong Meng,
  • Deming Kong,
  • Kwangwoong Kim,
  • Qiuchi Li,
  • Po Dong,
  • Ingemar J. Cox,
  • Christina Lioma,
  • Hao Hu

摘要

Optical neural networks (ONNs) promise computing efficiency beyond microelectronics for modern artificial intelligence (AI). Current ONNs using analog matrix-vector multiplication (MVM) implementations are fundamentally limited in numerical precision due to accumulated noise in electro-optical processing. We propose a digital-analog hybrid MVM architecture that achieves a high numerical precision without sacrificing computing efficiency. Our fabricated proof-of-concept hybrid optical processor (HOP) achieves 16-bit precision in high-definition image processing, with a pixel error rate of 1.8 × 10−3 at a signal-to-noise ratio of 18.2 dB, and shows no accuracy loss in MNIST digit recognition. We further explore applying the HOP processor in You Look Only Once (YOLO) object detection and demonstrate sufficient numerical precision is crucial for high confidence detection in real-world neural networks. The hybrid optical computing concept may be applied to various photonic MVM implementations to enable accurate optical computing architectures.