Dual Optical Frequency Comb Neuron: Co-Developing Hardware and Algorithm,Advanced Intelligent Systems

当前位置： X-MOL 学术 › Adv. Intell. Syst. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Dual Optical Frequency Comb Neuron: Co-Developing Hardware and Algorithm
Advanced Intelligent Systems ( IF 6.8 ) Pub Date : 2023-03-16 , DOI: 10.1002/aisy.202200417
Jun Zhang _{1,

2} , Zilong Tao _{1,

2} , Qiuquan Yan _{1,

2} , Shiyin Du _{1,

2} , Yuhua Tang ₁ , Hengzhu Liu ₁ , Ke Wei _{1,

3} , Tong Zhou ₂ , Tian Jiang _{2,

3}

Affiliation

Previous studies on photonic neural network have demonstrated that algorithm can inspire hardware design. This study seeks to demonstrate that hardware can also inspire algorithm design. To further exploit the advantages of photonic analog computing, the authors develop hardware and algorithm simultaneously for photonic convolutional neural networks. Specifically, this work developed an architecture called dual optical frequency comb neuron (DOFCN) enabled by an integrated microcomb to perform cosinusoidal nonlinear activation and vector convolution without temporal or spatial dispersion and large-scale modulator arrays. Furthermore, DOFCN-based composite vector convolutional neural networks (CVCNNs), an optical-electric hybrid model, are proposed to perform classification and regression tests in signal modulation format identification and optical structure inverse design tasks, respectively. The ablation experiments show that under 4-bit precision limit, the element-wise activation CVCNN has 14% higher classification accuracy, 76% lower regression residuals, and 100% higher training efficiency than that of the 32-bit standard convolutional neural network (CNN). DOFCN exhibits impressive spectral information processing ability to facilitate signal-processing tasks related to optics and electromagnetics.

中文翻译：

双光频梳神经元：共同开发硬件和算法

先前对光子神经网络的研究表明，算法可以启发硬件设计。这项研究旨在证明硬件也可以激发算法设计。为了进一步发挥光子模拟计算的优势，作者同时开发了光子卷积神经网络的硬件和算法。具体来说，这项工作开发了一种称为双光学频率梳神经元（DOFCN）的架构，通过集成微梳实现余弦非线性激活和矢量卷积，而无需时间或空间色散和大规模调制器阵列。此外，基于 DOFCN 的复合矢量卷积神经网络（CVCNN）是一种光电混合模型，建议分别在信号调制格式识别和光学结构逆设计任务中进行分类和回归测试。消融实验表明，在4位精度限制下，逐元素激活CVCNN比32位标准卷积神经网络（CNN）分类精度提高14%，回归残差降低76%，训练效率提高100% ）。DOFCN 展现出令人印象深刻的光谱信息处理能力，可促进与光学和电磁学相关的信号处理任务。训练效率比32位标准卷积神经网络（CNN）提高100%。DOFCN 展现出令人印象深刻的光谱信息处理能力，可促进与光学和电磁学相关的信号处理任务。训练效率比32位标准卷积神经网络（CNN）提高100%。DOFCN 展现出令人印象深刻的光谱信息处理能力，可促进与光学和电磁学相关的信号处理任务。

更新日期：2023-03-16

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文