Implementation of optical neural network based on Mach–Zehnder interferometer array,IET Optoelectronics

当前位置： X-MOL 学术 › IET Optoelectron. › 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.)

Implementation of optical neural network based on Mach–Zehnder interferometer array
IET Optoelectronics ( IF 2.3 ) Pub Date : 2022-11-23 , DOI: 10.1049/ote2.12086
Yanan Du _{1,

2,

3,

4} , Kang Su _{1,

2,

3,

4} , Xinxin Yuan _{1,

2,

3,

4} , Tuo Li _{1,

2,

3,

4} , Kai Liu _{1,

2,

3,

4} , Hongtao Man _{1,

2,

3,

4} , Xiaofeng Zou _{1,

2,

3,

4}

Affiliation

Compared with electrons, photons have the potential to realise ultra-high speed operations because of its unique high speed and high parallelism. In recent years, there have been many researches on neural networks using optical hardware. The Mach–Zehnder interferometer (MZI) and micro-ring resonator (MRR) are commonly used as optical devices to realise linear operation units in optical neural networks (ONN). MZI has the advantages of simple fabrication, high sensitivity, and easy integration, which has attracted the attention of researchers. We summarise the implementation methods of ONN matrix multiplication based on MZI, the implementation methods of non-linear activation, and the on-chip training methods. We first summarise the researches on matrix multiplication of ONN based on MZI. Three kinds of MZI grid decomposition methods, Fast Fourier Transform (FFT) grid structures, and the corresponding derivation processes are introduced, respectively. Then, several experimental implementations of ONN based on MZI are summarised, and the characteristics of optical processors fabricated in these references are analysed. Finally, the realisation methods of non-linear activation and on-chip training of silicon ONN are introduced, respectively.

中文翻译：

基于Mach-Zehnder干涉仪阵列的光学神经网络实现

与电子相比，光子因其独特的高速和高并行性，具有实现超高速运算的潜力。近年来，已经有很多关于使用光学硬件的神经网络的研究。Mach-Zehnder 干涉仪 (MZI) 和微环形谐振器 (MRR) 通常用作光学器件，以实现光学神经网络 (ONN) 中的线性运算单元。MZI具有制作简单、灵敏度高、易于集成等优点，受到了研究人员的关注。我们总结了基于MZI的ONN矩阵乘法的实现方法，非线性激活的实现方法，片上训练方法。我们首先总结了基于MZI的ONN矩阵乘法的研究。三种MZI网格分解方法，分别介绍了快速傅立叶变换（FFT）网格结构，以及相应的推导过程。然后，总结了几种基于 MZI 的 ONN 实验实现，并分析了这些参考文献中制造的光处理器的特性。最后分别介绍了硅ONN非线性激活和片上训练的实现方法。

更新日期：2022-11-23

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南