Graphene/silicon heterojunction for reconfigurable phase-relevant activation function in coherent optical neural networks.
Graphene/silicon heterojunction for reconfigurable phase-relevant activation function in coherent optical neural networks.
复制标题
DOI：
10.1038/s41467-023-42116-6
复制
发表时间：
2023-10-31
影响因子：
16.6
通讯作者：
Lin, Hongtao
中科院分区：
文献类型：
--
作者：
Zhong, Chuyu;Liao, Kun;Dai, Tianxiang;Wei, Maoliang;Ma, Hui;Wu, Jianghong;Zhang, Zhibin;Ye, Yuting;Luo, Ye;Chen, Zequn;Jian, Jialing;Sun, Chunlei;Tang, Bo;Zhang, Peng;Liu, Ruonan;Li, Junying;Yang, Jianyi;Li, Lan;Liu, Kaihui;Hu, Xiaoyong;Lin, Hongtao
光神经网络（ONNs）预示着信息通信技术的新时代，并实现了各种智能应用。在ONN中，激活函数（AF）是决定网络性能的关键组件，片上AF设备仍在开发中。在这里，我们首先展示了片上可重构AF器件，其相位激活由双功能石墨烯/硅（Gra/Si）异质结实现。与其他片上自动对焦策略相比，光调制和检测在一个器件中，时间延迟更短，能耗更低，可重构性更高，器件占地面积更小。我们的Gra/Si异质结的实验调制电压（功率）低至1 V (0.5 mW)，优于许多纯硅异质结。在光探测方面，实现了200 mA/W以上的高响应。将生成的特殊非线性函数输入到复杂值的ONN中，以挑战手写字母和图像识别任务，显示出高效率、全组件集成的片上ONN的准确性和潜力。我们的研究结果为片上ONN器件提供了新的见解，并为高性能集成光电计算电路铺平了道路。设计一个有效的光神经网络激活函数仍然是一个挑战。在这里，作者展示了一种集调制器-探测器于一体的石墨烯/硅异质结环形谐振器，使片上可重构激活函数器件具有用于光学神经网络的相位激活能力。
Optical neural networks (ONNs) herald a new era in information and communication technologies and have implemented various intelligent applications. In an ONN, the activation function (AF) is a crucial component determining the network performances and on-chip AF devices are still in development. Here, we first demonstrate on-chip reconfigurable AF devices with phase activation fulfilled by dual-functional graphene/silicon (Gra/Si) heterojunctions. With optical modulation and detection in one device, time delays are shorter, energy consumption is lower, reconfigurability is higher and the device footprint is smaller than other on-chip AF strategies. The experimental modulation voltage (power) of our Gra/Si heterojunction achieves as low as 1 V (0.5 mW), superior to many pure silicon counterparts. In the photodetection aspect, a high responsivity of over 200 mA/W is realized. Special nonlinear functions generated are fed into a complex-valued ONN to challenge handwritten letters and image recognition tasks, showing improved accuracy and potential of high-efficient, all-component-integration on-chip ONN. Our results offer new insights for on-chip ONN devices and pave the way to high-performance integrated optoelectronic computing circuits. Designing an efficient activation function for optical neural networks remains a challenge. Here, the authors demonstrate a modulator-detector-in-one graphene/silicon heterojunction ring resonators enabling on-chip reconfigurable activation function devices with phase activation capability for optical neural networks.
登录
查看更多内容
影响因子：
1.7
作者：
Chen Hongwei;Yu Zhenming;Xu Kun
通讯作者：
Xu Kun
具有实虚型激活函数的复值循环神经网络的多稳定性
影响因子：
4
作者：
Huang, Yujiao;Zhang, Huaguang;Wang, Zhanshan
通讯作者：
Wang, Zhanshan
影响因子：
16.6
作者：
Feldmann J;Stegmaier M;Gruhler N;Ríos C;Bhaskaran H;Wright CD;Pernice WHP
通讯作者：
Pernice WHP
影响因子：
7
作者：
Casalino, Maurizio;Russo, Roberto;Coppola, Giuseppe
通讯作者：
Coppola, Giuseppe
影响因子：
64.8
作者：
Ashtiani, Farshid;Geers, Alexander J.;Aflatouni, Firooz
通讯作者：
Aflatouni, Firooz