Optimization of optical convolution kernel of optoelectronic hybrid convolution neural network

Xiaofeng Xu , Lianqing Zhu , Wei Zhuang , Dongliang Zhang , Lidan Lu , Pei Yuan

Optoelectronics Letters ›› 2022, Vol. 18 ›› Issue (3) : 181 -186.

PDF
Optoelectronics Letters ›› 2022, Vol. 18 ›› Issue (3) : 181 -186. DOI: 10.1007/s11801-022-1183-x
Article

Optimization of optical convolution kernel of optoelectronic hybrid convolution neural network

Author information +
History +
PDF

Abstract

To enhance the optical computation’s utilization efficiency, we develop an optimization method for optical convolution kernel in the optoelectronic hybrid convolution neural network (OHCNN). To comply with the actual calculation process, the convolution kernel is expanded from single-channel to two-channel, containing positive and negative weights. The Fashion-MNIST dataset is used to test the network architecture’s accuracy, and the accuracy is improved by 7.5% with the optimized optical convolution kernel. The energy efficiency ratio (EER) of two-channel network is 46.7% higher than that of the single-channel network, and it is 2.53 times of that of traditional electronic products.

Cite this article

Download citation ▾
Xiaofeng Xu, Lianqing Zhu, Wei Zhuang, Dongliang Zhang, Lidan Lu, Pei Yuan. Optimization of optical convolution kernel of optoelectronic hybrid convolution neural network. Optoelectronics Letters, 2022, 18(3): 181-186 DOI:10.1007/s11801-022-1183-x

登录浏览全文

4963

注册一个新账户 忘记密码

References

AI Summary AI Mindmap
PDF

133

Accesses

0

Citation

Detail

Sections
Recommended

AI思维导图

/