Design of a silicon-based optical neural network
D Zhang, P Wang, G Luo, Y Bi, Y Zhang… - 2019 2nd …, 2019 - atlantis-press.com
2019 2nd International Conference on Mathematics, Modeling and …, 2019•atlantis-press.com
In this paper, a silicon-based fully connected optical neural network (ONN) is designed,
which can be use to image classification and recognition with accuracy greater than 97%. A
fully connected neural network is constructed. One layer model has been used in chip
design. Chip simulation shows accuracy could not be impacted as photons large enough.
This structure could be used in deep learning.
which can be use to image classification and recognition with accuracy greater than 97%. A
fully connected neural network is constructed. One layer model has been used in chip
design. Chip simulation shows accuracy could not be impacted as photons large enough.
This structure could be used in deep learning.
Abstract
In this paper, a silicon-based fully connected optical neural network (ONN) is designed, which can be use to image classification and recognition with accuracy greater than 97%. A fully connected neural network is constructed. One layer model has been used in chip design. Chip simulation shows accuracy could not be impacted as photons large enough. This structure could be used in deep learning.
atlantis-press.com
以上显示的是最相近的搜索结果。 查看全部搜索结果