.png){kind=icon}
返回
Advanced Image Classification Using a Differential Diffractive Network with Learned Structured Illumination
.png){kind=icon}
PRE
AI
DOI：10.1021/acsphotonics.4c01511.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As a new optical machine learning framework, the diffractive deep neural network (D2NN) has attracted much attention due to its advantages such as low power consumption, parallel computing, and fast execution speed. Here, we demonstrate a new optical neural network design of a differential D2NN with structured illumination. In this scheme, the illumination patterns participate in the training process of the network and are optimized by an end-to-end technique. With the application of differential detection, the non-negativity constraint in a diffractive neural network can be alleviated. The test results show that this network architecture can achieve 97.63 and 88.10% classification accuracies on the MNIST and Fashion-MNIST data sets using only one diffractive layer, which exceeds the effect achieved by the five-layer traditional D2NN. Moreover, this network architecture can achieve a comprehensive improvement over a traditional D2NN in the challenging classification problems of tiny samples and samples blocked by occlusions. Compared with the traditional D2NN, this scheme innovatively uses the illumination patterns as new degrees of freedom in system design, which can effectively improve classification ability and reduce the space complexity of the optical neural network.
Keyword:
optical computing
optical machine learning
optical neural network
diffractive deep neural network
optical information processing
期刊
IF:
6.7
论文数:
5.6K
被引数:
2.5W
机构
引用论文
Training large-scale optoelectronic neural networks with dual-neuron optical-artificial learning.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏To image, or not to image: class-specific diffractive cameras with all-optical erasure of undesired objects成像或不成像: 特定类别的衍射相机，可对不需要的物体进行全光学擦除ELIGHT
OAAI
ELIGHTIF32.1
OAAI分享收藏Computational imaging without a computer: seeing through random diffusers at the speed of lightELIGHTOAAI
ELIGHTIF32.1
OAAI分享收藏Training of photonic neural networks through in situ backpropagation and gradient measurement通过原位反向传播和梯度测量训练光子神经网络OPTICAOAAI
OPTICAIF8.5
OAAI分享收藏
查看更多内容