.png){kind=icon}
返回
Recurrent diffractive deep neural networks
.png){kind=icon}
OA
AI
DOI：10.1364/OE.544350.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
What we believe is a novel recurrent diffractive deep neural network (RD2NN) is proposed for image time division multiplexing and frequency division multiplexing. The RD2NN is formed by a diffractive deep neural network (D2NN) with its output connected backward to the input. Therefore, it enables the signals to be generated sequentially in the time domain. By precoding the images via the inverse Fourier transform (IFT), one may also realize frequency division multiplexed images. To train the RD2NN, a modified optical real-time back-propagation (BP) algorithm is proposed, which expands the RD2NN into sequential D2NNs with identical phase configurations. The temporal output images of the previous stage D2NN are used as the input image for the next stage D2NN during the training. Five consecutive images are generated either in the time domain or in the frequency domain with a 7-layer trained RD2NN.
期刊
IF:
3.3
论文数:
6.1W
被引数:
14.3W
机构
引用论文
Computational imaging without a computer: seeing through random diffusers at the speed of light.png)
ELIGHTOAAI
ELIGHTIF32.1
OAAI分享收藏Artificial Bee Colony Algorithm for Economic Load Dispatch Problem with Non-smooth Cost Functions非平稳成本函数经济负荷分配问题的人工蜂群算法
PREAI
分享收藏From glioblastoma to endothelial cells through extracellular vesicles: messages for angiogenesis
PREAI
分享收藏Reinforcement learning in a large-scale photonic recurrent neural network大规模光子递归神经网络中的强化学习OPTICA
OAAI
OPTICAIF8.5
OAAI分享收藏Space-efficient optical computing with an integrated chip diffractive neural network集成芯片衍射神经网络的空间高效光学计算NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏In situ optical backpropagation training of diffractive optical neural networks衍射光学神经网络的原位光学反向传播训练PHOTONICS RESEARCH
PHOTONICS RESEARCHIF7.2
PREAI
分享收藏
查看更多内容