.png){kind=icon}
返回
Broad-spectrum diffractive network via ensemble learning
.png){kind=icon}
OA
AI
DOI：10.1364/OL.440421.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We propose a broad-spectrum diffractive deep neural network (BS-(DNN)-N-2) framework, which incorporates multiwavelength channels of input lightfields and performs a parallel phase-only modulation using a layered passive mask architecture. A complementary multichannel base learner cluster is formed in a homogeneous ensemble framework based on the diffractive dispersion during lightwave modulation. In addition, both the optical sum operation and the hybrid (optical-electronic) maxout operation are performed for motivating the BS-(DNN)-N-2 to learn and construct a mapping between input lightfields and truth labels under heterochromatic ambient lighting. The BS-(DNN)-N-2 can be trained using deep learning algorithms to perform a kind of wavelength-insensitive high-accuracy object classification. (C) 2022 Optical Society of America
期刊
IF:
3.3
论文数:
4.0W
被引数:
7.6W
机构
暂无机构信息
引用论文
Residual D2NN: training diffractive deep neural networks via learnable light shortcuts残差D2NN: 通过可学习的光捷径训练衍射深度神经网络.png)
OPTICS LETTERS
OPTICS LETTERSIF3.3
PREAI
分享收藏Anti-noise diffractive neural network for constructing an intelligent imaging detector arrayOPTICS EXPRESSOAAI
OPTICS EXPRESSIF3.3
OAAI分享收藏分享收藏分享收藏From glioblastoma to endothelial cells through extracellular vesicles: messages for angiogenesis
PREAI
分享收藏Robust light beam diffractive shaping based on a kind of compact all-optical neural network基于一种紧凑型全光神经网络的鲁棒光束衍射整形OPTICS EXPRESSOAAI
OPTICS EXPRESSIF3.3
OAAI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
查看更多内容