.png){kind=icon}
返回
Unitary learning for diffractive deep neural network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.optlaseng.2020.106499.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Realization of deep learning with coherent diffraction has achieved remarkable development nowadays, which benefits on the fact that matrix multiplication can be optically executed in parallel with high band-with and low latency. Coherent optical field in the form of complex-valued entity can be manipulated into a task-oriented output. In this paper, a modulation mechanism is established by implementing the equivalence between a digital deep unitary neural network and optical coherent diffraction. We present a unitary learning avenue on diffractive deep neural network, meeting the physical unitary prior in coherent diffraction. The Unitary learning is a Backpropagation serving to unitary weights update through the gradient translation from Euclidean to Riemannian space. The temporal-space evolution characteristics in unitary learning are formulated and elucidated. And a compatible condition on how to select the nonlinear activation in complex space is unveiled, encapsulating the fundamental sigmoid, tanh and quasi-ReLu in complex space available in a single channel training. The performance of phase-ReLu is particularly emphasized. As a preliminary application, diffractive deep neural network with unitary learning is tentatively implemented on the 2D classification and verification tasks.
Keyword:
Artificial intelligence
Fourier optics
Unitary learning
Compatible condition
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.7
论文数:
7.3K
被引数:
1.7W
机构
引用论文
Roadmap on material-function mapping for photonic-electronic hybrid neural networks.png)
APL MATERIALS
OAAI
APL MATERIALSIF4.5
OAAI分享收藏Generalization Characteristics of Complex-Valued Feedforward Neural Networks in Relation to Signal Coherence与信号相干相关的复值前馈神经网络的泛化特性
PREAI
分享收藏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OPTICS LETTERS
OPTICS LETTERSIF3.3
PREAI
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