.png){kind=icon}
返回
Optical random phase dropout in a diffractive deep neural network
.png){kind=icon}
OA
AI
DOI：10.1364/OL.428761.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Unitary learning is a backpropagation (BP) method that serves to update unitary weights in fully connected deep complex-valued neural networks, meeting a prior unitary in an active modulation diffractive deep neural network. However, the square matrix characteristic of unitary weights in each layer results in its learning belonging to a small-sample training, which produces an almost useless network that has a fairly poor generalization capability. To alleviate such a serious over-fitting problem, in this Letter, optical random phase dropout is formulated and designed. The equivalence between unitary forward and diffractive networks deduces a synthetic mask that is seamlessly compounded with a computational modulation and a random sampling comb called dropout. The dropout is filled with random phases in its zero positions that satisfy the Bernoulli distribution, which could slightly deflect parts of transmitted optical rays in each output end to generate statistical inference networks. The enhancement of generalization benefits from the fact that massively parallel full connection with different optical links is involved in the training. The random phase comb introduced into unitary BP is in the form of conjugation, which indicates the significance of optical BP. (C) 2021 Optical Society of America
Keyword:
BACKPROPAGATION
OPTIMIZATION
期刊
IF:
3.3
论文数:
4.0W
被引数:
7.6W
机构
引用论文
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.png)
OPTICA
OAAI
OPTICAIF8.5
OAAI分享收藏From glioblastoma to endothelial cells through extracellular vesicles: messages for angiogenesis
PREAI
分享收藏Backpropagation through nonlinear units for the all-optical training of neural networksPHOTONICS RESEARCHOAAI
PHOTONICS RESEARCHIF7.2
OAAI分享收藏
查看更多内容