.png){kind=icon}
返回
Sophisticated deep learning with on-chip optical diffractive tensor processing
.png){kind=icon}
OA
AI
DOI：10.1364/PRJ.484662.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Ever-growing deep-learning technologies are making revolutionary changes for modern life. However, conventional computing architectures are designed to process sequential and digital programs but are burdened with performing massive parallel and adaptive deep-learning applications. Photonic integrated circuits provide an efficient approach to mitigate bandwidth limitations and the power-wall brought on by its electronic counterparts, showing great potential in ultrafast and energy-free high-performance computation. Here, we propose an optical computing ar-chitecture enabled by on-chip diffraction to implement convolutional acceleration, termed optical convolution unit (OCU). We demonstrate that any real-valued convolution kernels can be exploited by the OCU with a promi-nent computational throughput boosting via the concept of structral reparameterization. With the OCU as the fundamental unit, we build an optical convolutional neural network (oCNN) to implement two popular deep learn-ing tasks: classification and regression. For classification, Fashion Modified National Institute of Standards and Technology (Fashion-MNIST) and Canadian Institute for Advanced Research (CIFAR-4) data sets are tested with accuracies of 91.63% and 86.25%, respectively. For regression, we build an optical denoising convolutional neural network to handle Gaussian noise in gray-scale images with noise level & sigma; = 10,15, and 20, resulting in clean images with an average peak signal-to-noise ratio (PSNR) of 31.70, 29.39, and 27.72 dB, respectively. The proposed OCU presents remarkable performance of low energy consumption and high information density due to its fully passive nature and compact footprint, providing a parallel while lightweight solution for future compute-in-memory architecture to handle high dimensional tensors in deep learning. & COPY; 2023 Chinese Laser Press
Keyword:
ARTIFICIAL-INTELLIGENCE
SWITCH
PHOTONICS
NETWORKS
COMPACT
POWER
GEMM
期刊
IF:
7.2
论文数:
2.4K
被引数:
1.3W
机构
引用论文
分享收藏True fractional calcium absorption in Chinese children measured with stable isotopes (42Ca and44Ca)
OAAI
OAAI分享收藏分享收藏Programmable matrix operation with reconfigurable time-wavelength plane manipulation and dispersed time delay.png)
OPTICS EXPRESSOAAI
OPTICS EXPRESSIF3.3
OAAI分享收藏
查看更多内容