.png){kind=icon}
返回
Optical multi-imaging-casting accelerator for fully parallel universal convolution computing
.png){kind=icon}
OA
AI
DOI：10.1364/PRJ.472741.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, optical computing has emerged as a potential solution to computationally heavy convolution, aiming at accelerating various large science and engineering tasks. Based on optical multi-imaging-casting architecture, we propose a paradigm for a universal optical convolutional accelerator with truly massive parallelism and high precision. A two-dimensional Dammann grating is the key element for generating multiple displaced images of the kernel, which is the core process for kernel sliding on the convolved matrix in optical convolutional ar-chitecture. Our experimental results indicate that the computing accuracy is typically about 8 bits, and this ac-curacy could be improved further if high-contrast modulators are used. Moreover, a hybrid analog-digital coding method is demonstrated to improve computing accuracy. Additionally, a convolutional neural network for the standard MNIST dataset is demonstrated, with recognition accuracy for inference reaching 97.3%. Since this architecture could function under incoherent light illumination, this scheme will provide opportunities for han-dling white-light images directly from lenses without photoelectric conversion, in addition to convolutional accelerators. (c) 2023 Chinese Laser Press
Keyword:
MULTIPLICATION
NETWORKS
期刊
IF:
7.2
论文数:
2.4K
被引数:
1.3W
机构
引用论文
The cathodic behavior of microwave-treated manganese dioxide in lithium nonaqueous cells微波处理的二氧化锰在非水锂电池中的阴极行为
PREAI
分享收藏Photonics for artificial intelligence and neuromorphic computing用于人工智能和神经形态计算的光子学.png)
NATURE PHOTONICS
OAAI
NATURE PHOTONICSIF32.9
OAAI分享收藏分享收藏
查看更多内容