当前位置:
X-MOL 学术
›
arXiv.cs.ET
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Photonic single perceptron at Giga-OP/s speeds with Kerr microcombs for scalable optical neural networks
arXiv - CS - Emerging Technologies Pub Date : 2021-05-12 , DOI: arxiv-2105.10407 Mengxi Tan, Xingyuan Xu, David J. Moss
arXiv - CS - Emerging Technologies Pub Date : 2021-05-12 , DOI: arxiv-2105.10407 Mengxi Tan, Xingyuan Xu, David J. Moss
Optical artificial neural networks (ONNs) have significant potential for
ultra-high computing speed and energy efficiency. We report a novel approach to
ONNs that uses integrated Kerr optical microcombs. This approach is
programmable and scalable and is capable of reaching ultrahigh speeds. We
demonstrate the basic building block ONNs, a single neuron perceptron, by
mapping synapses onto 49 wavelengths to achieve an operating speed of 11.9 x
109 operations per second, or GigaOPS, at 8 bits per operation, which equates
to 95.2 gigabits/s (Gbps). We test the perceptron on handwritten digit
recognition and cancer cell detection, achieving over 90% and 85% accuracy,
respectively. By scaling the perceptron to a deep learning network using off
the shelf telecom technology we can achieve high throughput operation for
matrix multiplication for real-time massive data processing.
中文翻译:
带有Kerr微梳的Giga-OP / s速度的光子单感知器,用于可扩展的光学神经网络
光学人工神经网络(ONN)具有超高的计算速度和能源效率的巨大潜力。我们报告了一种使用集成的Kerr光学微梳的新颖方法。这种方法是可编程的和可扩展的,并且能够达到超高速。我们通过将突触映射到49个波长上以实现每秒11.9 x 109次操作或GigaOPS的操作速度(每次操作8位),相当于95.2吉比特/秒(Gbps),展示了基本的神经元ONN,即单个神经元感知器)。我们在手写数字识别和癌细胞检测上测试感知器,分别达到90%和85%以上的准确性。
更新日期:2021-05-24
中文翻译:
带有Kerr微梳的Giga-OP / s速度的光子单感知器,用于可扩展的光学神经网络
光学人工神经网络(ONN)具有超高的计算速度和能源效率的巨大潜力。我们报告了一种使用集成的Kerr光学微梳的新颖方法。这种方法是可编程的和可扩展的,并且能够达到超高速。我们通过将突触映射到49个波长上以实现每秒11.9 x 109次操作或GigaOPS的操作速度(每次操作8位),相当于95.2吉比特/秒(Gbps),展示了基本的神经元ONN,即单个神经元感知器)。我们在手写数字识别和癌细胞检测上测试感知器,分别达到90%和85%以上的准确性。