ITO-based electro-absorption modulator for photonic neural activation function
ITO-based electro-absorption modulator for photonic neural activation function
复制标题
DOI：
10.1063/1.5109039
复制
发表时间：
2019-08-01
期刊：
影响因子：
6.1
通讯作者：
Sorger, V. J.
中科院分区：
文献类型：
--
作者：
Amin, R.;George, J. K.;Sorger, V. J.
最近，集成光学已成为实现机器学习算法，特别是神经网络的功能平台。光子集成电路可以通过线性光学使用加权机制，直接以高效率和低功耗执行矢量矩阵乘法。然而，对于激活函数（即阈值）来说却不能这样说，它需要非线性光学或具有适当动态范围的电光模块。尽管全光非线性光学可能更快，但其当前的集成具有挑战性并且效率相当低。在这里，我们展示了一种基于单片集成到硅光子波导中的氧化铟锡层的电吸收调制器，其动态范围用作光子神经元的非线性激活函数。阈值机制基于光电二极管，该光电二极管集成了称重的产品，其光电压驱动电吸收调制器。然后构建突触和神经元电路来执行 200 节点 MNIST 分类神经网络，用于对非线性激活函数进行基准测试并与等效电子模块进行比较。 (c) 2019 年作者。除非另有说明，所有文章内容均根据知识共享署名 (CC BY) 许可证 (http://creativecommons.org/licenses/by/4.0/) 获得许可。
Recently, integrated optics has become a functional platform for implementing machine learning algorithms and, in particular, neural networks. Photonic integrated circuits can straightforwardly perform vector-matrix multiplications with high efficiency and low power consumption by using weighting mechanism through linear optics. However, this cannot be said for the activation function, i.e., threshold, which requires either nonlinear optics or an electro-optic module with an appropriate dynamic range. Even though all-optical nonlinear optics is potentially faster, its current integration is challenging and is rather inefficient. Here, we demonstrate an electroabsorption modulator based on an indium tin oxide layer monolithically integrated into silicon photonic waveguides, whose dynamic range is used as a nonlinear activation function of a photonic neuron. The thresholding mechanism is based on a photodiode, which integrates the weighed products, and whose photovoltage drives the electroabsorption modulator. The synapse and neuron circuit is then constructed to execute a 200-node MNIST classification neural network used for benchmarking the nonlinear activation function and compared with an equivalent electronic module. (c) 2019 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).