Time-Delayed Reservoir Computing Based on a Two-Element Phased Laser Array for Image Identification
Time-Delayed Reservoir Computing Based on a Two-Element Phased Laser Array for Image Identification
复制标题
DOI：
10.1109/jphot.2021.3115598
复制
发表时间：
2021-10-01
影响因子：
2.4
通讯作者：
Li, Nianqiang
中科院分区：
文献类型：
--
作者：
Huang, Yu;Zhou, Pei;Li, Nianqiang
我们报告了一个简单的方法，时间延迟油藏计算（RC）的基础上的二元激光相控阵图像识别。在这里，与光反馈和注入相控激光阵列的训练，根据通过定向梯度直方图提取的代表性特征。这些特征向量乘以随机掩码信号以形成输入数据，该输入数据随后在库中被训练。通过优化RC的参数，我们实现了97.44%的MNIST数据集和85.46%的Fashion-MNIST数据集上的识别准确率。这些结果表明，我们提出的RC确实可以准确的分类手写数字和时尚生产。此外，我们还预测了一种基于更大规模的激光相控阵的RC方案，该方案有望以更高的速度处理更复杂的任务。我们的工作提供了一种可能性，先进的图像处理使用高度集成的神经形态光子系统。
We report on a simple approach of time-delayed reservoir computing (RC) based on a two-element phased laser array for image identification. Here the phased laser array with optical feedback and injection is trained according to the representative characteristics extracted through histograms of oriented gradients. These characteristic vectors are multiplied by a random mask signal to form input data, which are subsequently trained in the reservoir. By optimizing the parameters of the RC, we achieve an identification accuracy of 97.44% on the MNIST dataset and 85.46% on the Fashion-MNIST dataset. These results indicate that our proposed RC indeed allows accurate classification of handwritten digit and fashion production. Moreover, we further forecast an RC scheme based on a larger-scale phased laser array, which is expected to tackle more complex tasks at a high speed. Our work offers a possibility for advanced image processing using highly integrated neuromorphic photonic systems.