Sun Yifan, Li Qian, Kong Ling-Jun, Zhang Xiangdong
Key Laboratory of advanced optoelectronic quantum architecture and measurements of Ministry of Education, Beijing Key Laboratory of Nanophotonics & Ultrafine Optoelectronic Systems, School of Physics, Beijing Institute of Technology, 100081, Beijing, China.
Light Sci Appl. 2024 Jan 31;13(1):36. doi: 10.1038/s41377-024-01376-7.
Compared with electrical neural networks, optical neural networks (ONNs) have the potentials to break the limit of the bandwidth and reduce the consumption of energy, and therefore draw much attention in recent years. By far, several types of ONNs have been implemented. However, the current ONNs cannot realize the acceleration as powerful as that indicated by the models like quantum neural networks. How to construct and realize an ONN with the quantum speedup is a huge challenge. Here, we propose theoretically and demonstrate experimentally a new type of optical convolutional neural network by introducing the optical correlation. It is called the correlated optical convolutional neural network (COCNN). We show that the COCNN can exhibit "quantum speedup" in the training process. The character is verified from the two aspects. One is the direct illustration of the faster convergence by comparing the loss function curves of the COCNN with that of the traditional convolutional neural network (CNN). Such a result is compatible with the training performance of the recently proposed quantum convolutional neural network (QCNN). The other is the demonstration of the COCNN's capability to perform the QCNN phase recognition circuit, validating the connection between the COCNN and the QCNN. Furthermore, we take the COCNN analog to the 3-qubit QCNN phase recognition circuit as an example and perform an experiment to show the soundness and the feasibility of it. The results perfectly match the theoretical calculations. Our proposal opens up a new avenue for realizing the ONNs with the quantum speedup, which will benefit the information processing in the era of big data.
与电子神经网络相比，光学神经网络（ONNs）有潜力突破带宽限制并降低能耗，因此近年来备受关注。到目前为止，已经实现了几种类型的ONNs。然而，当前的ONNs无法实现像量子神经网络等模型所显示的那样强大的加速。如何构建并实现具有量子加速的ONN是一个巨大的挑战。在此，我们通过引入光学相关性在理论上提出并在实验上证明了一种新型的光学卷积神经网络。它被称为相关光学卷积神经网络（COCNN）。我们表明，COCNN在训练过程中可以展现出“量子加速”。这一特性从两个方面得到了验证。一方面，通过比较COCNN与传统卷积神经网络（CNN）的损失函数曲线，直接说明了更快的收敛性。这样的结果与最近提出的量子卷积神经网络（QCNN）的训练性能相契合。另一方面，展示了COCNN执行QCNN相位识别电路的能力，验证了COCNN与QCNN之间的联系。此外，我们以将COCNN模拟为3量子比特QCNN相位识别电路为例进行实验，以展示其合理性和可行性。结果与理论计算完美匹配。我们的提议为实现具有量子加速的ONNs开辟了一条新途径，这将有益于大数据时代的信息处理。
