Hybrid quantum-classical convolutional neural networks
Hybrid quantum-classical convolutional neural networks
复制标题
混合量子经典卷积神经网络
DOI：
10.1007/s11433-021-1734-3
复制
发表时间：
2021-09-01
影响因子：
6.4
通讯作者：
Huang, He-Liang
中科院分区：
文献类型：
--
作者：
Liu, Junhua;Lim, Kwan Hui;Huang, He-Liang
深度学习已被证明能够在特定环境或背景下比人类更好地识别数据模式。并行地，量子计算已经证明能够通过少量的门操作输出复杂的波函数，这可以生成经典计算机难以产生的分布。在这里，我们提出了一种混合量子经典卷积神经网络（QCCNN），其灵感来自卷积神经网络（CNN），但适用于量子计算以增强特征映射过程。QCCNN在量子比特数量和电路深度方面对目前有噪声的中等规模量子计算机是友好的，同时保留了经典CNN的重要特征，如非线性和可扩展性。我们还提出了一个自动计算混合量子-经典损失函数梯度的框架，该框架可以直接应用于其他混合量子-经典算法。我们通过将其应用于俄罗斯方块数据集来展示这种架构的潜力，并表明QCCNN可以完成分类任务，其学习精度超过具有相同结构的经典CNN。
Deep learning has been shown to be able to recognize data patterns better than humans in specific circumstances or contexts. In parallel, quantum computing has demonstrated to be able to output complex wave functions with a few number of gate operations, which could generate distributions that are hard for a classical computer to produce. Here we propose a hybrid quantum-classical convolutional neural network (QCCNN), inspired by convolutional neural networks (CNNs) but adapted to quantum computing to enhance the feature mapping process. QCCNN is friendly to currently noisy intermediate-scale quantum computers, in terms of both number of qubits as well as circuit's depths, while retaining important features of classical CNN, such as nonlinearity and scalability. We also present a framework to automatically compute the gradients of hybrid quantum-classical loss functions which could be directly applied to other hybrid quantum-classical algorithms. We demonstrate the potential of this architecture by applying it to a Tetris dataset, and show that QCCNN can accomplish classification tasks with learning accuracy surpassing that of classical CNN with the same structure.