Quanvolutional neural networks: powering image recognition with quantum circuits
Quanvolutional neural networks: powering image recognition with quantum circuits
复制标题
DOI：
10.1007/s42484-020-00012-y
复制
发表时间：
2020-06-01
影响因子：
4.8
通讯作者：
Cook, Tristan
中科院分区：
文献类型：
--
作者：
Henderson, Maxwell;Shakya, Samriddhi;Cook, Tristan
卷积神经网络（CNN）在许多机器学习应用中迅速普及，特别是在图像识别领域。这些网络产生的大部分好处来自于它们以分层方式从数据中提取特征的能力。这些特征是使用各种转换层提取的，特别是卷积层，它为模型命名。在这项工作中，我们引入了一种新型的转换层，称为量子卷积，或quanvolutional层。量子卷积层通过使用多个随机量子电路对数据进行局部变换来对输入数据进行操作，其方式类似于由随机卷积滤波器层执行的变换。如果这些量子变换产生了有意义的特征用于分类目的，那么这种算法可能对近期的量子计算机有实际用途，因为它需要很少或没有纠错的小量子电路。在这项工作中，我们通过比较在MNIST数据集上构建的三种类型的模型来经验性地评估这些量子变换的潜在好处：CNN，量子卷积神经网络（QNN）和引入额外非线性的CNN。我们的研究结果表明，与纯经典CNN相比，QNN模型具有更高的测试集精度和更快的训练速度。
Convolutional neural networks (CNNs) have rapidly risen in popularity for many machine learning applications, particularly in the field of image recognition. Much of the benefit generated from these networks comes from their ability to extract features from the data in a hierarchical manner. These features are extracted using various transformational layers, notably the convolutional layer which gives the model its name. In this work, we introduce a new type of transformational layer called a quantum convolution, or quanvolutional layer. Quanvolutional layers operate on input data by locally transforming the data using a number of random quantum circuits, in a way that is similar to the transformations performed by random convolutional filter layers. Provided these quantum transformations produce meaningful features for classification purposes, then this algorithm could be of practical use for near-term quantum computers as it requires small quantum circuits with little to no error correction. In this work, we empirically evaluated the potential benefit of these quantum transformations by comparing three types of models built on the MNIST dataset: CNNs, quantum convolutional neural networks (QNNs), and CNNs with additional non-linearities introduced. Our results showed that the QNN models had both higher test set accuracy as well as faster training compared with the purely classical CNNs.