论文标题

现实世界,小和高维数据集的量子转移学习

Quantum Transfer Learning for Real-World, Small, and High-Dimensional Datasets

论文作者

Otgonbaatar, Soronzonbold, Schwarz, Gottfried, Datcu, Mihai, Kranzlmüller, Dieter

论文摘要

量子机学习(QML)网络有望通过其局部有效维度对某些常规深度学习(例如卫星图像)进行一些计算(或量子)优势,以对某些常规深度学习(例如卫星图像)进行分类(例如卫星图像)。但是,无论承诺的量子优势如何,都有两个主要挑战:1)当前可用的量子位(Qubits)的数量很小,而实际数据集则以数百个高维元素(即功能)为特征。此外,没有一种统一的方法将实际高维数据集嵌入有限数量的Qubits中。 2)一些现实世界数据集太小,无法训练复杂的QML网络。因此,为了解决这两个挑战,用于对现实世界,小和高维数据集进行基准测试和验证QML网络,我们采用了量子转移学习,由多QML QML网络组成,由多QML QML网络以及一个非常深的卷积网络(一种具有VGG16的非常深的卷积网络)(一种带有VGG16的体系结构)从任何小型高含量数据中提取信息性特征。我们使用有或没有数据重新上传层作为多QML网络的实时振幅和强烈的n层QML网络,并通过使用其局部有效维度来评估其表达能力; QML网络的局部有效维度越低,其在看不见的数据上的性能就越好。我们的数值结果表明,强烈输入的N层QML网络的局部有效维度低于实幅度QML网络,并且在难以分类的三类标签问题上表现优于它。此外,量子转移学习有助于解决上述两个挑战,以基准和验证现实世界,小和高维数据集的QML网络。

Quantum machine learning (QML) networks promise to have some computational (or quantum) advantage for classifying supervised datasets (e.g., satellite images) over some conventional deep learning (DL) techniques due to their expressive power via their local effective dimension. There are, however, two main challenges regardless of the promised quantum advantage: 1) Currently available quantum bits (qubits) are very small in number, while real-world datasets are characterized by hundreds of high-dimensional elements (i.e., features). Additionally, there is not a single unified approach for embedding real-world high-dimensional datasets in a limited number of qubits. 2) Some real-world datasets are too small for training intricate QML networks. Hence, to tackle these two challenges for benchmarking and validating QML networks on real-world, small, and high-dimensional datasets in one-go, we employ quantum transfer learning composed of a multi-qubit QML network, and a very deep convolutional network (a with VGG16 architecture) extracting informative features from any small, high-dimensional dataset. We use real-amplitude and strongly-entangling N-layer QML networks with and without data re-uploading layers as a multi-qubit QML network, and evaluate their expressive power quantified by using their local effective dimension; the lower the local effective dimension of a QML network, the better its performance on unseen data. Our numerical results show that the strongly-entangling N-layer QML network has a lower local effective dimension than the real-amplitude QML network and outperforms it on the hard-to-classify three-class labelling problem. In addition, quantum transfer learning helps tackle the two challenges mentioned above for benchmarking and validating QML networks on real-world, small, and high-dimensional datasets.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源