Quantum Machine Learning
Quantum Machine Learning
复制标题
DOI：
10.1007/978-1-4842-6522-2_5
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
M. Schuld;Francesco Petruccione
中科院分区：
文献类型：
--
作者：
M. Schuld;Francesco Petruccione
在本章和下一章中，我们将探索量子机器学习和量子深度学习的令人兴奋的领域。机器学习和深度学习近年来取得了巨大的成功，这是因为我们可以使用的计算能力的增加，以及这些领域的高端研究。量子机器学习为提高现有机器学习算法的计算效率提供了一个令人兴奋的机会，也为解决一些计算上更棘手的问题提供了一种方法。在本章中，我们从Harrow-Hassidim-Lloyd算法开始，它通常被称为HHL，它在量子计算领域中充当矩阵反演例程。因此，HHL将是线性回归和最小二乘支持向量机等算法的默认选择。随后，我们将在本章中详细讨论量子线性回归和支持向量机。然后，我们将继续实现量子例程，如量子点积和量子欧几里得距离，因为它们是若干机器学习算法（如k-means聚类和最近邻方法）的组成部分。对此，我们将详细实现k-means聚类方法。此外，我们将通过说明Grover算法在k-means算法中的簇分配中的使用来讨论如何使用Grover算法来优化量子目标。主成分分析是一种重要的机器学习技术，我们将非常详细地介绍它的量子实现。
In this chapter and the next one, we will explore the exciting areas of quantum machine learning and quantum deep learning. Machine learning and deep learning have seen great success in recent years because of the increase in the computational power at our disposal and because of the high-end research in these fields. Quantum machine learning presents an exciting opportunity to increase the computational efficiency of the existing machine learning algorithms as well as presents a way to tackle some of the more computationally intractable problems. In this chapter, we start with the Harrow-Hassidim-Lloyd algorithm, popularly known as HHL, which acts as the matrix inversion routine in the quantum computing domain. Hence, HHL will be the default choice for algorithms such as linear regression and least square support vector machines. Subsequently, we touch upon quantum linear regression and support vector machines in detail in this chapter. We will then move on to implementing quantum routines such as quantum dot product and quantum Euclidean distances since they are integral to several machine learning algorithms such as the k-means clustering and nearest neighbor methods. In this regard, we will implement the k-means clustering method in detail. Also, we will discuss how Grover’s algorithm can be used to optimize quantum objectives by illustrating its usage in the cluster assignment in the k-means algorithm. Principal component analysis is an important machine learning technique, and we will walk through its quantum implementation in great detail as well.