Experimental Realization of a Quantum Support Vector Machine

Abstract

The fundamental principle of artificial intelligence is the ability of machines to learn from previous experience and do future work accordingly. In the age of big data, classical learning machines often require huge computational resources in many practical cases. Quantum machine learning algorithms, on the other hand, could be exponentially faster than their classical counterparts by utilizing quantum parallelism. Here, we demonstrate a quantum machine learning algorithm to implement handwriting recognition on a four-qubit NMR test bench. The quantum machine learns standard character fonts and then recognizes handwritten characters from a set with two candidates. Because of the wide spread importance of artificial intelligence and its tremendous consumption of computational resources, quantum speedup would be extremely attractive against the challenges of big data.

Recent advances in quantum machine learning

“…However, QSVM alogorithm is able to provide an exponential speedup, which is O (log( NM )) . In addition, QSVM is one of the machine learning algorithms, which has already been implemented on quantum computing hardware . In fact, there are two versions of QSVM that gives quadratical and exponential speedup separately.…”

“…24 In addition, QSVM is one of the machine learning algorithms, which has already been implemented on quantum computing hardware. 4 In fact, there are two versions of QSVM that gives quadratical and exponential speedup separately. One of them focuses on solving nonconvex optimization problems by involving Grover's algorithm as a subroutine.…”

“…In addition, some algorithms have been implemented and tested on the forementioned real quantum computer. [4][5][6][7] Obviously, there are two essential parts in machine learning-the data and the learning process. Likewise, in quantum domain, it also includes these two parts.…”

Reconstruction of a Photonic Qubit State with Reinforcement Learning

“…Machine learning (ML), as a subtopic within artificial intelligence (AI) realm, has already become a powerful tool for data mining, pattern recognition, among others. Meanwhile, there are many recent works combining ML techniques with quantum information tools . These include expressing and witnessing quantum entanglement by artificial neural networks (ANN), analyzing and restructuring a quantum state by restricted Boltzmann machines (RBM), as well as detecting quantum change points, and learning Hamiltonians by Bayesian inference .…”

Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 2 Applications and Future Perspectives

“…In this section, we have discussed SVM and STM for medium and large scale problems. For big data classification problems quite perspective and promising is a quantum computing approach [Biamonte et al, 2016, Chatterjee and Yu, 2016, Li et al, 2015, Rebentrost et al, 2014, Schuld et al, 2015 and a tensor network approach discussed in the next Chapter 3.…”