[4Yin2] Interactive session 2

[4Yin2-50] Performance evaluation of quantum kernel machine learning

〇Takao Tomono¹, Satoko Natsubori¹, Katsumi Imaizumi¹ (1.Toppan Inc.)

Keywords:quantum machine learning, quantum kernel

Machine learning classifiers have been used in medicine, factory inspections, and automated driving. Support Vector Machines (SVMs), one of the classifiers, are particularly useful and have been used in various situations. In particular, kernel methods are very important for nonlinear and unsolvable classification. On the other hand, quantum machine learning has received much attention in recent years, but its specific evaluation has not been done much. In this study, we examined the process of building a learning model for classification using a heart disease data set. As a result, we found that the classical kernel method is a method to build a learning model by improving the true positive rate from a random model, while the quantum kernel method is a method to reduce the false positive rate from high true positive rate and false positive rate. In summary, we have demonstrated for the first time the process of quantum circuit learning by using the ROC space. Furthermore, we were able to construct a learning model using a quantum kernel with higher accuracy than that constructed by the classical kernel method.