Supervised Learning Using Quantum Technology



Published Jul 19, 2020
Daniel Jaroszewski Benedikt Sturm Wolfgang Mergenthaler Kay Steffen Patrick Linke Michael Regel Björn Haack


In this paper, we present classical machine learning algorithms enhanced by quantum technology to classify a data set. The data set contains binary input variables and binary output variables. The goal is to extend classical approaches such as neural networks by using quantum machine learning principles. Classical algorithms struggle as the dimensionality of the feature space increases. We examine the usage of quantum technologies to speed up these classical algorithms and to introduce the new quantum paradigm into machine diagnostic domain. Most of the prognosis models based on binary or multi-valued classification have become increasingly complex throughout the recent past. Starting with a short introduction into quantum computing, we will present an approach of combining quantum computing and classical machine learning to the reader. Further, we show different implementations of quantum classification algorithms. Finally, the algorithms presented are applied to a data set. The results of the implementations are shown and discussed in the last section.

Abstract 78 | PDF Downloads 97



supervised learning, machine learning, classification, tensorflow quantum, predictive maintenance, Quantum Technology, planQK

Tehnical Papers