Quantum Classifiers applied to Multi-User Detector in Communications Systems

In this paper we implement two quantum machine learning (QML) algorithms, namely, kernel-based classifier (QKC) and variational quantum classifier (VQC), considering different types of encoding functions. We compare its performance to that of its classical counterpart, the classical support vector machine (SVM) applied to the multi-user detector in a MU-DS-CDMA system, with a scenario where the user code generates non-linearities as a function of the channel delay profile. The results explicitly prove accuracy advantage achieved by our quantum classifiers on three types of datasets. This work shows that quantum classifiers have a huge potential to be useful in the future as the number of qubits in the quantum computer increases.