Quantum Machine Learning with HQC Architectures using non-Classically Simulable Feature Maps

TL;DR

This paper demonstrates the use of non-classically simulable feature maps in hybrid quantum-classical architectures to effectively perform quantum machine learning tasks on near-term quantum computers, showing practical real-world applications.

Contribution

It introduces the application of QSVM with non-classically simulable feature maps in HQC architectures, highlighting their potential for real-world quantum machine learning tasks.

Findings

Achieved accurate mental health treatment prediction using quantum models

Proved NISQ HQC architectures can be effective in practical applications

Demonstrated the viability of non-classically simulable feature maps in quantum ML

Abstract

Hybrid Quantum-Classical (HQC) Architectures are used in near-term NISQ Quantum Computers for solving Quantum Machine Learning problems. The quantum advantage comes into picture due to the exponential speedup offered over classical computing. One of the major challenges in implementing such algorithms is the choice of quantum embeddings and the use of a functionally correct quantum variational circuit. In this paper, we present an application of QSVM (Quantum Support Vector Machines) to predict if a person will require mental health treatment in the tech world in the future using the dataset from OSMI Mental Health Tech Surveys. We achieve this with non-classically simulable feature maps and prove that NISQ HQC Architectures for Quantum Machine Learning can be used alternatively to create good performance models in near-term real-world applications.