New Approach of KNN Algorithm in Quantum Computing Based on New Design of Quantum Circuits

Abstract

Quantum computing is rising as a new type of computer that theoretically reduces the time complexity of classical methods exponentially because of the nature of superposition. It is promising to reduce run times on large datasets in machine learning (ML). Meanwhile, k-nearest neighbor (kNN) is a simple ML algorithm that can be translated to a quantum version (QkNN) to perform classification tasks efficiently. Here, we show a new version of QkNN which has a speed up in time complexity by using a new design of quantum circuits called integrated swap test. This quantum circuit can load two N - dimensional states and calculate the fidelity between them. Results show that QkNN allows us to take a different approach to the ML field.