13.01.2020
As the world grows in its use of technology, machine learning algorithms are being used with increasing frequency to understand the patterns in the data that we produce. As humanity begins to create more data than ever before, we need more efficient ways to sort through this data to find the underlying patterns. A Support Vector Machine is a type of machine learning algorithm that is able to classify datasets. It has recently been proven successful, working on both a quantum computer and a classical computer, using slightly different methods. This report aims to look deeper into each of these methods of classifying a health dataset and determining the benefits of each classification method.
This scientific experiment will aim to explain the basics behind both a Classical and Quantum Support Vector Machine that is able to classify between two distinct classes. It will then further elaborate onwards, comparing the Classical Support Vector Machine (SVM) to the Quantum Support Vector Machine (QSVM) in the aim to find which is computationally superior.
In this report, I will focus on support vector machines, which are designed for classification problems on small datasets and which have a quantum QSVM counterpart.
combined.ipynb is the main file for this report