To do machine learning on a quantum computer requires one to first load real-world data onto it. It turns out researchers are still stuck on this first step. We currently don't know what is the best way encode classical information into a quantum system and whether this will give us any advantage over classical algorithms. In this project we will explore different approaches to embed real data onto a quantum computer in the context of training a quantum support vector machine (QSVM). We will compare what people have done in literature with any new ideas we may have. We will be exploring a (crucial) open question in quantum machine learning - who knows what we will find!
Description
We will be using Python and the Qiskit library to code up our quantum machine learning model. More information/code on QSVMs can be found here:
Abstract
To do machine learning on a quantum computer requires one to first load real-world data onto it. It turns out researchers are still stuck on this first step. We currently don't know what is the best way encode classical information into a quantum system and whether this will give us any advantage over classical algorithms. In this project we will explore different approaches to embed real data onto a quantum computer in the context of training a quantum support vector machine (QSVM). We will compare what people have done in literature with any new ideas we may have. We will be exploring a (crucial) open question in quantum machine learning - who knows what we will find!
Description
We will be using Python and the Qiskit library to code up our quantum machine learning model. More information/code on QSVMs can be found here:
Analysis will be done on simulators and if we have time we can see how our models perform with real devices.
If you don't know anything about machine learning (ML) don't worry! We will go through the ML required on the first day.
Members
Deliverable
Optimal QSVM models for toy datasets.
GitHub repo