Skip to content

Source code for the numerical experiments conducted in the thesis "Toward Interpretable Quantum Machine Learning: Feature Attribution and Variational Quantum Circuits"

Notifications You must be signed in to change notification settings

LiukDiihMieu/IML-Quantum

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

IML-Quantum

This repository contains the source code for the numerical experiments conducted in the master's thesis titled "Toward Interpretable Quantum Machine Learning: Feature Attribution and Variational Quantum Circuits".

The FeatureAttr.py script acts as the core module, which includes various feature attribution algorithms and helper functions that are repeatedly used throughout the different experiments.

The synthetic_4x4.ipynb notebook demonstrates the usage of feature attribution methods to interpret a VQC model that has been trained on a $4\times4$ synthetic image dataset.

The FashionMNIST.ipynb notebook provides an example of how to explain a single-qubit data-reuploading classifier that was utilized in a $9\times9$ downscaled FashionMNIST binary classification task.

About

Source code for the numerical experiments conducted in the thesis "Toward Interpretable Quantum Machine Learning: Feature Attribution and Variational Quantum Circuits"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published