Explaining AI through visual explanations and efficient interpretable models

Author

Janith Wanniarachchi

A thesis submitted for the degree of Doctor of Philosophy at Monash University, Department of Econometrics & Business Statistics.

Abstract

Explainable AI (XAI) methods were introduced to demystify the working of black box models. However as these methods matured, the mechanisms behind these methods became a black box itself. In this thesis we prov

Declaration

This thesis is an original work of my research and contains no material which has been accepted for the award of any other degree or diploma at any university or equivalent institution and that, to the best of my knowledge and belief, this thesis contains no material previously published or written by another person, except where due reference is made in the text of the thesis.

Student name: Janith Wanniarachchi

Student signature:

Date:

I hereby certify that the above declaration correctly reflects the nature and extent of the student’s and co-authors’ contributions to this work. In instances where I am not the responsible author I have consulted with the responsible author to agree on the respective contributions of the authors.

Main Supervisor name: Di Cook

Main Supervisor signature:

Date:

Reproducibility statement

This thesis is written using Quarto with renv(Ushey 2022) to create a reproducible environment. All materials (including the data sets and source files) required to reproduce this document can be found at the Github repository github.com/janithwanni/phd-thesis.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Acknowledgements

I acknowledge the use of ChatGPT to generate missing documentation for R functions. The output from these was used to make sure that the documentation is understandable from an outside perspective.

This research was supported by an Australian Government Research Training Program (RTP) Scholarship.