Developing Explainable Machine Learning Model using Augmented Concept Activation Vector

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hassanpour, Reza, Oztoprak, Kasim, Netten, Niels, Busker, Tony, Bargh, Mortaza S., Choenni, Sunil, Kizildag, Beyza, Kilinc, Leyla Sena
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929648682663936
author Hassanpour, Reza
Oztoprak, Kasim
Netten, Niels
Busker, Tony
Bargh, Mortaza S.
Choenni, Sunil
Kizildag, Beyza
Kilinc, Leyla Sena
author_facet Hassanpour, Reza
Oztoprak, Kasim
Netten, Niels
Busker, Tony
Bargh, Mortaza S.
Choenni, Sunil
Kizildag, Beyza
Kilinc, Leyla Sena
contents Machine learning models use high dimensional feature spaces to map their inputs to the corresponding class labels. However, these features often do not have a one-to-one correspondence with physical concepts understandable by humans, which hinders the ability to provide a meaningful explanation for the decisions made by these models. We propose a method for measuring the correlation between high-level concepts and the decisions made by a machine learning model. Our method can isolate the impact of a given high-level concept and accurately measure it quantitatively. Additionally, this study aims to determine the prevalence of frequent patterns in machine learning models, which often occur in imbalanced datasets. We have successfully applied the proposed method to fundus images and managed to quantitatively measure the impact of radiomic patterns on the model decisions.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19208
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Developing Explainable Machine Learning Model using Augmented Concept Activation Vector
Hassanpour, Reza
Oztoprak, Kasim
Netten, Niels
Busker, Tony
Bargh, Mortaza S.
Choenni, Sunil
Kizildag, Beyza
Kilinc, Leyla Sena
Machine Learning
68T07
I.2.6
Machine learning models use high dimensional feature spaces to map their inputs to the corresponding class labels. However, these features often do not have a one-to-one correspondence with physical concepts understandable by humans, which hinders the ability to provide a meaningful explanation for the decisions made by these models. We propose a method for measuring the correlation between high-level concepts and the decisions made by a machine learning model. Our method can isolate the impact of a given high-level concept and accurately measure it quantitatively. Additionally, this study aims to determine the prevalence of frequent patterns in machine learning models, which often occur in imbalanced datasets. We have successfully applied the proposed method to fundus images and managed to quantitatively measure the impact of radiomic patterns on the model decisions.
title Developing Explainable Machine Learning Model using Augmented Concept Activation Vector
topic Machine Learning
68T07
I.2.6
url https://arxiv.org/abs/2412.19208