Integrating White and Black Box Techniques for Interpretable Machine Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vernon, Eric M., Masuyama, Naoki, Nojima, Yusuke
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910524198879232
author Vernon, Eric M.
Masuyama, Naoki
Nojima, Yusuke
author_facet Vernon, Eric M.
Masuyama, Naoki
Nojima, Yusuke
contents In machine learning algorithm design, there exists a trade-off between the interpretability and performance of the algorithm. In general, algorithms which are simpler and easier for humans to comprehend tend to show worse performance than more complex, less transparent algorithms. For example, a random forest classifier is likely to be more accurate than a simple decision tree, but at the expense of interpretability. In this paper, we present an ensemble classifier design which classifies easier inputs using a highly-interpretable classifier (i.e., white box model), and more difficult inputs using a more powerful, but less interpretable classifier (i.e., black box model).
format Preprint
id arxiv_https___arxiv_org_abs_2407_08973
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Integrating White and Black Box Techniques for Interpretable Machine Learning
Vernon, Eric M.
Masuyama, Naoki
Nojima, Yusuke
Machine Learning
In machine learning algorithm design, there exists a trade-off between the interpretability and performance of the algorithm. In general, algorithms which are simpler and easier for humans to comprehend tend to show worse performance than more complex, less transparent algorithms. For example, a random forest classifier is likely to be more accurate than a simple decision tree, but at the expense of interpretability. In this paper, we present an ensemble classifier design which classifies easier inputs using a highly-interpretable classifier (i.e., white box model), and more difficult inputs using a more powerful, but less interpretable classifier (i.e., black box model).
title Integrating White and Black Box Techniques for Interpretable Machine Learning
topic Machine Learning
url https://arxiv.org/abs/2407.08973