Hurley, Catherine B. and O’Connell, Mark and Domijan, Katarina (2022) Interactive Slice Visualization for Exploring Machine Learning Models. Journal of Computational and Graphical Statistics, 31 (1). pp. 1-13. ISSN 1061-8600

Preview

Download (3MB) | Preview

Abstract

Machine learning models fit complex algorithms to arbitrarily large datasets. These algorithms are well known to be high on performance and low on interpretability. We use interactive visualization of slices of predictor space to address the interpretability deficit; in effect opening up the black-box of machine learning algorithms, for the purpose of interrogating, explaining, validating and comparing model fits. Slices are specified directly through interaction, or using various touring algorithms designed to visit high-occupancy sections, or regions where the model fits have interesting properties. The methods presented here are implemented in the R package condvis2. Supplementary files for this article are available online.

Item Type:	Article
Additional Information:	Cite as: Catherine B. Hurley, Mark O’Connell & Katarina Domijan (2022) Interactive Slice Visualization for Exploring Machine Learning Models, Journal of Computational and Graphical Statistics, 31:1, 1-13, DOI: 10.1080/10618600.2021.1983439
Keywords:	Black-Box Models; Conditioning; Model explanation; Sectioning; Supervised and unsupervised learning; XAI;
Academic Unit:	Faculty of Science and Engineering > Mathematics and Statistics Faculty of Science and Engineering > Research Institutes > Hamilton Institute
Item ID:	17950
Identification Number:	https://doi.org/10.1080/10618600.2021.1983439
Depositing User:	Katarina Domijan
Date Deposited:	14 Dec 2023 09:36
Journal or Publication Title:	Journal of Computational and Graphical Statistics
Publisher:	Taylor & Francis Online
Refereed:	Yes
URI:	Publisher
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads