Salvato in:
Dettagli Bibliografici
Autori principali: Jorgensen, Christian, Lin, Arthur Y., Vasavada, Rhushil, Cersonsky, Rose K.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.05861
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917339419639808
author Jorgensen, Christian
Lin, Arthur Y.
Vasavada, Rhushil
Cersonsky, Rose K.
author_facet Jorgensen, Christian
Lin, Arthur Y.
Vasavada, Rhushil
Cersonsky, Rose K.
contents How do classification models "see" our data? Based on their success in delineating behaviors, there must be some lens through which it is easy to see the boundary between classes; however, our current set of visualization techniques makes this prospect difficult. In this work, we propose a hybrid supervised-unsupervised technique distinctly suited to visualizing the decision boundaries determined by classification problems. This method provides a human-interpretable map that can be analyzed qualitatively and quantitatively, which we demonstrate through visualizing and interpreting a decision boundary for chemical neurotoxicity. While we discuss this method in the context of chemistry-driven problems, its application can be generalized across subfields for "unboxing" the operations of machine-learning classification models.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05861
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Interpretable Visualizations of Data Spaces for Classification Problems
Jorgensen, Christian
Lin, Arthur Y.
Vasavada, Rhushil
Cersonsky, Rose K.
Machine Learning
N/A
How do classification models "see" our data? Based on their success in delineating behaviors, there must be some lens through which it is easy to see the boundary between classes; however, our current set of visualization techniques makes this prospect difficult. In this work, we propose a hybrid supervised-unsupervised technique distinctly suited to visualizing the decision boundaries determined by classification problems. This method provides a human-interpretable map that can be analyzed qualitatively and quantitatively, which we demonstrate through visualizing and interpreting a decision boundary for chemical neurotoxicity. While we discuss this method in the context of chemistry-driven problems, its application can be generalized across subfields for "unboxing" the operations of machine-learning classification models.
title Interpretable Visualizations of Data Spaces for Classification Problems
topic Machine Learning
N/A
url https://arxiv.org/abs/2503.05861