Visual Exploration of Neural Network Projection Stability

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

We present a method to visually assess the stability of deep learned projections. For this, we perturb the high-dimensional data
by controlled sequences and visualize the resulting changes in the 2D projection. We apply our method to a recent deep learned
projection framework on several training configurations (learned projections and real-world datasets). Our method, which is
simple to implement, runs at interactive rates, sheds several novel insights on the stability of the explored method.
Original languageEnglish
Title of host publicationProceedings of Machine Learning in Visualization (MLVis)
Number of pages5
DOIs
Publication statusPublished - 2022

Fingerprint

Dive into the research topics of 'Visual Exploration of Neural Network Projection Stability'. Together they form a unique fingerprint.

Cite this