Visual Exploration of Neural Network Projection Stability

Loading...
Thumbnail Image
Date
2022
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
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.
Description

CCS Concepts: Human-centered computing --> Information visualization; Visual analytics; Visualization systems and tools

        
@inproceedings{
10.2312:mlvis.20221068
, booktitle = {
Machine Learning Methods in Visualisation for Big Data
}, editor = {
Archambault, Daniel
and
Nabney, Ian
and
Peltonen, Jaakko
}, title = {{
Visual Exploration of Neural Network Projection Stability
}}, author = {
Bredius, Carlo
and
Tian, Zonglin
and
Telea, Alexandru
}, year = {
2022
}, publisher = {
The Eurographics Association
}, ISBN = {
978-3-03868-182-3
}, DOI = {
10.2312/mlvis.20221068
} }
Citation