Machine Learning Methods in Visualisation for Big Data 2023

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2633348
Table of Contents
Interactive Dense Pixel Visualizations for Time Series and Model Attribution Explanations
[full paper Image] [meta data Image]
Udo Schlegel and Daniel Keim

BibTeX (Machine Learning Methods in Visualisation for Big Data 2023)
@inproceedings{
10.2312:mlvis.20232010,

booktitle = {
Machine Learning Methods in Visualisation for Big Data},

editor = {
Archambault, Daniel
 and 
Nabney, Ian
 and 
Peltonen, Jaakko
},
title = {{
MLVis 2023: Frontmatter}},

author = {
Archambault, Daniel
 and 
Nabney, Ian
 and 
Peltonen, Jaakko
},
year = {
2023},

publisher = {
The Eurographics Association},


ISBN = {978-3-03868-224-0},

DOI = {
10.2312/mlvis.20232010}

}
@inproceedings{
10.2312:mlvis.20231113,

booktitle = {
Machine Learning Methods in Visualisation for Big Data},

editor = {
Archambault, Daniel
 and 
Nabney, Ian
 and 
Peltonen, Jaakko
},
title = {{
Interactive Dense Pixel Visualizations for Time Series and Model Attribution Explanations}},

author = {
Schlegel, Udo
 and 
Keim, Daniel
},
year = {
2023},

publisher = {
The Eurographics Association},


ISBN = {978-3-03868-224-0},

DOI = {
10.2312/mlvis.20231113}

}

Browse

Recent Submissions

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    MLVis 2023: Frontmatter
    (The Eurographics Association, 2023) Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
  • Thumbnail Image
    Item
    Interactive Dense Pixel Visualizations for Time Series and Model Attribution Explanations
    (The Eurographics Association, 2023) Schlegel, Udo; Keim, Daniel; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
    The field of Explainable Artificial Intelligence (XAI) for Deep Neural Network models develops significantly, offering numerous techniques to extract explanations from models. However, evaluating explanations is often not trivial, and differences in applied metrics can be subtle, especially with non-intelligible data. Thus, there is a need for visualizations tailored to explore explanations for domains with such data, e.g., time series. We propose DAVOTS, an interactive visual analytics approach to explore raw time series data, activations of neural networks, and attributions in a dense-pixel visualization to gain insights into the data, models' decisions, and explanations. To further support users in exploring large datasets, we apply clustering approaches to the visualized data domains to highlight groups and present ordering strategies for individual and combined data exploration to facilitate finding patterns. We visualize a CNN trained on the FordA dataset to demonstrate the approach.