Machine Learning Methods in Visualisation for Big Data 2022

Permanent URI for this collection

Papers
Visual Exploration of Neural Network Projection Stability
Carlo Bredius, Zonglin Tian, and Alexandru Telea
Saliency Clouds: Visual Analysis of Point Cloud-oriented Deep Neural Networks in DeepRL for Particle Physics
Raju Ningappa Mulawade, Christoph Garth, and Alexander Wiebel
ViNNPruner: Visual Interactive Pruning for Deep Learning
Udo Schlegel, Samuel Schiegg, and Daniel A. Keim

BibTeX (Machine Learning Methods in Visualisation for Big Data 2022)
@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}
}
@inproceedings{
10.2312:mlvis.20222008,
booktitle = {
Machine Learning Methods in Visualisation for Big Data},
editor = {
Archambault, Daniel
and
Nabney, Ian
and
Peltonen, Jaakko
}, title = {{
MLVis 2022: Frontmatter}},
author = {
Archambault, Daniel
and
Nabney, Ian
and
Peltonen, Jaakko
}, year = {
2022},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-182-3},
DOI = {
10.2312/mlvis.20222008}
}
@inproceedings{
10.2312:mlvis.20221070,
booktitle = {
Machine Learning Methods in Visualisation for Big Data},
editor = {
Archambault, Daniel
and
Nabney, Ian
and
Peltonen, Jaakko
}, title = {{
ViNNPruner: Visual Interactive Pruning for Deep Learning}},
author = {
Schlegel, Udo
and
Schiegg, Samuel
and
Keim, Daniel A.
}, year = {
2022},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-182-3},
DOI = {
10.2312/mlvis.20221070}
}
@inproceedings{
10.2312:mlvis.20221069,
booktitle = {
Machine Learning Methods in Visualisation for Big Data},
editor = {
Archambault, Daniel
and
Nabney, Ian
and
Peltonen, Jaakko
}, title = {{
Saliency Clouds: Visual Analysis of Point Cloud-oriented Deep Neural Networks in DeepRL for Particle Physics}},
author = {
Mulawade, Raju Ningappa
and
Garth, Christoph
and
Wiebel, Alexander
}, year = {
2022},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-182-3},
DOI = {
10.2312/mlvis.20221069}
}

Browse

Recent Submissions

Now showing 1 - 4 of 4
  • Item
    Visual Exploration of Neural Network Projection Stability
    (The Eurographics Association, 2022) Bredius, Carlo; Tian, Zonglin; Telea, Alexandru; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
    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.
  • Item
    MLVis 2022: Frontmatter
    (The Eurographics Association, 2022) Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
  • Item
    ViNNPruner: Visual Interactive Pruning for Deep Learning
    (The Eurographics Association, 2022) Schlegel, Udo; Schiegg, Samuel; Keim, Daniel A.; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
    Neural networks grow vastly in size to tackle more sophisticated tasks. In many cases, such large networks are not deployable on particular hardware and need to be reduced in size. Pruning techniques help to shrink deep neural networks to smaller sizes by only decreasing their performance as little as possible. However, such pruning algorithms are often hard to understand by applying them and do not include domain knowledge which can potentially be bad for user goals. We propose ViNNPruner, a visual interactive pruning application that implements state-of-the-art pruning algorithms and the option for users to do manual pruning based on their knowledge. We show how the application facilitates gaining insights into automatic pruning algorithms and semi-automatically pruning oversized networks to make them more efficient using interactive visualizations.
  • Item
    Saliency Clouds: Visual Analysis of Point Cloud-oriented Deep Neural Networks in DeepRL for Particle Physics
    (The Eurographics Association, 2022) Mulawade, Raju Ningappa; Garth, Christoph; Wiebel, Alexander; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
    We develop and describe saliency clouds, that is, visualization methods employing explainable AI methods to analyze and interpret deep reinforcement learning (DeepRL) agents working on point cloud-based data. The agent in our application case is tasked to track particles in high energy physics and is still under development. The point clouds contain properties of particle hits on layers of a detector as the input to reconstruct the trajectories of the particles. Through visualization of the influence of different points, their possible connections in an implicit graph, and other features on the decisions of the policy network of the DeepRL agent, we aim to explain the decision making of the agent in tracking particles and thus support its development. In particular, we adapt gradient-based saliency mapping methods to work on these point clouds. We show how the properties of the methods, which were developed for image data, translate to the structurally different point cloud data. Finally, we present visual representations of saliency clouds supporting visual analysis and interpretation of the RL agent's policy network.