Machine Learning Methods in Visualisation for Big Data 2022

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2633201

Browse

Browsing Machine Learning Methods in Visualisation for Big Data 2022 by Title

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    MLVis 2022: Frontmatter
    (The Eurographics Association, 2022) Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko; Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
  • Thumbnail Image
    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.
  • Thumbnail Image
    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.
  • Thumbnail Image
    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.