Saliency Clouds: Visual Analysis of Point Cloud-oriented Deep Neural Networks in DeepRL for Particle Physics

Simple item page
dc.contributor.authorMulawade, Raju Ningappaen_US
dc.contributor.authorGarth, Christophen_US
dc.contributor.authorWiebel, Alexanderen_US
dc.contributor.editorArchambault, Danielen_US
dc.contributor.editorNabney, Ianen_US
dc.contributor.editorPeltonen, Jaakkoen_US
dc.date.accessioned2022-06-02T09:48:26Z
dc.date.available2022-06-02T09:48:26Z
dc.date.issued2022
dc.description.abstractWe 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.en_US
dc.description.sectionheadersPapers
dc.description.seriesinformationMachine Learning Methods in Visualisation for Big Data
dc.identifier.doi10.2312/mlvis.20221069
dc.identifier.isbn978-3-03868-182-3
dc.identifier.pages7-11
dc.identifier.pages5 pages
dc.identifier.urihttps://doi.org/10.2312/mlvis.20221069
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/mlvis20221069
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Human-centered computing --> Visualization techniques; Computing methodologies --> Neural networks
dc.subjectHuman centered computing
dc.subjectVisualization techniques
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.titleSaliency Clouds: Visual Analysis of Point Cloud-oriented Deep Neural Networks in DeepRL for Particle Physicsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
007-011.pdf
Size:
2.63 MB
Format:
Adobe Portable Document Format
Download
Collections
Machine Learning Methods in Visualisation for Big Data 2022