Machine Learning Methods in Visualisation for Big Datahttps://diglib.eg.org:443/handle/10.2312/26324022024-03-29T02:27:54Z2024-03-29T02:27:54ZInteractive Dense Pixel Visualizations for Time Series and Model Attribution ExplanationsSchlegel, UdoKeim, Danielhttps://diglib.eg.org:443/handle/10.2312/mlvis202311132023-07-07T08:37:40Z2023-01-01T00:00:00ZInteractive Dense Pixel Visualizations for Time Series and Model Attribution Explanations
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.
2023-01-01T00:00:00ZMLVis 2023: FrontmatterArchambault, DanielNabney, IanPeltonen, Jaakkohttps://diglib.eg.org:443/handle/10.2312/mlvis202320102023-07-07T08:37:40Z2023-01-01T00:00:00ZMLVis 2023: Frontmatter
Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko
2023-01-01T00:00:00ZSaliency Clouds: Visual Analysis of Point Cloud-oriented Deep Neural Networks in DeepRL for Particle PhysicsMulawade, Raju NingappaGarth, ChristophWiebel, Alexanderhttps://diglib.eg.org:443/handle/10.2312/mlvis202210692022-12-19T08:27:32Z2022-01-01T00:00:00ZSaliency Clouds: Visual Analysis of Point Cloud-oriented Deep Neural Networks in DeepRL for Particle Physics
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.
2022-01-01T00:00:00ZViNNPruner: Visual Interactive Pruning for Deep LearningSchlegel, UdoSchiegg, SamuelKeim, Daniel A.https://diglib.eg.org:443/handle/10.2312/mlvis202210702022-12-19T08:27:33Z2022-01-01T00:00:00ZViNNPruner: Visual Interactive Pruning for Deep Learning
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.
2022-01-01T00:00:00Z