Machine Learning Methods in Visualisation for Big Data 2019

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632787

Browse

Browsing Machine Learning Methods in Visualisation for Big Data 2019 by Title

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    Interpreting Black-Box Semantic Segmentation Models in Remote Sensing Applications
    (The Eurographics Association, 2019) Janik, Adrianna; Sankaran, Kris; Ortiz, Anthony; Archambault, Daniel and Nabney, Ian and Peltonen, Jaakko
    In the interpretability literature, attention is focused on understanding black-box classifiers, but many problems ranging from medicine through agriculture and crisis response in humanitarian aid are tackled by semantic segmentation models. The absence of interpretability for these canonical problems in computer vision motivates this study. In this study we present a usercentric approach that blends techniques from interpretability, representation learning, and interactive visualization. It allows to visualize and link latent representation to real data instances as well as qualitatively assess strength of predictions. We have applied our method to a deep learning model for semantic segmentation, U-Net, in a remote sensing application of building detection. This application is of high interest for humanitarian crisis response teams that rely on satellite images analysis. Preliminary results shows utility in understanding semantic segmentation models, demo presenting the idea is available online.
  • Thumbnail Image
    Item
    MLVis 2019: Frontmatter
    (The Eurographics Association, 2019) Archambault, Daniel; Nabney, Ian; Peltonen, Jaakko; Archambault, Daniel and Nabney, Ian and Peltonen, Jaakko
  • Thumbnail Image
    Item
    On KDE-based Brushing in Scatterplots and how it Compares to CNN-based Brushing
    (The Eurographics Association, 2019) Fan, Chaoran; Hauser, Helwig; Archambault, Daniel and Nabney, Ian and Peltonen, Jaakko
    In this paper, we investigate to which degree the human should be involved into the model design and how good the empirical model can be with more careful design. To find out, we extended our previously published Mahalanobis brush (the best current empirical model in terms of accuracy for brushing points in a scatterplot) by further incorporating the data distribution information that is captured by the kernel density estimation (KDE). Based on this work, we then include a short discussion between the empirical model, designed in detail by an expert and the deep learning-based model that is learned from user data directly.
  • Thumbnail Image
    Item
    Visual Analysis of Multivariate Urban Traffic Data Resorting to Local Principal Curves
    (The Eurographics Association, 2019) Silva, Carla; d'Orey, Pedro; Aguiar, Ana; Archambault, Daniel and Nabney, Ian and Peltonen, Jaakko
    Traffic congestion causes major economic, environmental and social problems in modern cities. We present an interactive visualization tool to assist domain experts on the identification and analysis of traffic patterns at a city scale making use of multivariate empirical urban data and fundamental diagrams. The proposed method combines visualization techniques with an improved local principle curves method to model traffic dynamics and facilitate comparison of traffic patterns - resorting to the fitted curve with a confidence interval - between different road segments and for different external conditions. We demonstrate the proposed technique in an illustrative real-world case study in the city of Porto, Portugal.
  • Thumbnail Image
    Item
    Visual Ensemble Analysis to Study the Influence of Hyper-parameters on Training Deep Neural Networks
    (The Eurographics Association, 2019) Hamid, Sagad; Derstroff, Adrian; Klemm, Sören; Ngo, Quynh Quang; Jiang, Xiaoyi; Linsen, Lars; Archambault, Daniel and Nabney, Ian and Peltonen, Jaakko
    A good deep neural network design allows for efficient training and high accuracy. The training step requires a suitable choice of several hyper-parameters. Limited knowledge exists on how the hyper-parameters impact the training process, what is the interplay of multiple hyper-parameters, and what is the interrelation of hyper-parameters and network topology. In this paper, we present a structured analysis towards these goals by investigating an ensemble of training runs.We propose a visual ensemble analysis based on hyper-parameter space visualizations, performance visualizations, and visualizing correlations of topological structures. As a proof of concept, we apply our approach to deep convolutional neural networks.