Buy your pass

Convolutional networks beyond the Euclidean space

OnlineDiscovery - From Molecules to Models

  • Register

    * Register (or log in) to the Neural Network to add this session to your agenda or watch the replay

    • Date
    12 November 2025
    Timeframe
    17:00 - 18:00 CET Geneva
    Duration
    60 minutes
    Share this session

    Convolutional networks have revolutionized image analysis and data science. They are among the main driving forces behind the current AI revolution. I will sketch important developments covering the initial breakthrough on the problem of image classification (Krizhevsky et al., NeurIPS 2012) and then focus on efforts to extend the power of deep networks beyond image classification to other challenges in image analysis, in shape analysis, in medicine and in the life sciences. Examples include optical flow estimation (Dosovitskiy et al., ICCV 2015), the acceleration of diffusion tensor imaging (Golkov et al. 2016), tuberculosis screening from chest x-ray (Golkov et al., Sci. Reports 2019), or protein structure prediction (Golkov et al., NeurIPS 2016). I will also give a short overview of convolutional networks for graph-valued data and present a recent solution that extends convolutional networks to directed graphs using holomorphic functional calculus (Koke & Cremers, ICLR ! 2024).

     

    Learning Objectives:

    By the end of the session, participants will be able to:

    • Explain the fundamental principles and architecture of convolutional networks.
    • Apply convolutional networks to non-Euclidean data structures.
    • Share this session
    • Days
      Hours
      Min
      Sec
    Add to Calendar
    Discover more from programme stream
    Discovery - From Molecules to Models
    Convolutional networks beyond the Euclidean space

    Convolutional networks beyond the Euclidean space

    12 November 2025 - 17:00 to 18:00

    Related stories

    Are you sure you want to remove this speaker?