Ultimate Intelligence

Wednesday, May 1, 2019

Geometric Deep Learning?

I found a new website: http://geometricdeeplearning.com/
Good tutorials:

  • Joan Bruna NIPS 2017 Geometric Deep Learning on Graphs and Manifolds
  • PDF tutorial:https://arxiv.org/pdf/1611.08402.pdf
  • Xavier Bresson: "Convolutional Neural Networks on Graphs"
  • Slides: http://helper.ipam.ucla.edu/publications/dlt2018/dlt2018_14506.pdf
Basically in the tutorial Joan introduced the concept of manifold and graph theories. And then derived spectral graph convolution operations. What is missing is how can CNN be applied to general manifold instead of Euclidean space and graph? 
Posted by JP Zhang at 3:24 PM
Email ThisBlogThis!Share to TwitterShare to FacebookShare to Pinterest

No comments:

Post a Comment

Newer Post Older Post Home
Subscribe to: Post Comments (Atom)

Blog Archive

  • ►  2020 (2)
    • ►  September (1)
    • ►  March (1)
  • ▼  2019 (26)
    • ►  December (1)
    • ►  October (2)
    • ►  September (4)
    • ►  June (6)
    • ▼  May (8)
      • What is reinforcement learning?
      • Neural Architecture Search
      • Max Welling's "Intelligence Per Kilowatt-Hour"
      • Those measurements for two probability distributions
      • What is a cross-entropy loss function?
      • Doing Things in a Reverse Way---those reverse oper...
      • Deconvolution
      • Geometric Deep Learning?
    • ►  April (4)
    • ►  March (1)
Simple theme. Theme images by luoman. Powered by Blogger.