Completed
Graph Convolutional Networks (Kipf & Welling 2017)
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Exploring the Cosmos with Deep Learning
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 the ACDM view of the Universe
- 3 the Large Synoptic Survey Telescope
- 4 what does it look like?
- 5 the challenge for modern surveys
- 6 example of application: gravitational time delays
- 7 automated lens searches: Ring Finder (Gavazzi et al. 2014)
- 8 Conventional Convolutional Neural Network
- 9 Bottleneck residual units
- 10 Pre-activation ResNet
- 11 I performance on simulations
- 12 Euclid strong lens finding challenge
- 13 impact of galaxy morphology
- 14 Auto-Encoding Variational Bayes (Kingma & Welling 2014)
- 15 recognition model and variational lower bound
- 16 the reparameterization trick
- 17 Conditional Variational AutoEncoder (CVAE)
- 18 testing the conditional generation
- 19 morphological statistics
- 20 take away message
- 21 intrinsic alignment of galaxies
- 22 hydrodynamical simulations
- 23 inpainting intrinsic aligments on Nbody simulations
- 24 spectral theory on graphs
- 25 spectral graph convolutions
- 26 Graph Convolutional Networks (Kipf & Welling 2017)
- 27 results on the galaxy inpainting problem
- 28 conclusion
