Exploring the Cosmos with Deep Learning

Exploring the Cosmos with Deep Learning

Alan Turing Institute via YouTube Direct link

automated lens searches: Ring Finder (Gavazzi et al. 2014)

7 of 28

7 of 28

automated lens searches: Ring Finder (Gavazzi et al. 2014)

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

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.