Parameter Sharing - Recurrent and Convolutional Nets

Parameter Sharing - Recurrent and Convolutional Nets

Alfredo Canziani via YouTube Direct link

– Math on the whiteboard

9 of 29

9 of 29

– Math on the whiteboard

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Parameter Sharing - Recurrent and Convolutional Nets

Automatically move to the next video in the Classroom when playback concludes

  1. 1 – Welcome to class
  2. 2 – Hypernetworks
  3. 3 – Shared weights
  4. 4 – Parameter sharing ⇒ adding the gradients
  5. 5 – Max and sum reductions
  6. 6 – Recurrent nets
  7. 7 – Unrolling in time
  8. 8 – Vanishing and exploding gradients
  9. 9 – Math on the whiteboard
  10. 10 – RNN tricks
  11. 11 – RNN for differential equations
  12. 12 – GRU
  13. 13 – What is a memory
  14. 14 – LSTM – Long Short-Term Memory net
  15. 15 – Multilayer LSTM
  16. 16 – Attention for sequence to sequence mapping
  17. 17 – Convolutional nets
  18. 18 – Detecting motifs in images
  19. 19 – Convolution definitions
  20. 20 – Backprop through convolutions
  21. 21 – Stride and skip: subsampling and convolution “à trous”
  22. 22 – Convolutional net architecture
  23. 23 – Multiple convolutions
  24. 24 – Vintage ConvNets
  25. 25 – How does the brain interpret images?
  26. 26 – Hubel & Wiesel's model of the visual cortex
  27. 27 – Invariance and equivariance of ConvNets
  28. 28 – In the next episode…
  29. 29 – Training time, iteration cycle, and historical remarks

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.