SynFlow - Pruning Neural Networks Without Any Data by Iteratively Conserving Synaptic Flow

SynFlow - Pruning Neural Networks Without Any Data by Iteratively Conserving Synaptic Flow

Yannic Kilcher via YouTube Direct link

- Intro & Overview

1 of 11

1 of 11

- Intro & Overview

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

SynFlow - Pruning Neural Networks Without Any Data by Iteratively Conserving Synaptic Flow

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

  1. 1 - Intro & Overview
  2. 2 - Pruning Neural Networks
  3. 3 - Lottery Ticket Hypothesis
  4. 4 - Paper Story Overview
  5. 5 - Layer Collapse
  6. 6 - Synaptic Saliency Conservation
  7. 7 - Connecting Layer Collapse & Saliency Conservation
  8. 8 - Iterative Pruning avoids Layer Collapse
  9. 9 - The SynFlow Algorithm
  10. 10 - Experiments
  11. 11 - Conclusion & Comments

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.