Completed
- Conclusion & Comments
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
How to Represent Part-Whole Hierarchies in a Neural Network - Geoff Hinton's Paper Explained
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro & Overview
- 2 - Object Recognition as Parse Trees
- 3 - Capsule Networks
- 4 - GLOM Architecture Overview
- 5 - Top-Down and Bottom-Up communication
- 6 - Emergence of Islands
- 7 - Cross-Column Attention Mechanism
- 8 - My Improvements for the Attention Mechanism
- 9 - Some Design Decisions
- 10 - Training GLOM as a Denoising Autoencoder & Contrastive Learning
- 11 - Coordinate Transformations & Representing Uncertainty
- 12 - How GLOM handles Video
- 13 - Conclusion & Comments
