Differentiable Associative Memories, Attention, and Transformers

Differentiable Associative Memories, Attention, and Transformers

Alfredo Canziani via YouTube Direct link

– Disclaimer

3 of 15

3 of 15

– Disclaimer

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Differentiable Associative Memories, Attention, and Transformers

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

  1. 1 – Motivation for reasoning & planning
  2. 2 – Inference through energy minimization
  3. 3 – Disclaimer
  4. 4 – Planning through energy minimization
  5. 5 – Q&A Optimal control diagram
  6. 6 – Differentiable associative memory and attention
  7. 7 – Transformers
  8. 8 – Q&A Other differentiable attention architectures
  9. 9 – Transformer architecture
  10. 10 – Transformer applications: 1. Multilingual transformer Architecture XML-R
  11. 11 – 2. Supervised symbol manipulation
  12. 12 – 3. NL understanding & generation
  13. 13 – 4. DETR
  14. 14 – Planing through optimal control
  15. 15 – 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.