Lecture 2.3: Backpropagation, a tensor view (DLVU)
Вставка
- Опубліковано 27 вер 2024
- lecturer: Peter Bloem
course website: dlvu.github.io
In this video, we work out the backpropagation algorithm in a vectorized version: that is purely in terms of basic linear algebra operations like matrix and vector multiplication. This helps us to express neural networks in a clean notation, and to accelarate their computation.
extremely underrated resource for learning backpropagation! Thank you for this!
This is a great course. Thanks for all these details!
This is exceptionally well explained. I'm a student at TU Delft and this really helped me understand how to speed up my code, and why it works. Thanks a lot!