How to Add Attention to LSTM Network! : PyTorch Deep Learning Tutorial Section13

TIMESTAMPS:
0:00 - Introduction
0:25 - Previous video overview: Attention Mechanism
1:43 - LSTM's memory buffer limitations
3:02 - Incorporating attention with LSTM
4:56 - Diagram: Storing LSTM outputs for attention
6:45 - Architecture overview: Multi-headed attention
8:23 - Training loop adjustments
10:12 - Text generation examples
12:58 - Using attention alone in future
14:37 - Conclusion
In this video I show how we can add the Attention Mechanism to our LSTM text generator to improve it's performance!
Donations
www.buymeacoffee.com/lukeditria
The corresponding code is available here!
github.com/LukeDitria/pytorch...
Discord Server:
/ discord