TIMESTAMPS:
01:10 Text Classification
01:49 Using Attention to build a Transformer (Theory)
06:20 Basic Transformer Architecture (Code)
06:59 what is a Position Embedding? (Theory + Code)
09:03 Training the Text Classifier (Code)
09:40 Testing, What tokens are important? (Theory + Code)
11:10 What is Padding key masks? (Theory + Code)
14:14 Scaling up! Encoder-Only Transformer!
In this video I introduce the Transformer model, a Neural Network architecture that can process sequential data using attention!
Donations
https://www.buymeacoffee.com/lukeditria
The corresponding code is available here! (Section 14)
https://github.com/LukeDitria/pytorch...
Discord Server:
/ discord