Assemble Linear Layers and Attention
Beginner NVIDIA, Meta+3
Use tensor operations to implement a linear layer (y = xW^T + b) and scaled dot-product attention. Understand how tensor ops combine into meaningful neural network components.
Keywords
deep-learningtensor-ops
Python
Run your code to see results
No results yet
Run your code to check it against the examples, or submit to run every test.