Self-Attention Paragraph Typos

[PeppeSaccardi]

In the paragraph Self-Attention(I) of Week 12/Attention and the Transformer there is a little mistake after the definition of the hidden layer as matrix multiplication: the vector should belong to instead of

[Atcold]

Of course, thanks! Would you like to send a PR to fix this across all languages?

[PeppeSaccardi]

Of course! Thank you Alfredo!