Source identity
| Field | Recorded value |
|---|---|
| Source type | Primary research paper |
| Original record | Attention Is All You Need |
| Date | Not specified in source |
Source access
This register entry preserves the source identity and provenance. Its full text is available through the original source when a link is supplied.
Open the original source ↗Mathematical records from this source
Scaled dot-product attention logits
For each query, compute its dot product with every key and divide by the square root of the query/key feature width. The transposed key axes put corresponding features into the…
Scaled dot-product attention
Query-key dot products are divided by √dₖ, row-wise softmax converts them into weights that sum to one, and those weights average the value vectors. The code implements these…
Scaled dot-product attention
Query-key dot products are divided by √dₖ, row-wise softmax converts them into weights that sum to one, and those weights average the value vectors. The code implements these…
Scaled dot-product attention
Query-key dot products are divided by √dₖ, row-wise softmax converts them into weights that sum to one, and those weights average the value vectors. The code implements these…
Scaled dot-product attention
Query-key dot products are divided by √dₖ, row-wise softmax converts them into weights that sum to one, and those weights average the value vectors. The code implements these…
Scaled dot-product attention
Query-key dot products are divided by √dₖ, row-wise softmax converts them into weights that sum to one, and those weights average the value vectors. The code implements these…