hierarchical transformer model
C39887
concept
A hierarchical transformer model is a neural network architecture that processes data at multiple levels of granularity (e.g., tokens, sentences, documents) using stacked transformer layers to capture both local and global contextual dependencies efficiently.
Observed surface forms (1)
| Surface form | Occurrences |
|---|---|
| Transformer variant | 1 |
Instances (2)
| Instance | Via concept surface |
|---|---|
| Swin Transformer | — |
| Transformer-XL | Transformer variant |