Comparison of different Unique hard attention transformer models by the formal languages they can recognize
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918045358751744 |
|---|---|
| author | Ryvkin, Leonid |
| author_facet | Ryvkin, Leonid |
| contents | This note is a survey of various results on the capabilities of unique hard attention transformers encoders (UHATs) to recognize formal languages. We distinguish between masked vs. non-masked, finite vs. infinite image and general vs. bilinear attention score functions. We recall some relations between these models, as well as a lower bound in terms of first-order logic and an upper bound in terms of circuit complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03370 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comparison of different Unique hard attention transformer models by the formal languages they can recognize Ryvkin, Leonid Machine Learning Computation and Language Formal Languages and Automata Theory This note is a survey of various results on the capabilities of unique hard attention transformers encoders (UHATs) to recognize formal languages. We distinguish between masked vs. non-masked, finite vs. infinite image and general vs. bilinear attention score functions. We recall some relations between these models, as well as a lower bound in terms of first-order logic and an upper bound in terms of circuit complexity. |
| title | Comparison of different Unique hard attention transformer models by the formal languages they can recognize |
| topic | Machine Learning Computation and Language Formal Languages and Automata Theory |
| url | https://arxiv.org/abs/2506.03370 |