Learning Families of Algebraic Structures from Text
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916118470328320 |
|---|---|
| author | Bazhenov, Nikolay Fokina, Ekaterina Rossegger, Dino Soskova, Alexandra Vatev, Stefan |
| author_facet | Bazhenov, Nikolay Fokina, Ekaterina Rossegger, Dino Soskova, Alexandra Vatev, Stefan |
| contents | We adapt the classical notion of learning from text to computable structure theory. Our main result is a model-theoretic characterization of the learnability from text for classes of structures. We show that a family of structures is learnable from text if and only if the structures can be distinguished in terms of their theories restricted to positive infinitary $Σ_2$ sentences. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05744 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Families of Algebraic Structures from Text Bazhenov, Nikolay Fokina, Ekaterina Rossegger, Dino Soskova, Alexandra Vatev, Stefan Logic 03C57, 03E15 F.4.1 We adapt the classical notion of learning from text to computable structure theory. Our main result is a model-theoretic characterization of the learnability from text for classes of structures. We show that a family of structures is learnable from text if and only if the structures can be distinguished in terms of their theories restricted to positive infinitary $Σ_2$ sentences. |
| title | Learning Families of Algebraic Structures from Text |
| topic | Logic 03C57, 03E15 F.4.1 |
| url | https://arxiv.org/abs/2402.05744 |