| Autor: |
Bazhenov, Nikolay, Fokina, Ekaterina, Rossegger, Dino, Soskova, Alexandra, Vatev, Stefan |
| Rok vydání: |
2024 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
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 $\Sigma_2$ sentences. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
