arXiv · 2402.05744
Learning Families of Algebraic Structures from Text
Abstract
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Nikolay Bazhenov, Ekaterina Fokina, Dino Rossegger, Alexandra Soskova, Stefan Vatev. 2024-02-08. Learning Families of Algebraic Structures from Text. https://arxiv.org/abs/2402.05744
Cite the original work for its findings. Save a collection to share your selection of sources.