Record link: 
http://hdl.handle.net/20.500.12708/208504
https://doi.org/10.34726/8204
-
Title: 
Learning Families of Algebraic Structures from Text
en
Citation: 
Bazhenov, N., Fokina, E., Rossegger, D., Soskova, A., & Vatev, S. (2024). Learning Families of Algebraic Structures from Text. In L. L. Patey, E. Pimentel, L. Galeotti, & F. Manea (Eds.), Twenty Years of Theoretical and Practical Synergies : 20th Conference on Computability in Europe, CiE 2024, Amsterdam, The Netherlands, July 8–12, 2024, Proceedings (pp. 166–178). Springer. https://doi.org/10.34726/8204
-
reposiTUm DOI: 
10.34726/8204
-
Publisher DOI: 
10.1007/978-3-031-64309-5_14
-
Publication Type: 
Inproceedings - Full-Paper Contribution
en
Language: 
English
-
Authors: 
Bazhenov, Nikolay 
Fokina, Ekaterina 
Rossegger, Dino 
Soskova, Alexandra 
Vatev, Stefan 
-
Organisational Unit: 
E104-02 - Forschungsbereich Computational Logic 
-
Published in: 
Twenty Years of Theoretical and Practical Synergies : 20th Conference on Computability in Europe, CiE 2024, Amsterdam, The Netherlands, July 8–12, 2024, Proceedings 
-
ISBN: 
978-3-031-64309-5
-
Volume: 
14773
-
Date (published): 
2-Jul-2024
-
Event name: 
20th Conference on Computability in Europe 
en
Event date: 
8-Jul-2024 - 12-Jul-2024
-
Event place: 
Amsterdam, Netherlands (the)
-
Number of Pages: 
13
-
Publisher: 
Springer, Cham
-
Peer reviewed: 
Yes
-
Keywords: 
Algorithmic learning; Infinitary logic; Scott topology
en
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 Σ2 sentences.
en
Project title: 
Algorithmische Komplexität von Strukturen und deren Äquivalenzrelationen: 101026834 (European Commission) 
-
Research Areas: 
Mathematical and Algorithmic Foundations: 100%
-
Science Branch: 
1020 - Informatik: 5%
1010 - Mathematik: 95%
-
License: 
In Copyright
en
Appears in Collections:
Conference Paper

Fulltext (Accepted Version)
Adobe PDF
(195.02 kB)
arXiv preprint
In Copyright
Embargo. Accessible from 03.07.2025
Show full item record

Page view(s)

40
checked on Jan 14, 2025

Download(s)

4
checked on Jan 14, 2025

Google ScholarTM

Check