Unpublished conference/Abstract (Scientific congresses, symposiums and conference proceedings)
Learning Deterministic Finite Automata from Infinite Alphabets
Pellegrino, Gaetano; Hammerschmidt, Christian; Lin, Qin et al.
2016The 13th International Conference on Grammatical Inference
 

Files


Full Text
learning-deterministic-automata.pdf
Author preprint (232.79 kB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
passive learning; deterministic finite automata; regression
Abstract :
[en] We proposes an algorithm to learn automata infinite alphabets, or at least too large to enumerate. We apply it to define a generic model intended for regression, with transitions constrained by intervals over the alphabet. The algorithm is based on the Red \& Blue framework for learning from an input sample. We show two small case studies where the alphabets are respectively the natural and real numbers, and show how nice properties of automata models like interpretability and graphical representation transfer to regression where typical models are hard to interpret.
Research center :
Interdisciplinary
Disciplines :
Computer science
Author, co-author :
Pellegrino, Gaetano;  Delft University of Technology > Faculty of Electrical Engineering, Mathematics and Computer Science
Hammerschmidt, Christian ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Lin, Qin;  Delft University of Technology > Faculty of Electrical Engineering, Mathematics and Computer Science
Verwer, Sicco;  Delft University of Technology > Faculty of Electrical Engineering, Mathematics and Computer Science
External co-authors :
yes
Language :
English
Title :
Learning Deterministic Finite Automata from Infinite Alphabets
Publication date :
October 2016
Number of pages :
12
Event name :
The 13th International Conference on Grammatical Inference
Event date :
from 05-10-2016 to 07-10-2016
Audience :
International
Focus Area :
Computational Sciences
Name of the research project :
R-AGR-0685-11-Z
Funders :
FNR - Fonds National de la Recherche [LU]
Available on ORBilu :
since 09 September 2016

Statistics


Number of views
119 (3 by Unilu)
Number of downloads
376 (5 by Unilu)

Bibliography


Similar publications



Contact ORBilu