Learning Picture Languages Using Dimensional Reduction

One-dimensional (string) formal languages and their learning have been studied in considerable depth. However, the knowledge of their two-dimensional (picture) counterpart, which retains similar importance, is lacking. We investigate the problem of learning formal two-dimensional picture languages...

Full description

Bibliographic Details
Main Authors: David Kubon, František Mráz, Ivan Rychtera
Format: Article
Language:English
Published: Asociación Española para la Inteligencia Artificial 2023-04-01
Series:Inteligencia Artificial
Subjects:
Online Access:https://journal.iberamia.org/index.php/intartif/article/view/1051
_version_ 1797672237048791040
author David Kubon
František Mráz
Ivan Rychtera
author_facet David Kubon
František Mráz
Ivan Rychtera
author_sort David Kubon
collection DOAJ
description One-dimensional (string) formal languages and their learning have been studied in considerable depth. However, the knowledge of their two-dimensional (picture) counterpart, which retains similar importance, is lacking. We investigate the problem of learning formal two-dimensional picture languages by applying learning methods for one-dimensional (string) languages. We formalize the transcription process from a two-dimensional input picture into a string and propose a few adaptations to it. These proposals are then tested in a series of experiments, and their outcomes are compared. Finally, these methods are applied to a practical problem and an automaton for recognizing a part of the MNIST dataset is learned. The obtained results show improvements in the topic and the potential to use the learning of automata in fitting problems.
first_indexed 2024-03-11T21:27:07Z
format Article
id doaj.art-a3aba76ea3264146a5baafb66d86e45d
institution Directory Open Access Journal
issn 1137-3601
1988-3064
language English
last_indexed 2024-03-11T21:27:07Z
publishDate 2023-04-01
publisher Asociación Española para la Inteligencia Artificial
record_format Article
series Inteligencia Artificial
spelling doaj.art-a3aba76ea3264146a5baafb66d86e45d2023-09-27T22:03:04ZengAsociación Española para la Inteligencia ArtificialInteligencia Artificial1137-36011988-30642023-04-01267110.4114/intartif.vol26iss71pp59-74Learning Picture Languages Using Dimensional ReductionDavid Kubon0František Mráz1Ivan Rychtera2Charles University, Czech RepublicCharles University, Czech RepublicCharles University, Czech Republic One-dimensional (string) formal languages and their learning have been studied in considerable depth. However, the knowledge of their two-dimensional (picture) counterpart, which retains similar importance, is lacking. We investigate the problem of learning formal two-dimensional picture languages by applying learning methods for one-dimensional (string) languages. We formalize the transcription process from a two-dimensional input picture into a string and propose a few adaptations to it. These proposals are then tested in a series of experiments, and their outcomes are compared. Finally, these methods are applied to a practical problem and an automaton for recognizing a part of the MNIST dataset is learned. The obtained results show improvements in the topic and the potential to use the learning of automata in fitting problems. https://journal.iberamia.org/index.php/intartif/article/view/1051LearningGrammatical inferenceAutomataFormal languagesPicture languages
spellingShingle David Kubon
František Mráz
Ivan Rychtera
Learning Picture Languages Using Dimensional Reduction
Inteligencia Artificial
Learning
Grammatical inference
Automata
Formal languages
Picture languages
title Learning Picture Languages Using Dimensional Reduction
title_full Learning Picture Languages Using Dimensional Reduction
title_fullStr Learning Picture Languages Using Dimensional Reduction
title_full_unstemmed Learning Picture Languages Using Dimensional Reduction
title_short Learning Picture Languages Using Dimensional Reduction
title_sort learning picture languages using dimensional reduction
topic Learning
Grammatical inference
Automata
Formal languages
Picture languages
url https://journal.iberamia.org/index.php/intartif/article/view/1051
work_keys_str_mv AT davidkubon learningpicturelanguagesusingdimensionalreduction
AT frantisekmraz learningpicturelanguagesusingdimensionalreduction
AT ivanrychtera learningpicturelanguagesusingdimensionalreduction