Learning Picture Languages Using Dimensional Reduction

Kód výsledku v IS VaVaI

RIV/00216208:11320/23:10477026 - isvavai.cz

Výsledek na webu

https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=lXccYpSkil

DOI - Digital Object Identifier

10.4114/intartif.vol26iss71pp59-74

Jazyk výsledku

angličtina

Název v původním jazyce

Learning Picture Languages Using Dimensional Reduction

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Learning Picture Languages Using Dimensional Reduction

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Inteligencia Artificial

ISSN

1988-3064

e-ISSN

1988-3064

Svazek periodika

26

Číslo periodika v rámci svazku

71

Stát vydavatele periodika

ES - Španělské království

Počet stran výsledku

16

Strana od-do

59-74

Kód UT WoS článku

000984251300001

EID výsledku v databázi Scopus

2-s2.0-85159680544