Simulation of pattern recognition systém via modular neural networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17310%2F11%3AA11010RU" target="_blank" >RIV/61988987:17310/11:A11010RU - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61988987:17310/11:A14010RU

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Simulation of pattern recognition systém via modular neural networks

Popis výsledku v původním jazyce

It is the purpose of the present paper to suggest an approach to utilization of mathematical models of a classification system for pattern recognition. Pattern recognition has a long history but has recently become much more widespread as the automated capture of signals and images has become cheaper. Very many of the applications of neural networks are to classification, and so are within the field of pattern recognition. This article describes a classification system for pattern recognition based on artificial neural networks with modular architecture. We use a three layer feedforward network model that is learned with the backpropagation algorithm for all experiments. Our experimental recognition objects were digits and their type fonts. We also propose outline further development on this topic in conclusion.

Název v anglickém jazyce

Simulation of pattern recognition systém via modular neural networks

Popis výsledku anglicky

It is the purpose of the present paper to suggest an approach to utilization of mathematical models of a classification system for pattern recognition. Pattern recognition has a long history but has recently become much more widespread as the automated capture of signals and images has become cheaper. Very many of the applications of neural networks are to classification, and so are within the field of pattern recognition. This article describes a classification system for pattern recognition based on artificial neural networks with modular architecture. We use a three layer feedforward network model that is learned with the backpropagation algorithm for all experiments. Our experimental recognition objects were digits and their type fonts. We also propose outline further development on this topic in conclusion.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2011

Kód důvěrnosti údajů

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

Název statě ve sborníku

Simulation of pattern recognition systém via modular neural networks

ISBN

978-80-89313-51-8

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

—

Název nakladatele

STU Bratislava

Místo vydání

—

Místo konání akce

Bratislava

Datum konání akce

1. 2. 2011

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—