Rules extraction from neural networks trained on multimedia data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F19%3A00512089" target="_blank" >RIV/67985807:_____/19:00512089 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21240/19:00334955 RIV/68407700:21340/19:00334955

Výsledek na webu

<a href="http://ceur-ws.org/Vol-2473/paper4.pdf" target="_blank" >http://ceur-ws.org/Vol-2473/paper4.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Rules extraction from neural networks trained on multimedia data

Popis výsledku v původním jazyce

Since the universal approximation property of artificial neural networks was discovered in the late 1980s, i.e., their capability to arbitrarily well approximate nearly arbitrary relationships and dependences, a full exploitation of this property has been always hindered by the very low human-comprehensibility of the purely numerical representation that neural networks use for such relationships and dependences. The mainstream of attempts to mitigate that incomprehensibility are methods extracting, from the numerical representation, rules of some formal logic, which are in general viewed as human-comprehensible. Many dozens of such methods have already been proposed since the 1980s, differing in a number of diverse aspects. Due to that diversity, and also due to a close connection of the semantics of extracted rules to the repsective application domain, no rules extraction methods have ever become a standard, and it is always necessary to select a suitable method for the considered domain. Here, rules extraction from trained neural networks is employed for multimedia data, which is an increasingly important but also increasingly complex kind of data. Three particular rules extraction methods are considered and applied to the modalities recognized text data and the speech acoustic data, both of them with different subsets of features. A detailed comparison of the performance of the considered methods on those datasets is presented, and a statistical analysis of the obtained results is performed.n

Název v anglickém jazyce

Rules extraction from neural networks trained on multimedia data

Popis výsledku anglicky

Since the universal approximation property of artificial neural networks was discovered in the late 1980s, i.e., their capability to arbitrarily well approximate nearly arbitrary relationships and dependences, a full exploitation of this property has been always hindered by the very low human-comprehensibility of the purely numerical representation that neural networks use for such relationships and dependences. The mainstream of attempts to mitigate that incomprehensibility are methods extracting, from the numerical representation, rules of some formal logic, which are in general viewed as human-comprehensible. Many dozens of such methods have already been proposed since the 1980s, differing in a number of diverse aspects. Due to that diversity, and also due to a close connection of the semantics of extracted rules to the repsective application domain, no rules extraction methods have ever become a standard, and it is always necessary to select a suitable method for the considered domain. Here, rules extraction from trained neural networks is employed for multimedia data, which is an increasingly important but also increasingly complex kind of data. Three particular rules extraction methods are considered and applied to the modalities recognized text data and the speech acoustic data, both of them with different subsets of features. A detailed comparison of the performance of the considered methods on those datasets is presented, and a statistical analysis of the obtained results is performed.n

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/GA18-18080S" target="_blank" >GA18-18080S: Objevování znalostí v datech o aktivitě člověka založené na fúzi</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

ITAT 2019: Information Technologies – Applications and Theory

ISBN

—

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

10

Strana od-do

26-35

Název nakladatele

Technical University & CreateSpace Independent Publishing

Místo vydání

Aachen

Místo konání akce

Donovaly

Datum konání akce

20. 9. 2019

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—