Modeling deduction with recurrent neural networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60460709%3A41110%2F12%3A54653" target="_blank" >RIV/60460709:41110/12:54653 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Modeling deduction with recurrent neural networks

Popis výsledku v původním jazyce

In the paper we focus on reasoning with IF?THEN rules in propositional fragment of predicate calculus and on its modeling with neural networks. At first IF THEN deduction from facts is defined. Then it is proved that for any non-contradictory set of IF-THEN rules and literals (representing facts) there exists a layered recurrent network with 2 hidden layers that can specify all IF THEN deducible literals. If we denote the set of all literal IF-THEN consequences as D0 and the set of all literal logical consequences as D, then obviously D0?D. Thus D0 can be considered to be an approximation of D. Using the designed network for simulation of contradiction proof, the approximation D0 may be easily refined. Furthermore, the network may also be used for determination of D. However, the algorithm that realizes necessary network computations has exponential complexity.

Název v anglickém jazyce

Modeling deduction with recurrent neural networks

Popis výsledku anglicky

In the paper we focus on reasoning with IF?THEN rules in propositional fragment of predicate calculus and on its modeling with neural networks. At first IF THEN deduction from facts is defined. Then it is proved that for any non-contradictory set of IF-THEN rules and literals (representing facts) there exists a layered recurrent network with 2 hidden layers that can specify all IF THEN deducible literals. If we denote the set of all literal IF-THEN consequences as D0 and the set of all literal logical consequences as D, then obviously D0?D. Thus D0 can be considered to be an approximation of D. Using the designed network for simulation of contradiction proof, the approximation D0 may be easily refined. Furthermore, the network may also be used for determination of D. However, the algorithm that realizes necessary network computations has exponential complexity.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

BD - Teorie informace

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2012

Kód důvěrnosti údajů

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

Název periodika

Neural Network World

ISSN

1210-0552

e-ISSN

—

Svazek periodika

22

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

15

Strana od-do

123-137

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—