Generating adaptation rule-specific neural network

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10474027" target="_blank" >RIV/00216208:11320/23:10474027 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=b-~HZgiNzQ" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=b-~HZgiNzQ</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10009-023-00725-y" target="_blank" >10.1007/s10009-023-00725-y</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Generating adaptation rule-specific neural network

Popis výsledku v původním jazyce

There have been a number of approaches to employ neural networks in self-adaptive systems; in many cases, generic neural networks and deep learning are utilized for this purpose. When this approach is to be applied to improve an adaptation process initially driven by logical adaptation rules, the problem is that (1) these rules represent a significant and tested body of domain knowledge, which may be lost if they are replaced by a neural network, and (2) the learning process is inherently demanding given the black-box nature and the number of weights in generic neural networks to be trained. In this paper, we introduce the rule-specific neural network method that makes it possible to transform the guard of an adaptation rule into a rule-specific neural network, the composition of which is driven by the structure of the logical predicates in the guard. Our experiments confirmed that the black box effect is eliminated, the number of weights is significantly reduced, and much faster learning is achieved whilst the accuracy is preserved. This text is an extended version of the paper presented at the ISOLA 2022 conference (Bureš et al. in Proceedings of ISOLA 2022, Rhodes, Greece, pp. 215-230, 2022).

Název v anglickém jazyce

Generating adaptation rule-specific neural network

Popis výsledku anglicky

There have been a number of approaches to employ neural networks in self-adaptive systems; in many cases, generic neural networks and deep learning are utilized for this purpose. When this approach is to be applied to improve an adaptation process initially driven by logical adaptation rules, the problem is that (1) these rules represent a significant and tested body of domain knowledge, which may be lost if they are replaced by a neural network, and (2) the learning process is inherently demanding given the black-box nature and the number of weights in generic neural networks to be trained. In this paper, we introduce the rule-specific neural network method that makes it possible to transform the guard of an adaptation rule into a rule-specific neural network, the composition of which is driven by the structure of the logical predicates in the guard. Our experiments confirmed that the black box effect is eliminated, the number of weights is significantly reduced, and much faster learning is achieved whilst the accuracy is preserved. This text is an extended version of the paper presented at the ISOLA 2022 conference (Bureš et al. in Proceedings of ISOLA 2022, Rhodes, Greece, pp. 215-230, 2022).

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

<a href="/cs/project/GC20-24814J" target="_blank" >GC20-24814J: FluidTrust - popora důvěry pomocí dynamicky proměnlivého řízení přistupu k datům a zdrojům v systémech Průmyslu 4.0</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název periodika

International Journal on Software Tools for Technology Transfer

ISSN

1433-2779

e-ISSN

1433-2787

Svazek periodika

25

Číslo periodika v rámci svazku

neuveden

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

14

Strana od-do

733-746

Kód UT WoS článku

001098098200001

EID výsledku v databázi Scopus

2-s2.0-85175982447