EP 3815001 A1 20210505 - METHOD OF MODELLING FOR CHECKING THE RESULTS PROVIDED BY AN ARTIFICIAL NEURAL NETWORK AND OTHER ASSOCIATED METHODS
Title (en)
METHOD OF MODELLING FOR CHECKING THE RESULTS PROVIDED BY AN ARTIFICIAL NEURAL NETWORK AND OTHER ASSOCIATED METHODS
Title (de)
MODELLIERUNGSVERFAHREN ZUR ÜBERPRÜFUNG DER ERGEBNISSE EINES KÜNSTLICHEN NEURONALEN NETZES UND ANDERE ZUGEHÖRIGE VERFAHREN
Title (fr)
PROCEDE DE MODELISATION POUR LE CONTROLE DES RESULTATS FOURNIS PAR UN RESEAU DE NEURONES ARTIFICIELS ET AUTRES PROCEDES ASSOCIES
Publication
Application
Priority
- FR 1856012 A 20180629
- EP 2019067289 W 20190628
Abstract (en)
[origin: WO2020002573A1] An aspect of the invention relates to a method of modelling for checking the results provided by an artificial neural network comprising the following steps: - Generate an artificial neural network; - Train the artificial neural network on a training database; - Test the artificial neural network on at least one test datum dependent on a plurality of variables vi; so as to obtain a result R per test datum, the result R being dependent on the variables vi; - for each result R: · Approximate by a linear model a first function F1 dependent solely on the result R so as to obtain a second function F2 , the first function F1 and the second function F2 being dependent on the variables vi; · Simplify the second function F2 to obtain a third function F3 dependent on a smaller number of variables vi; · Apply to the third function F3 the inverse function of the first function F1 to obtain an operating model of the neural network.
IPC 8 full level
G06N 3/08 (2006.01); G06N 3/04 (2006.01); G06N 5/04 (2006.01)
CPC (source: EP US)
G06F 18/217 (2023.01 - US); G06N 3/045 (2023.01 - EP US); G06N 3/08 (2013.01 - EP US); G06N 5/045 (2013.01 - EP)
Citation (search report)
See references of WO 2020002573A1
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated extension state (EPC)
BA ME
DOCDB simple family (publication)
WO 2020002573 A1 20200102; CA 3104759 A1 20200102; EP 3815001 A1 20210505; FR 3083354 A1 20200103; SG 11202012987T A 20210225; US 2021279526 A1 20210909
DOCDB simple family (application)
EP 2019067289 W 20190628; CA 3104759 A 20190628; EP 19733051 A 20190628; FR 1856012 A 20180629; SG 11202012987T A 20190628; US 201917255824 A 20190628