Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020089597 - AN EXPLAINABLE ARTIFICIAL INTELLIGENCE MECHANISM

Publication Number WO/2020/089597
Publication Date 07.05.2020
International Application No. PCT/GB2019/053045
International Filing Date 29.10.2019
IPC
G06N 5/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
04Inference methods or devices
G06Q 40/02 2012.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
40Finance; Insurance; Tax strategies; Processing of corporate or income taxes
02Banking, e.g. interest calculation, credit approval, mortgages, home banking or on-line banking
CPC
G06N 5/048
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
04Inference methods or devices
048Fuzzy inferencing
G06Q 40/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
40Finance; Insurance; Tax strategies; Processing of corporate or income taxes
Applicants
  • LOGICAL GLUE LIMITED [GB]/[GB]
Inventors
  • HAGRAS, Hani
  • GARCIA, Gonzalo Ruiz
Agents
  • IP21 LIMITED
Priority Data
1817684.230.10.2018GB
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) AN EXPLAINABLE ARTIFICIAL INTELLIGENCE MECHANISM
(FR) MÉCANISME D'INTELLIGENCE ARTIFICIELLE EXPLICABLE
Abstract
(EN)
A method of determining and explaining an artificial intelligence, AI, system employing an opaque model from a local or global point of view, the method comprising the steps of: providing an input and a corresponding output of the opaque model; sampling the opaque model around the input to generate training data samples; performing feature selection to determine dominant features; generating a Type-2 Fuzzy Logic Model, FLM; training the Type-2 FLM with the training data samples; and inputting the input into the Type-2 FLM to provide an explanation of the output from the opaque model.
(FR)
L'invention concerne un procédé permettant de déterminer et d’expliquer un système d'intelligence artificielle (AI) utilisant un modèle opaque à partir d'un point de vue local ou global, ledit procédé comprenant les étapes consistant à : fournir une entrée et une sortie correspondante du modèle opaque ; échantillonner le modèle opaque autour de l'entrée afin de générer des échantillons de données d'apprentissage ; effectuer une sélection de caractéristiques afin de déterminer les caractéristiques dominantes ; générer un modèle de logique floue de type 2 (FLM) ; apprendre le FLM de type 2 avec les échantillons de données d'apprentissage ; et saisir l’entrée dans le FLM de type 2 afin de fournir une explication de la sortie du modèle opaque.
Latest bibliographic data on file with the International Bureau