EP 3782079 A4 20220119 - MODEL INTERPRETATION
Title (en)
MODEL INTERPRETATION
Title (de)
MODELLINTERPRETATION
Title (fr)
INTERPRÉTATION DE MODÈLE
Publication
Application
Priority
- US 201815959040 A 20180420
- US 201815959030 A 20180420
- US 2019026331 W 20190408
Abstract (en)
[origin: WO2019204072A1] Input data associated with a machine learning model is classified into a plurality of clusters. A plurality of linear surrogate models are generated. One of the plurality of linear surrogate models corresponds to one of the plurality of clusters. A linear surrogate model is configured to output a corresponding prediction based on input data associated with a corresponding cluster. Prediction data associated with the machine learning model and prediction data associated with the plurality of linear surrogate models are outputted.
IPC 8 full level
G06N 5/04 (2006.01); G06N 5/00 (2006.01); G06N 7/00 (2006.01); G06N 20/20 (2019.01)
CPC (source: EP)
G06N 5/01 (2023.01); G06N 5/045 (2013.01); G06N 7/01 (2023.01); G06N 20/20 (2019.01)
Citation (search report)
- [A] US 2015379429 A1 20151231 - LEE POLLY PO YEE [US], et al
- [A] US 2003212520 A1 20031113 - CAMPOS MARCOS M [US], et al
- [X] HALL PATRICK ET AL: "Machine Learning Interpretability with H2O Driverless AI", 17 April 2018 (2018-04-17), XP055871801, Retrieved from the Internet <URL:https://web.archive.org/web/20180417181338if_/http://docs.h2o.ai:80/driverless-ai/latest-stable/docs/booklets/MLIBooklet.pdf> [retrieved on 20211210]
- See also references of WO 2019204072A1
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
DOCDB simple family (publication)
WO 2019204072 A1 20191024; CN 112154459 A 20201229; EP 3782079 A1 20210224; EP 3782079 A4 20220119; SG 11202009599S A 20201029
DOCDB simple family (application)
US 2019026331 W 20190408; CN 201980026981 A 20190408; EP 19788527 A 20190408; SG 11202009599S A 20190408