EP 3472713 A4 20200226 - SYSTEMS AND METHODS FOR GENERATING DATA EXPLANATIONS FOR NEURAL NETWORKS AND RELATED SYSTEMS
Title (en)
SYSTEMS AND METHODS FOR GENERATING DATA EXPLANATIONS FOR NEURAL NETWORKS AND RELATED SYSTEMS
Title (de)
SYSTEME UND VERFAHREN ZUR ERZEUGUNG VON DATENERKLÄRUNGEN FÜR NEURONALE NETZWERKE UND ZUGEHÖRIGE SYSTEME
Title (fr)
SYSTÈMES ET PROCÉDÉS DE GÉNÉRATION D'EXPLICATIONS DE DONNÉES POUR RÉSEAUX NEURONAUX ET SYSTÈMES APPARENTÉS
Publication
Application
Priority
US 2016038516 W 20160621
Abstract (en)
[origin: WO2017222505A1] A method for generating data explanations in a recursive cortical network includes receiving a set of evidence data at child feature nodes of a first layer of the recursive cortical network, setting a transformation configuration that directs messaging of evidence data and transformed data between layers of the network, performing a series of transformations on the evidence data according to the transformation configuration, the series including at least one forward transformation and at least one reverse transformation, and outputting the transformed evidence data.
IPC 8 full level
G06G 7/60 (2006.01); G06N 3/08 (2023.01); G06K 9/00 (2006.01); G06K 9/40 (2006.01)
CPC (source: EP US)
G06N 3/044 (2023.01 - EP); G06N 3/045 (2023.01 - EP); G06N 3/047 (2023.01 - EP); G06N 3/08 (2013.01 - EP US)
Citation (search report)
- [XI] US 2009006289 A1 20090101 - JAROS ROBERT G [US], et al
- [XI] LIN L ET AL: "A stochastic graph grammar for compositional object representation and recognition", PATTERN RECOGNITION, ELSEVIER, GB, vol. 42, no. 7, 1 July 2009 (2009-07-01), pages 1297 - 1307, XP026026922, ISSN: 0031-3203, [retrieved on 20081117], DOI: 10.1016/J.PATCOG.2008.10.033
- See also references of WO 2017222505A1
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 2017222505 A1 20171228; AU 2016410565 A1 20190124; AU 2022202492 A1 20220512; CA 3028919 A1 20171228; CA 3028919 C 20220426; CN 109643389 A 20190416; CN 109643389 B 20230822; EP 3472713 A1 20190424; EP 3472713 A4 20200226; JP 2019520655 A 20190718; JP 6761055 B2 20200923
DOCDB simple family (application)
US 2016038516 W 20160621; AU 2016410565 A 20160621; AU 2022202492 A 20220414; CA 3028919 A 20160621; CN 201680088615 A 20160621; EP 16906432 A 20160621; JP 2018567585 A 20160621