Processing

Please wait...

Settings

Settings

Goto Application

1. WO2018141942 - CLASSIFIER TRAINING

Publication Number WO/2018/141942
Publication Date 09.08.2018
International Application No. PCT/EP2018/052719
International Filing Date 02.02.2018
IPC
G06K 9/62 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
CPC
G06K 9/6267
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 20/20
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
20Ensemble learning
Applicants
  • KONINKLIJKE PHILIPS N.V. [NL]/[NL]
Inventors
  • QADIR, Ashequl
  • DATLA, Vivek, Varma
  • LEE, Kathy, Mi, Young
  • AL HASAN, Sheikh, Sadid
  • FARRI, Oladimeji, Feyisetan
Agents
  • VAN VELZEN, Maaike, Mathilde
  • DE HAAN, Poul, Erik
Priority Data
62/45408503.02.2017US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) CLASSIFIER TRAINING
(FR) APPRENTISSAGE DE CLASSIFICATEUR
Abstract
(EN) Methods and systems for training a classifier. The system includes two or more classifiers that can each analyze features extracted from inputted data. The system may determine a true label for the input data based on the first label and the second label, and retrain at least one of the first classifier and the second classifier based on a training example comprising the input data and the true label.
(FR) L'invention porte sur des procédés et des systèmes pour entraîner un classificateur. Le système comprend au moins deux classificateurs qui peuvent chacun analyser des caractéristiques extraites de données entrées. Le système peut déterminer une véritable étiquette pour les données d'entrée sur la base de la première étiquette et de la seconde étiquette, et renvoyer au moins le premier classificateur et/ou le second classificateur sur la base d'un exemple d'apprentissage comprenant les données d'entrée et la véritable étiquette.
Related patent documents
Latest bibliographic data on file with the International Bureau