TRAINING A NEURAL NETWORK

A method (100) performed by a central processor of training a first neural network to classify medical data comprises receiving (102) a first parameter indicative of a weight in the first neural network, the first parameter being obtained during training of the first neural network on a first set of...

Full description

Saved in:
Bibliographic Details
Main Author MANKE, Dirk
Format Patent
LanguageEnglish
French
German
Published 21.08.2019
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DIAGNOSIS
HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA
HUMAN NECESSITIES
HYGIENE
IDENTIFICATION
INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS
MEDICAL OR VETERINARY SCIENCE
PHYSICS
SURGERY
Online AccessGet full text

Cover

More Information
Summary:A method (100) performed by a central processor of training a first neural network to classify medical data comprises receiving (102) a first parameter indicative of a weight in the first neural network, the first parameter being obtained during training of the first neural network on a first set of medical data. The method further comprises combining (104) the first parameter with a second parameter to determine an update to the weight, the second parameter being indicative of a respective weight in a second neural network. The method (100) further comprises sending (106) the update to the weight to the first neural network.
Bibliography:Application Number: EP20180156991