EP 4154191 A1 20230329 - PSEUDO-ROUNDING IN ARTIFICIAL NEURAL NETWORKS
Title (en)
PSEUDO-ROUNDING IN ARTIFICIAL NEURAL NETWORKS
Title (de)
PSEUDO-RUNDUNG IN KÜNSTLICHEN NEURONALEN NETZEN
Title (fr)
PSEUDO-ARRONDISSEMENT DANS DES RÉSEAUX NEURONAUX ARTIFICIELS
Publication
Application
Priority
IB 2020054903 W 20200522
Abstract (en)
[origin: WO2021234437A1] A system for increasing quality of results of computations of an artificial neural network (ANN) by using complex rounding rules for parameters in the ANN is provided, the system comprising one or more processing units configured to: receive a plurality of first parameters for one or more neurons of ANN, the first parameters being of a first data type; and change the first parameters to second parameters of a second data type to obtain a plurality of the second parameters according to a rule in which a distance between at least one first parameter and corresponding second parameter is greater than a distance between the first parameter and a value of the second data type closest to the at least one first parameter. A distance between a vector of the first parameters and a vector of the second parameters is minimized.
IPC 8 full level
G06N 3/063 (2006.01)
CPC (source: EP)
G06N 3/063 (2013.01)
Citation (search report)
See references of WO 2021234437A1
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
Designated extension state (EPC)
BA ME
Designated validation state (EPC)
KH MA MD TN
DOCDB simple family (publication)
DOCDB simple family (application)
IB 2020054903 W 20200522; EP 20733010 A 20200522