公开(公告)号：US20230153066A1

公开(公告)日：2023-05-18

申请号：US17702242

申请日：2022-03-23

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jong-Ryul LEE ,  Yong-Hyuk MOON ,  Yong-Ju LEE

IPC: G06F7/499 ,  G06F7/523 ,  G06F7/50 ,  G06N3/04

CPC classification number: G06F7/49947 ,  G06F7/50 ,  G06F7/523 ,  G06N3/04

Abstract: Disclosed herein is a method for measuring the weight of a discrete entity, performed in a neural network model configured with multiple layers, the method including receiving data configured with the indices of discrete entities, converting the data into embedding vectors corresponding to respective indices through an embedding layer, generating a masked vector through element-wise multiplication between a mask vector and the embedding vector, calculating a loss using output based on the masked vector, and training the model based on the loss.