公开(公告)号：US20230237355A1

公开(公告)日：2023-07-27

申请号：US18125897

申请日：2023-03-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jongha Ryu ,  Yoo Jin Choi ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G06N7/01 ,  G06N20/00

CPC classification number: G06N7/01 ,  G06N20/00 ,  G06N5/04

Abstract: A method and system are herein disclosed. The method includes developing a joint latent variable model having a first variable, a second variable, and a joint latent variable representing common information between the first and second variables; generating a variational posterior of the joint latent variable model; training the variational posterior; performing inference of the first variable from the second variable based on the variational posterior, wherein performing the inference comprises conditionally generating the first variable from the second variable; and extracting common information between the first variable and the second variable, wherein extracting the common information comprises adding a regularization term to a loss function.

公开(公告)号：US11615317B2

公开(公告)日：2023-03-28

申请号：US16886429

申请日：2020-05-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Jongha Ryu ,  Mostafa El-Khamy ,  Jungwon Lee ,  Young-Han Kim

IPC: G06N20/20 ,  G06N3/088 ,  G06N3/04

Abstract: A system and method for operating a neural network. In some embodiments, the neural network includes a variational autoencoder, and the training of the neural network includes training the variational autoencoder with a plurality of samples of a first random variable; and a plurality of samples of a second random variable, the plurality of samples of the first random variable and the plurality of samples of the second random variable being unpaired, the training of the neural network including updating weights in the neural network based on a first loss function, the first loss function being based on a measure of deviation from consistency between: a conditional generation path from the first random variable to the second random variable, and a conditional generation path from the second random variable to the first random variable.

公开(公告)号：US20210319326A1

公开(公告)日：2021-10-14

申请号：US16886429

申请日：2020-05-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Jongha Ryu ,  Mostafa El-Khamy ,  Jungwon Lee ,  Young-Han Kim

IPC: G06N3/08 ,  G06N3/04

Abstract: A system and method for operating a neural network. In some embodiments, the neural network includes a variational autoencoder, and the training of the neural network includes training the variational autoencoder with a plurality of samples of a first random variable; and a plurality of samples of a second random variable, the plurality of samples of the first random variable and the plurality of samples of the second random variable being unpaired, the training of the neural network including updating weights in the neural network based on a first loss function, the first loss function being based on a measure of deviation from consistency between: a conditional generation path from the first random variable to the second random variable, and a conditional generation path from the second random variable to the first random variable.

公开(公告)号：US11620555B2

公开(公告)日：2023-04-04

申请号：US16373913

申请日：2019-04-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jongha Ryu ,  Yoo Jin Choi ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G06N7/00 ,  G06N20/00 ,  G06N5/04

Abstract: A method and system are herein disclosed. The method includes developing a joint latent variable model having a first variable, a second variable, and a joint latent variable representing common information between the first and second variables, generating a variational posterior of the joint latent variable model, training the variational posterior, and performing inference of the first variable from the second variable based on the variational posterior.