公开(公告)号：US20240256895A1

公开(公告)日：2024-08-01

申请号：US18343073

申请日：2023-06-28

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  Korea Advanced Institute of Science and Technology

Inventor： Jonghoon YOON ,  Geon PARK ,  Jaehong YOON ,  Sung Ju HWANG ,  Wonyong JEONG

IPC: G06N3/098 ,  G06N3/045

CPC classification number: G06N3/098 ,  G06N3/045

Abstract: A method and device with federated learning of neural network models are disclosed. A method includes: receiving weights of respective clients, wherein each weight has a respectively corresponding precision that is initially an inherent precision; using a dequantizer to change the weights such that the precisions thereof are changed from the inherent precisions to a same reference precision; determining masks respectively corresponding to the weights based on the inherent precisions; based on the masks, determining an integrated weight by merging the weights having the reference precision; and quantizing the integrated weight to generate quantized weights having the inherent precisions, respectively, and transmitting the quantized weights to the clients.

公开(公告)号：US20210256374A1

公开(公告)日：2021-08-19

申请号：US17145876

申请日：2021-01-11

Applicant: Samsung Electronics Co., Ltd ,  Korea Advanced Institute of Science and Technology

Inventor： Sung Ju HWANG ,  Saehoon KIM ,  Eunho YANG ,  Jaehong YOON

IPC: G06N3/08 ,  G06N3/04

Abstract: A processor-implemented neural network method includes: determining an adaptive parameter and an adaptive mask of a current task to be learned among a plurality of tasks of a neural network; determining a model parameter of the current task based on the adaptive parameter, the adaptive mask, and a shared parameter of the plurality of tasks; and training the model parameter and an adaptive parameter of a previous task with respect to the current task, wherein the adaptive parameter of the previous task and the shared parameter are trained with respect to the previous task.

公开(公告)号：US20220366240A1

公开(公告)日：2022-11-17

申请号：US17731710

申请日：2022-04-28

Applicant: AITRICS CO., LTD. ,  KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Sung Ju HWANG ,  Wonyong JEONG ,  Ha Yeon LEE ,  Geon PARK ,  Eun Young HYUNG

IPC: G06N3/08

Abstract: Disclosed herein are an apparatus and method for task-adaptive neural network retrieval based on meta-contrastive learning. The apparatus for task-adaptive neural network retrieval based on meta-contrastive learning includes: memory configured to store a database including a learning model pool consisting of a plurality of datasets and neural networks pre-trained on the datasets and also store a program for task-adaptive neural network retrieval based on meta-contrastive learning; and a controller configured to perform task-adaptive neural network retrieval based on meta-contrastive learning by executing the program. In this case, the controller learns a cross-modal latent space for datasets and neural networks trained on the datasets by calculating the similarity between each dataset and a neural network trained on the dataset while considering constraints included in any one task previously selected from the database, thereby retrieving an optimal neural network.

公开(公告)号：US20240412077A1

公开(公告)日：2024-12-12

申请号：US18486183

申请日：2023-10-13

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Sung Ju HWANG ,  Minseon KIM ,  Hyeonjeong HA

IPC: G06N3/0985 ,  G06N3/094

Abstract: There is provided an adversarial meta-learning method. The method comprises: transforming an obtained original image for learning to generate a first transformed image and a second transformed image; generating a first vector from the first transformed image using the first encoder; generating a second vector from the second transformed image using the second encoder; generating a first noise image and a second noise image by adding noise for adversarial attack to the original image for learning using the first vector, the second vector, and the original image for learning; and repeating obtaining at least one of the first noise image or the second noise image as the original image for learning and generating the first transformed image and the second transformed image.

公开(公告)号：US20240143940A1

公开(公告)日：2024-05-02

申请号：US18544209

申请日：2023-12-18

Applicant: 42Maru Inc. ,  Korea Advanced Institute of Science and Technology

Inventor： Dong Hwan KIM ,  Sung Ju HWANG ,  Seanie LEE ,  Dong Bok LEE ,  Woo Tae JEONG ,  Han Su KIM ,  You Kyung KWON ,  Hyun Ok KIM

IPC: G06F40/35 ,  G06N3/045 ,  G06N3/08 ,  G06N5/04

CPC classification number: G06F40/35 ,  G06N3/045 ,  G06N3/08 ,  G06N5/04

Abstract: The present invention relates to a context-based QA generation architecture, and an object of the present invention is to generate diverse QA pairs from a single context. To achieve the object, the present invention includes a latent variable generating network including at least one encoder and an artificial neural network (Multi-Layer Perceptron: MLP) and configured to train the artificial neural network using a first context, a first question, and a first answer, and generate a second question latent variable and a second answer latent variable by applying the trained artificial neural network to a second context, an answer generating network configured to generate a second answer by decoding the second answer latent variable, and a question generating network configured to generate a second question based on a second context and the second answer.

公开(公告)号：US20240412488A1

公开(公告)日：2024-12-12

申请号：US18485377

申请日：2023-10-12

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Sung Ju HWANG ,  Minseon KIM ,  Hyeonjeong HA ,  Sooel SON

IPC: G06V10/774 ,  G06F16/532 ,  G06V10/74 ,  G06V10/764

Abstract: In accordance with an aspect of the present disclosure, there is provided an adversarial self-supervised learning method for an encoder. The method comprises selecting a target image of an original image for training from an image group included in a previously collected dataset; generating a noise image by combining the original image for training with noise using the original image for training and the target image; and training the encoder using the noise image and the original image for training.

公开(公告)号：US20210365792A1

公开(公告)日：2021-11-25

申请号：US17328124

申请日：2021-05-24

Applicant: Samsung Electronics Co., Ltd. ,  Korea Advanced Institute of Science and Technology

Inventor： Sangil JUNG ,  Sung Ju HWANG ,  Changin CHOI ,  Changyong SON

IPC: G06N3/08 ,  G06N5/04 ,  G06N3/10

Abstract: Disclosed are a neural network-based training method, inference method and apparatus. The neural network-based inference method includes receiving a quantization level for quantizing a weight of a neural network and an activation value that is processed by the neural network, receiving a weight quantized based on the quantization level, generating a quantized activation value by quantizing the activation value based on the quantization level, and performing inference based on the quantized weight and the quantized activation value.

公开(公告)号：US20210241098A1

公开(公告)日：2021-08-05

申请号：US17119381

申请日：2020-12-11

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  Korea Advanced Institute of Science and Technology

Inventor： Seong-Jin PARK ,  Sung Ju HWANG ,  Seungju HAN ,  Insoo KIM ,  Jiwon BAEK ,  Jaejoon HAN

IPC: G06N3/08 ,  G06K9/62 ,  G06F17/18

Abstract: A processor-implemented neural network method includes: extracting, by a feature extractor of a neural network, a plurality of training feature vectors corresponding to a plurality of training class data of each of a plurality of classes including a first class and a second class; determining, by a feature sample generator of the neural network, an additional feature vector of the second class based on a mean vector and a variation vector of the plurality of training feature vectors of each of the first class and the second class; and training a class vector of the second class included in a classifier of the neural network based on the additional feature vector and the plurality of training feature vectors of the second class.