-
11.发明公开公开(公告)号：US20230163945A1
公开(公告)日：2023-05-25
申请号：US17954029
申请日：2022-09-27
Inventor： Seong Cheon PARK , Hyun Woo KIM , Jung Chan NA
CPC classification number: H04L9/008 , H04L9/0618 , G06F7/4876
Abstract: Provided are a method and apparatus for a hardware-based accelerated arithmetic operation on homomorphically encrypted messages. The method of performing hardware-based modular multiplication on homomorphically encrypted messages according to the present invention includes receiving a plurality of homomorphically encrypted messages expressed in a polynomial form and a modulus for modular multiplication, decomposing the modulus into a product of a plurality of disjoint factors through CRT operation, and extracting a divided ciphertext from a plurality of homomorphically encrypted messages based on each of the disjoint factors, performing NTT transformation on each coefficient of the divided ciphertext, performing a pointwise multiplication operation between result values of the NTT transformation, performing INTT transformation on a result value of the pointwise multiplication operation to obtain the divided ciphertext, and merging the divided ciphertext obtained in the performing of the INTT transformation through ICRT operation to generate an output ciphertext.
-
公开(公告)号：US20220215204A1
公开(公告)日：2022-07-07
申请号：US17570226
申请日：2022-01-06
Inventor： Ningombam Devarani Devi , Sungwon YI , Hyun Woo KIM , Hwa Jeon SONG , Byung Hyun YOO
IPC: G06K9/62
Abstract: Provided is a method for exploration based on curiosity and prioritization of experience data in multi-agent reinforcement learning, the method including the steps of: calculating a similarity between a policy of a first agent and a policy of a second agent and computing a final reward using the similarity; and performing clustering on a replay buffer using a result of calculating the similarity between the policy of the first agent and the policy of the second agent and performing sampling on data in the cluster.
-
13.发明申请公开(公告)号：US20220180071A1
公开(公告)日：2022-06-09
申请号：US17540768
申请日：2021-12-02
Inventor： Eui Sok CHUNG , Hyun Woo KIM , Gyeong Moon PARK , Jeon Gue PARK , Hwa Jeon SONG , Byung Hyun YOO , Ran HAN
IPC: G06F40/40 , G06F40/284 , G06F40/216
Abstract: Provided are a system and method for adaptive masking and non-directional language understanding and generation. The system for adaptive masking and non-directional language understanding and generation according to the present invention includes an encoder unit including an adaptive masking block for performing masking on training data, a language generator for restoring masked words, and an encoder for detecting whether or not the restored sentence construction words are original, and a decoder unit including a generation word position detector for detecting a position of a word to be generated next, a language generator for determining a word suitable for the corresponding position, and a non-directional training data generator for decoder training.
-
14.发明申请公开(公告)号：US20200219166A1
公开(公告)日：2020-07-09
申请号：US16711934
申请日：2019-12-12
Inventor： Hyun Woo KIM , Hwa Jeon SONG , Eui Sok CHUNG , Ho Young JUNG , Jeon Gue PARK , Yun Keun LEE
Abstract: A method and apparatus for estimating a user's requirement through a neural network which are capable of reading and writing a working memory and for providing fashion coordination knowledge appropriate for the requirement through the neural network using a long-term memory, by using the neural network using an explicit memory, in order to accurately provide the fashion coordination knowledge. The apparatus includes a language embedding unit for embedding a user's question and a previously created answer to acquire a digitized embedding vector; a fashion coordination knowledge creation unit for creating fashion coordination through the neural network having the explicit memory by using the embedding vector as an input; and a dialog creation unit for creating dialog content for configuring the fashion coordination through the neural network having the explicit memory by using the fashion coordination knowledge and the embedding vector an input.
-
公开(公告)号：US20200175119A1
公开(公告)日：2020-06-04
申请号：US16671773
申请日：2019-11-01
Inventor： Eui Sok CHUNG , Hyun Woo KIM , Hwa Jeon SONG , Ho Young JUNG , Byung Ok KANG , Jeon Gue PARK , Yoo Rhee OH , Yun Keun LEE
Abstract: Provided are sentence embedding method and apparatus based on subword embedding and skip-thoughts. To integrate skip-thought sentence embedding learning methodology with a subword embedding technique, a skip-thought sentence embedding learning method based on subword embedding and methodology for simultaneously learning subword embedding learning and skip-thought sentence embedding learning, that is, multitask learning methodology, are provided as methodology for applying intra-sentence contextual information to subword embedding in the case of subword embedding learning. This makes it possible to apply a sentence embedding approach to agglutinative languages such as Korean in a bag-of-words form. Also, skip-thought sentence embedding learning methodology is integrated with a subword embedding technique such that intra-sentence contextual information can be used in the case of subword embedding learning. A proposed model minimizes additional training parameters based on sentence embedding such that most training results may be accumulated in a subword embedding parameter.
-
Patent Agency Ranking
16.发明公开公开(公告)号：US20240256885A1
公开(公告)日：2024-08-01
申请号：US18517931
申请日：2023-11-22
Inventor： Byunghyun YOO , Hyun Woo KIM , Hwajeon SONG , Jeongmin YANG , Sungwon YI , Euisok CHUNG , Ran HAN
IPC: G06N3/092
CPC classification number: G06N3/092
Abstract: Provided is an exploration method based on reward decomposition in multi-agent reinforcement learning. The exploration method includes: generating a positive reward estimation model through neural network training based on training data including states of all agents, actions of all the agents, and a global reward true value; generating, for each of the agents, a first individual utility function based on the global reward true value and generating a second individual utility function using the positive reward estimation model; and determining an action of each of the agents using the first individual utility function and the second individual utility function based on the state of each of the agents.
-
17.发明公开公开(公告)号：US20240160859A1
公开(公告)日：2024-05-16
申请号：US18507953
申请日：2023-11-13
Inventor： Eui Sok CHUNG , Hyun Woo KIM , Jeon Gue PARK , Hwa Jeon SONG , Jeong Min YANG , Byung Hyun YOO , Ran HAN
IPC: G06F40/40
CPC classification number: G06F40/40
Abstract: The present invention relates to a multi-modality system for recommending multiple items using an interaction and a method of operating the same. The multi-modality system includes an interaction data preprocessing module that preprocesses an interaction data set and converts the preprocessed interaction data set into interaction training data; an item data preprocessing module that preprocesses item information data and converts the preprocessed item information data into item training data; and a learning module that includes a neural network model that is trained using the interaction training data and the item training data and outputs a result including a set of recommended items using a conversation context with a user as input.
-
公开(公告)号：US20230274127A1
公开(公告)日：2023-08-31
申请号：US18088428
申请日：2022-12-23
Inventor： Hyun Woo KIM , Jeon Gue PARK , Hwajeon SONG , Jeongmin YANG , Byunghyun YOO , Euisok CHUNG , Ran HAN
IPC: G06N3/045 , G06F18/15 , G06F18/213 , G06F18/22
CPC classification number: G06N3/045 , G06F18/15 , G06F18/213 , G06F18/22
Abstract: A concept based few-shot learning method is disclosed. The method includes estimating a task embedding corresponding to a task to be executed from support data that is a small amount of learning data; calculating a slot probability of a concept memory necessary for a task based on the task embedding; extracting features of query data that is test data, and of the support data; comparing local features for the extracted features with slots of a concept memory to extract a concept, and generating synthesis features to have maximum similarity to the extracted features through the slots of the concept memory; and calculating a task execution result from the synthesis feature and the extracted concept by applying the slot probability as a weight.
-
公开(公告)号：US20210374545A1
公开(公告)日：2021-12-02
申请号：US17332464
申请日：2021-05-27
Inventor： Hyun Woo KIM , Jeon Gue PARK , Hwa Jeon SONG , Yoo Rhee OH , Byung Hyun YOO , Eui Sok CHUNG , Ran HAN
Abstract: A knowledge increasing method includes calculating uncertainty of knowledge obtained from a neural network using an explicit memory, determining the insufficiency of the knowledge on the basis of the calculated uncertainty, obtaining additional data (learning data) for increasing insufficient knowledge, and training the neural network by using the additional data to autonomously increase knowledge.
-
公开(公告)号：US20210089904A1
公开(公告)日：2021-03-25
申请号：US17024062
申请日：2020-09-17
Inventor： Eui Sok CHUNG , Hyun Woo KIM , Hwa Jeon SONG , Yoo Rhee OH , Byung Hyun YOO , Ran HAN
Abstract: The present invention provides a new learning method where regularization of a conventional model is reinforced by using an adversarial learning method. Also, a conventional method has a problem of word embedding having only a single meaning, but the present invention solves a problem of the related art by applying a self-attention model.
-
-
-
-
-
-
-
-
-
Search Results
22
records
(took 0.022 seconds)
