-
公开(公告)号：US20240203398A1
公开(公告)日：2024-06-20
申请号：US18540594
申请日：2023-12-14
Inventor： Jeom Ja KANG , Kiyoung PARK , Hwajeon SONG
Abstract: Disclosed herein is a voice recognition system with an enhanced summarization function according to the present invention. The voice recognition system include: an audio feature extractor configured to extract a voice feature from an audio signal to generate a feature vector; a salience extractor configured to extract a importance of speech from at least one of the audio signal or a video signal to generate an importance vector; and a neural network configured to output a recognition result based on the feature vector and the importance vector, in which the recognition result is output by masking some.
-
公开(公告)号：US20240330649A1
公开(公告)日：2024-10-03
申请号：US18610804
申请日：2024-03-20
Inventor： Jeongmin YANG , Hyun Woo KIM , Hwajeon SONG , Byunghyun YOO , Euisok CHUNG , Ran HAN
IPC: G06N3/043
CPC classification number: G06N3/043
Abstract: Provided is an inference method employing a prompt-based meta-learning network and a computer system. The inference method includes selecting a task, generating a prompt key for the selected task using a prompt-embedding network (PEN), calculating similarities between the prompt key for the selected task and prompt keys included in a prompt key pool (PKP), acquiring a prompt value for the selected task using a memory network (MN), and generating an inference result for the selected task using a model-agnostic meta-learning (MAML)-based pre-trained model (MPM).
-
Patent Agency Ranking
3.发明公开公开(公告)号：US20240202454A1
公开(公告)日：2024-06-20
申请号：US18471538
申请日：2023-09-21
Inventor： Euisok CHUNG , Hyun Woo KIM , Hwajeon SONG , Jeongmin YANG , Byunghyun YOO , Ran HAN
IPC: G06F40/30 , G06F40/284
CPC classification number: G06F40/30 , G06F40/284
Abstract: A domain adaptation procedure, such as fine-tuning training, is required to utilize a large-capacity PLM for a specific domain. Attempts in existing research have been made to improve performance of a PLM through domain adaptor technology based on an N-gram in order to reduce errors on the basis of the results of domain text error analysis of the PLM. Proposed is a method of selecting a semantic chunk through a domain semantic chunk graph and PageRank based on the existing domain adaptor research, with an N-gram as the semantic chunk. Proposed is also a method of domain-adapting a large-capacity PLM using semantic chunk dynamic weight masking, which reflects an output value of a PLM rather than simply integrating embedding values of semantic chunks, in a semantic chunk domain adaptor technology.
-
公开(公告)号：US20210089933A1
公开(公告)日：2021-03-25
申请号：US16902513
申请日：2020-06-16
Inventor： Hwajeon SONG , Hyun Woo KIM , Euisok CHUNG , Ho Young JUNG , Yunkeun LEE
Abstract: An apparatus for learning procedural knowledge generates procedural knowledge data by connecting unit knowledge that is generated though each episode through interaction with a user, stores the procedural knowledge data generated from each episode in a short-term memory, estimates data to be long-term memorized from the procedural knowledge data stored in the short-term memory, converts the estimated data into long-term memory data, and stores the long-term memory data in a long-term memory.
-
5.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.
-
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：US20230229740A1
公开(公告)日：2023-07-20
申请号：US18070979
申请日：2022-11-29
Inventor： MINHO PARK , Dong-oh KANG , Hwajeon SONG , Jeun Woo LEE
IPC: G06F18/2431 , G06F18/28
CPC classification number: G06F18/2431 , G06F18/28
Abstract: The present invention provides a multiclass classification apparatus and method robust to imbalanced data, which generate artificial data of a minority class on the basis of an over-sampling technique based on adversarial learning to balance imbalanced data and performs multiclass classification robust to imbalanced data by using corresponding data in class classification learning without additionally collecting data.
-
-
-
-
-
-
Search Results
7
records
(took 0.049 seconds)
