-
公开(公告)号：US20220318351A1
公开(公告)日：2022-10-06
申请号：US17569914
申请日：2022-01-06
发明人： Jaeyun LEE , Kyuhong KIM , Jiwhan KIM , Sungun PARK , Kiho CHO , Jaejoon HAN
摘要： A processor-implemented method with input data classification includes: extracting an input embedding vector including a feature of biometric information of a user from input data including the biometric information; determining an adaptive embedding vector adaptive to the input embedding vector, based on a combination of a plurality of enrollment embedding vectors that are based on enrollment data; and classifying the input data based on a similarity between the input embedding vector and the adaptive embedding vector.
-
公开(公告)号：US20230252283A1
公开(公告)日：2023-08-10
申请号：US17982618
申请日：2022-11-08
发明人： Jaeyun LEE , Kiho CHO , Jiwhan KIM , Sungun PARK , Jaejoon HAN
IPC分类号： G06N3/08
CPC分类号： G06N3/08
摘要： A processor-implemented method with a neural network includes: generating a first intermediate vector by applying a first activation function to first nodes in a first intermediate layer adjacent to an input layer among intermediate layers of the neural network; transferring the first intermediate vector to second nodes in a second intermediate layer adjacent to an output layer among the intermediate layers; generating a second intermediate vector by applying a second activation function to the second nodes; and applying the second intermediate vector to an output layer of the neural network, wherein the second activation function is determined by a first hyperparameter of which a multiplier of the second activation function is associated with an ascending slope of the second activation function and a second hyperparameter of which the multiplier is associated with a descending slope of the second activation function to fix a peak value of the second activation function.
-
公开(公告)号：US20240161007A1
公开(公告)日：2024-05-16
申请号：US18351100
申请日：2023-07-12
发明人： Heewon KIM , Hyun Sung CHANG , Jaeyun LEE , Kiho CHO
IPC分类号： G06N20/00
CPC分类号： G06N20/00
摘要： A processor-implemented method includes training a first model to predict confidences of labels for data samples in a training dataset, including using a corrected data sample obtained by correcting an incorrect label based on a corresponding confidence detected by the first model and an estimated corrected label generated by a second model; training the second model to estimate correct labels for the data samples, including estimating a correct other label corresponding to another incorrect label detected based on a corresponding confidence generated by the first model with respect to the other incorrect label; and automatically correcting the other incorrect label with the estimated correct other label.
-
公开(公告)号：US20230030937A1
公开(公告)日：2023-02-02
申请号：US17862568
申请日：2022-07-12
发明人： Jaeyun LEE , Kyuhong KIM , Sungun PARK , Jaejoon HAN
摘要： A processor-implemented method with image preprocessing includes: transforming a fingerprint image into a frequency domain; suppressing a low-frequency region corresponding to a first noise component of the fingerprint image in the frequency domain; and restoring the frequency domain, in which the low-frequency region is suppressed, as an image.
-
公开(公告)号：US20210313442A1
公开(公告)日：2021-10-07
申请号：US17060193
申请日：2020-10-01
发明人： Bongseok SUH , Daewon KIM , Beomjin PARK , Sukhyung PARK , Sungil PARK , Jaehoon SHIN , Bongseob YANG , Junggun YOU , Jaeyun LEE
IPC分类号： H01L29/66 , H01L29/423 , H01L29/10
摘要： A semiconductor device includes a first active region defined on a substrate, a first gate electrode across the first active region, a first drain region in the first active region at a position adjacent to the first gate electrode, an undercut region between the first active region and the first gate electrode, and a first gate spacer on a side surface of the first gate electrode and extending into the undercut region.
-
-
-
-
搜索结果
5 条记录 (耗时 0.025 秒)
