-
1.发明公开公开(公告)号：US20240320402A1
公开(公告)日：2024-09-26
申请号：US18544065
申请日：2023-12-18
发明人： Sangjune Bae , Taeyoon An , Joohyung You , In Huh , Moonhyun Cha , Jaemyung Choe
IPC分类号： G06F30/27
CPC分类号： G06F30/27
摘要： Provided are a method, a device, and a system for estimating threshold values of a kernel density function with respect to defects of a product. The method includes a bootstrapping sampling operation, estimating optimal kernel bandwidths for sample data sets by using a bandwidth estimation method selected according to a number of sample data from among a plurality of bandwidth estimation methods, estimating threshold values corresponding to a tail region of the kernel density function based on the optimal kernel bandwidths, and providing a quantitative value for quantifying uncertainty of the threshold values based on the plurality of threshold values.
-
公开(公告)号：US20240028910A1
公开(公告)日：2024-01-25
申请号：US18171550
申请日：2023-02-20
发明人： Yunjun Nam , Bogyeong Kang , Hyowon Moon , Byungseon Choi , Jaemyung Choe , Hyunjae Jang , In Huh
IPC分类号： G06N3/10 , G06N3/08 , G06F30/3308
CPC分类号： G06N3/10 , G06N3/08 , G06F30/3308
摘要： In a modeling method of a neural network, a first regression model is trained based on first sample data and first simulation result data. The first regression model is used to predict the first simulation result data from the first sample data. The first sample data represent at least one of conditions of a manufacturing process of a semiconductor device and characteristics of the semiconductor device. The first simulation result data are obtained by performing a simulation on the first sample data. In response to a consistency of the first regression model being lower than a target consistency, the first regression model is re-trained based on second sample data different from the first sample data. The second sample data are associated with a consistency reduction factor of the first regression model that is responsible for a prediction failure of the first regression model.
-
公开(公告)号：US11507801B2
公开(公告)日：2022-11-22
申请号：US16505155
申请日：2019-07-08
发明人： In Huh , Min Chul Park , Tae Ho Lee , Chang Wook Jeong , Chan Young Hwang
摘要： A method for detecting defects in a semiconductor device includes pre-training a pre-trained convolutional neural network (CNN) model using a sampled clean data set extracted from a first data set; training a normal convolutional neural network model and a label-noise convolutional neural network model using first data of the first data set and the pre-trained convolutional neural network model. The method also includes outputting a first prediction result on whether second data of a second data set is good or bad using the second data and the normal convolutional neural network model; and outputting a second prediction result on whether second data is good or bad using the second data and the label-noise convolutional neural network model. The first prediction result is compared with the second prediction result to perform noise correction when there is a label difference. Third data created as results of the noise correction is added to the sampled clean data set. The normal convolutional neural network model and the label-noise convolutional neural network model are additionally using the sampled clean data set with the third data added.
-
公开(公告)号：US20200042896A1
公开(公告)日：2020-02-06
申请号：US16518104
申请日：2019-07-22
发明人： JEONG-HOON KO , Jae-Jun Lee , Seong-Je Kim , In Huh , Chang-Wook Jeong
摘要： A method of selecting a model of machine learning executed by a processor is provided. The method includes: receiving at least one data-set; configuring a configuration space for machine learning of the at least one data-set; extracting, from the at least one data-set, a meta-feature including quantitative information about the data-set; calculating performance of the machine learning for the at least one data-set based on a plurality of configurations included in the configuration space; executing meta-learning based on the meta-feature, the plurality of configurations, and the calculated performance; and optimizing the configuration space based on a result of executing the meta-learning.
-
公开(公告)号：US11574095B2
公开(公告)日：2023-02-07
申请号：US16906038
申请日：2020-06-19
发明人： Sanghoon Myung , Hyunjae Jang , In Huh , Hyeon Kyun Noh , Min-Chul Park , Changwook Jeong
IPC分类号： G06F30/27 , G06N3/08 , G06N3/10 , G06N3/04 , G06F30/398
摘要： Provided is a simulation method performed by a process simulator, implemented with a recurrent neural network (RNN) including a plurality of process emulation cells, which are arranged in time series and configured to train and predict, based on a final target profile, a profile of each process step included in a semiconductor manufacturing process. The simulation method includes: receiving, at a first process emulation cell, a previous output profile provided at a previous process step, a target profile and process condition information of a current process step; and generating, at the first process emulation cell, a current output profile corresponding to the current process step, based on the target profile, the process condition information, and prior knowledge information, the prior knowledge information defining a time series causal relationship between the previous process step and the current process step.
-
公开(公告)号：US20220207393A1
公开(公告)日：2022-06-30
申请号：US17468819
申请日：2021-09-08
发明人： Naoto Umezawa , Changwook Jeong , Jisu Ryu , Kyu Hyun Lee , Jinyoung Lim , Wonik Jang , In Huh
摘要： Disclosed are methods of predicting semiconductor material properties and methods of testing semiconductor devices using the same. The prediction method comprises preparing a machine learning model that is trained with a training system and using the machine learning model to predict material properties of a target system. The machine learning model is represented as a function of material properties with respect to a descriptor. The descriptor is calculated from unrelaxed charge density (UCD) that is represented by summation of atomic charge density (ACD) of single atoms.
-
公开(公告)号：US11861280B2
公开(公告)日：2024-01-02
申请号：US17692883
申请日：2022-03-11
发明人： In Huh , Jeong-hoon Ko , Hyo-jin Choi , Seung-ju Kim , Chang-wook Jeong , Joon-wan Chai , Kwang-il Park , Youn-sik Park , Hyun-sun Park , Young-min Oh , Jun-haeng Lee , Tae-ho Lee
摘要： A method of reinforcement learning of a neural network device for generating a verification vector for verifying a circuit design comprising a circuit block includes inputting a test vector to the circuit block, generating one or more rewards based on a coverage corresponding to the test vector, the coverage being determined based on a state transition of the circuit block based on the test vector, and applying the one or more rewards to a reinforcement learning.
-
公开(公告)号：US11681947B2
公开(公告)日：2023-06-20
申请号：US16518104
申请日：2019-07-22
发明人： Jeong-Hoon Ko , Jae-Jun Lee , Seong-Je Kim , In Huh , Chang-Wook Jeong
CPC分类号： G06N20/00 , G06F11/3495 , G06F17/15 , G06F17/18
摘要： A method of selecting a model of machine learning executed by a processor is provided. The method includes: receiving at least one data-set; configuring a configuration space for machine learning of the at least one data-set; extracting, from the at least one data-set, a meta-feature including quantitative information about the data-set; calculating performance of the machine learning for the at least one data-set based on a plurality of configurations included in the configuration space; executing meta-learning based on the meta-feature, the plurality of configurations, and the calculated performance; and optimizing the configuration space based on a result of executing the meta-learning.
-
公开(公告)号：US20210117193A1
公开(公告)日：2021-04-22
申请号：US16915786
申请日：2020-06-29
发明人： Seungju Kim , Hyojin Choi , In Huh , Jeonghoon Ko , Changwook Jeong , Younsik Park , Joonwan Chai
摘要： An electronic device configured to generate a verification vector for verifying a semiconductor circuit including a first circuit block and a second circuit block includes a duplicate command eliminator configured to receive a first input vector including a plurality of commands and to provide a first converted vector, in which ones of the plurality of commands that generate the same state transition are changed into idle commands, based on a state transition of the first circuit block obtained by performing a simulation operation on the first input vector, a reduced vector generator configured to provide a first reduced vector in which a number of repetitions of the idle commands included in the first converted vector is reduced, and a verification vector generator configured to output the first reduced vector having a coverage that coincides with a target coverage among a plurality of first reduced vectors as a first verification vector.
-
10.发明申请公开(公告)号：US20210056425A1
公开(公告)日：2021-02-25
申请号：US16910908
申请日：2020-06-24
发明人： Changwook JEONG , Sanghoon Myung , In Huh , Hyeonkyun Noh , Minchul Park , Hyunjae Jang
摘要： A method for a hybrid model that includes a machine learning model and a rule-based model, includes obtaining a first output from the rule-based model by providing a first input to the rule-based model, and obtaining a second output from the machine learning model by providing the first input, a second input, and the obtained first output to the machine learning model. The method further includes training the machine learning model, based on errors of the obtained second output.
-
-
-
-
-
-
-
-
-
搜索结果
17 条记录 (耗时 0.016 秒)
