-
公开(公告)号:US20240078361A1
公开(公告)日:2024-03-07
申请号:US18310656
申请日:2023-05-02
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Youngmin OH , Doyun KIM , Hyung-Dal KWON , Yongwoo LEE , Bosun HWANG
IPC: G06F30/27 , G06F30/3308
CPC classification number: G06F30/27 , G06F30/3308
Abstract: A method of generating a circuit design parameter meeting a target specification, the method including generating a first probability distribution of a first specification using a first model provided a first parameter where the first model is configured to infer a correlation between the first parameter and the first probability distribution, generating a second parameter using a second model provided the first probability distribution, and updating the first model based on the second parameter. The second model is trained by using a reward, the reward being determined based on a second probability distribution of a second specification corresponding to the second parameter
-
公开(公告)号:US20250086477A1
公开(公告)日:2025-03-13
申请号:US18884874
申请日:2024-09-13
Applicant: Samsung Electronics Co., Ltd.
Inventor: Hyung-Dal KWON , Youngmin OH , Doyun KIM , Yoonhyeok LEE , Bosun HWANG
IPC: G06N3/126 , G06N3/0985
Abstract: A method is performed by one or more processors, and the method includes: receiving a problem definition for which an optimized solution is to be determined; executing a genetic algorithm to determine the optimized solution, the executing the genetic algorithm including iteratively performing, according to changing values of a control parameter, a genetic operation on a population of elements while evaluating elements of the population against the problem definition, the control parameter being a hyperparameter of the genetic operations; based on results of the respective iterations of the genetic operation to a neural network, generating, by a neural network, the values of the control parameter; and determining the optimized solution based on the iterations of the genetic operation as controlled, via the values of the control parameter, by the neural network.
-
公开(公告)号:US20240232498A1
公开(公告)日:2024-07-11
申请号:US18350419
申请日:2023-07-11
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Hyung-Dal KWON , Youngmin OH , Bosun HWANG
IPC: G06F30/392 , G06F30/398
CPC classification number: G06F30/392 , G06F30/398 , G06F2111/06
Abstract: An apparatus with circuit designing may include: one or more processors configured to: generate an initial solution set based on nodes and edges comprised in a graph corresponding to a circuit to be optimized; generate a crossover solution by performing a crossover operation based on a plurality of solutions comprised in the initial solution set; perform a first change of positions of nodes comprised in the crossover solution by performing a mutation operation on the crossover solution; and generate a target circuit structure by performing a second change of the positions of the first changed nodes based on lengths of the edges connecting the nodes.
-
公开(公告)号:US20250155484A1
公开(公告)日:2025-05-15
申请号:US18945874
申请日:2024-11-13
Applicant: Samsung Electronics Co., Ltd.
Inventor: Doyun KIM , Jaemin PARK , Youngmin OH , Bosun HWANG
IPC: G01R27/26
Abstract: An apparatus and method for analyzing a frequency characteristics of a substrate are provided, through the steps of tokenizing a trace of a substrate into a graph, generating a representation vector from the tokens of the graph, and analyzing a frequency characteristics of the substrate based on the representation vector.
-
公开(公告)号:US20250086476A1
公开(公告)日:2025-03-13
申请号:US18828342
申请日:2024-09-09
Applicant: Samsung Electronics Co., Ltd.
Inventor: Youngmin OH , Hyung-dal KWON , Bosun HWANG
Abstract: A method for performing a genetic algorithm is performed by one or more processors, and the method includes: generating a subset of elements by using a neural network from a population including elements that each correspond to a respective solution to a problem; generating child elements by performing a genetic algorithm on the subset; and determining that one of the child elements, from among the child elements is an answer to the problem.
-
-
-
-