公开(公告)号：US20180032663A1

公开(公告)日：2018-02-01

申请号：US15664960

申请日：2017-07-31

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jiho YOO ,  Seokho KANG ,  Youngchun KWON ,  Kyung doc KIM ,  Jaikwang SHIN ,  Hyosug LEE ,  Younsuk CHOI

IPC: G06F19/16 ,  G06N5/04 ,  G06F19/24 ,  G06N99/00

CPC classification number: G16B15/00 ,  G06N3/0445 ,  G06N5/04 ,  G06N20/00 ,  G16B40/00

Abstract: A structure-generating method for generating a structure candidate of a new material including: by a structure-generating processor: performing machine learning on a machine learning model, wherein the machine learning model is configured to provide a result based on a descriptor of a material, a physical property of the material, and a structure of the material; and generating a structure candidate of the new material based on the result of the machine learning, wherein the new material has a target physical property, and wherein the descriptor of the material, the physical property of the material, and the structure of the material are stored in a database.

公开(公告)号：US20230063171A1

公开(公告)日：2023-03-02

申请号：US17745374

申请日：2022-05-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Youngchun KWON ,  Seokho KANG ,  Jin Woo KIM ,  Dongseon LEE ,  Younsuk CHOI

IPC: G05B19/418

Abstract: A method of optimizing synthetic conditions includes receiving a graph-type descriptor comprising at least one of structural information of at least one reactant and structural information of a target product to be synthesized by the reactant; determining combinations of synthetic conditions for generating the target product by applying the graph-type descriptor to a prediction neural network model; selecting at least one initial condition combination from among the combinations based on a first confidence corresponding to a yield of the combinations; updating the prediction neural network model based on a ground-truth yield obtained from a result of an experiment with the initial condition combination; determining a priority of the combinations based on the updated prediction neural network model; and determining subsequent combinations of synthetic conditions based on the determined priority.

公开(公告)号：US20210174910A1

公开(公告)日：2021-06-10

申请号：US17114713

申请日：2020-12-08

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Youngchun KWON ,  Jiho YOO ,  Younsuk CHOI ,  Youngmin NAM ,  Minsik PARK ,  Jinwoo PARK ,  Dongseon LEE

IPC: G16C20/50 ,  G06N3/04 ,  G06N3/08 ,  G16C20/70

Abstract: A neural network apparatus for generating a new chemical structure may receive a structure input of a chemical structure; generate, based on the structure input, a negative attention vector that indicates a respective probability of presence of each of a plurality of blacklists in the structure input; generate a structure expression by encoding the structure input; generate a final reverse blacklist vector that does not include the plurality of blacklists, based on the negative attention vector and the structure expression; and generate the new chemical structure by decoding the final reverse blacklist vector.

公开(公告)号：US20210125060A1

公开(公告)日：2021-04-29

申请号：US16887062

申请日：2020-05-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Youngchun KWON ,  Jinwoo PARK ,  Dongseon LEE ,  Youngmin NAM ,  Minsik PARK ,  Jiho YOO ,  Younsuk CHOI

IPC: G06N3/08 ,  G06N3/04

Abstract: An apparatus for optimizing experimental conditions by using a neural network may calculate a prediction yield and accuracy of the prediction yield by using a neural network-based experimental prediction model. The apparatus may optimize the experimental conditions by determining an experiment priority of a respective experiment condition combination based on the prediction yield and the prediction accuracy and receiving a feedback of results of experiments performed according to the experiment priority.

公开(公告)号：US20190220573A1

公开(公告)日：2019-07-18

申请号：US16156709

申请日：2018-10-10

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  RESEARCH & BUSINESS FOUNDATION SUNGKYUNKWAN UNIVERSITY

Inventor： Youngchun KWON ,  Seokho KANG ,  Kyungdoc KIM ,  Jiho YOO ,  Younsuk CHOI

IPC: G06F19/00 ,  G06N3/04 ,  G06N3/08

CPC classification number: G16C20/40 ,  G06N3/04 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/0472 ,  G06N3/08 ,  G06N3/126 ,  G16C20/50 ,  G16C20/70 ,  G16C20/80

Abstract: A method of generating a chemical structure performed by a neural network device includes receiving a target property value and a target structure characteristic value; selecting first generation descriptors; generating second generation descriptors; determining, using a first neural network of the neural network device, property values of the second generation descriptors; determining, using a second neural network of the neural network device, structure characteristic values of the second generation descriptors; selecting, from the second generation descriptors, candidate descriptors that satisfy the target property value and the target structure characteristic value; and generating, using the second neural network of the neural network device, chemical structures for the selected candidate descriptors.