Patents by Inventor Junhwan Choi
Junhwan Choi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240145767Abstract: A solid-state electrolyte including: a compound represented by Formula 1 Lip-q-(?-5)×r+(?-1)×tM1qM21-rM3?rX1s-tX2?t??Formula 1 wherein, in Formula 1, 0<p?7, 0<q?0.24, 0?r?0.5, 1<s?12, 0?t?1, 0<p?q?(??5)×r+(??1)×t and 0<q/s?0.02, M1 is a monovalent cation and is an element of Group 1 or Group 11 of the Periodic Table, or a combination thereof, M2 is a pentavalent cation and is an element of Group 5 of the Periodic Table, M3 is a cation element having a valency of ?, X1 is a monovalent anion and is an element of Group 17 of the Periodic Table, and X2 is an anion having a valency of ?, and wherein the compound is amorphous.Type: ApplicationFiled: March 23, 2023Publication date: May 2, 2024Inventors: Wonsung Choi, Junhwan Ku
-
Patent number: 11952471Abstract: A polymer thin film having stretchability and dielectric properties and a method of forming the same are provided. The method includes forming the polymer thin film having stretchability and dielectric properties depending on a composition of a copolymer using an acrylate-based monomer and a vinyl group monomer.Type: GrantFiled: September 18, 2020Date of Patent: April 9, 2024Assignee: Korea Advanced Institute of Science and TechnologyInventors: SungGap Im, Juyeon Kang, Junhwan Choi
-
Patent number: 11951394Abstract: An image acquisition apparatus for acquiring an in-game 360 virtual reality (VR) image by using a plurality of virtual cameras includes a virtual camera group taking in-game images by using the plurality of virtual cameras. The image acquisition apparatus may also include a renderer generating textures for the taken images, generating a panoramic image by performing an equirectangular projection (ERP) mapping of the generated textures, and encoding the generated panoramic image. The image acquisition apparatus may further include an image generator generating a 360 VR image by combining audio information with the encoded panoramic image.Type: GrantFiled: April 20, 2021Date of Patent: April 9, 2024Assignee: Korea Electronics Technology InstituteInventors: Junhwan Jang, Woochool Park, Jinwook Yang, Sangpil Yoon, Minsu Choi, Junsuk Lee, Suho Song, Bonjae Koo
-
Publication number: 20240107098Abstract: Proposed are a mediation server operation method for an XR streaming service and XR streaming system supporting same, the mediation server operation method comprising the steps of: if a mediation server receives an XR content playback request from a connected user device, searching for an idle split rendering server; allocating the found idle split rendering server to the user device; receiving image data and sensor data from the user device; generating a rotation matrix on the basis of the received image data and sensor data; and transmitting the rotation matrix to the allocated split rendering server.Type: ApplicationFiled: December 5, 2023Publication date: March 28, 2024Inventors: Junhwan JANG, Woochool PARK, Minsu CHOI, Junsuk LEE, Bonjae KOO
-
Patent number: 11853893Abstract: A method includes generating, by a processor of a computing device, a first plurality of models (including a first number of models) based on a genetic algorithm and corresponding to a first epoch of the genetic algorithm. The method includes determining whether to modify an epoch size for the genetic algorithm during a second epoch of the genetic algorithm based on a convergence metric associated with at least one epoch that is prior to the second epoch. The second epoch is subsequent to the first epoch. The method further includes, based on determining to modify the epoch size, generating a second plurality of models (including a second number of models that is different than the first number) based on the genetic algorithm and corresponding to the second epoch. Each model of the first plurality of models and the second plurality of models includes data representative of neural networks.Type: GrantFiled: June 1, 2021Date of Patent: December 26, 2023Assignee: SPARKCOGNITION, INC.Inventors: Sari Andoni, Keith D. Moore, Elmira M. Bonab, Junhwan Choi
-
Publication number: 20230112096Abstract: Diverse clustering of a data set, including: generating a first plurality of clustering models based on a same data set; selecting, based on a novelty search of the first plurality of clustering models, a second plurality of clustering models; and generating a report based on the second plurality of clustering models.Type: ApplicationFiled: October 13, 2021Publication date: April 13, 2023Inventors: JUNHWAN CHOI, TYLER McDONNELL, YIYUN LAN, KEITH D. MOORE, CHUNG-YU HO
-
Patent number: 11610131Abstract: A method includes determining, by a processor of a computing device, a subset of models included in a plurality of models generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method includes aggregating the subset of models to generate an ensembler. The ensembler, when executed on an input, provides at least a portion of the input to each model of the subset of models to generate a plurality of intermediate outputs. An ensembler output of the ensembler is based on the plurality of intermediate outputs. The method further includes executing the ensembler on input data to determine the ensembler output.Type: GrantFiled: March 6, 2020Date of Patent: March 21, 2023Assignee: SPARKCOGNITION, INC.Inventors: Sari Andoni, Keith D. Moore, Elmira M. Bonab, Junhwan Choi, Tyler S. McDonnell
-
Publication number: 20210390416Abstract: A method includes generating, by a processor of a computing device, an output set of models corresponding to a first epoch of a genetic algorithm and based on an input set of models of the first epoch. The input set and the output set includes data representative of a neural network. The method includes determining a particular model of the output set based on a fitness function. A first topological parameter of a first model of the input set is modified to generate the particular model of the output set. The method includes modifying a probability that the first topological parameter is to be changed by a genetic operation during a second epoch of the genetic algorithm that is subsequent to the first epoch. The method includes generating a second output set of models corresponding to the second epoch and based on the output set and the modified probability.Type: ApplicationFiled: August 27, 2021Publication date: December 16, 2021Inventors: Sari Andoni, Keith D. Moore, Elmira M. Bonab, Junhwan Choi, Eric O. Korman
-
Publication number: 20210287097Abstract: A method includes generating, by a processor of a computing device, a first plurality of models (including a first number of models) based on a genetic algorithm and corresponding to a first epoch of the genetic algorithm. The method includes determining whether to modify an epoch size for the genetic algorithm during a second epoch of the genetic algorithm based on a convergence metric associated with at least one epoch that is prior to the second epoch. The second epoch is subsequent to the first epoch. The method further includes, based on determining to modify the epoch size, generating a second plurality of models (including a second number of models that is different than the first number) based on the genetic algorithm and corresponding to the second epoch. Each model of the first plurality of models and the second plurality of models includes data representative of neural networks.Type: ApplicationFiled: June 1, 2021Publication date: September 16, 2021Inventors: Sari Andoni, Keith D. Moore, Elmira M. Bonab, Junhwan Choi
-
Patent number: 11106978Abstract: A method includes generating, by a processor of a computing device, an output set of models corresponding to a first epoch of a genetic algorithm and based on an input set of models of the first epoch. The input set and the output set includes data representative of a neural network. The method includes determining a particular model of the output set based on a fitness function. A first topological parameter of a first model of the input set is modified to generate the particular model of the output set. The method includes modifying a probability that the first topological parameter is to be changed by a genetic operation during a second epoch of the genetic algorithm that is subsequent to the first epoch. The method includes generating a second output set of models corresponding to the second epoch and based on the output set and the modified probability.Type: GrantFiled: September 8, 2017Date of Patent: August 31, 2021Assignee: SPARKCOGNITION, INC.Inventors: Sari Andoni, Keith D. Moore, Elmira M. Bonab, Junhwan Choi, Eric O. Korman
-
Patent number: 11074503Abstract: A method includes generating, by a processor of a computing device, a first plurality of models (including a first number of models) based on a genetic algorithm and corresponding to a first epoch of the genetic algorithm. The method includes determining whether to modify an epoch size for the genetic algorithm during a second epoch of the genetic algorithm based on a convergence metric associated with at least one epoch that is prior to the second epoch. The second epoch is subsequent to the first epoch. The method further includes, based on determining to modify the epoch size, generating a second plurality of models (including a second number of models that is different than the first number) based on the genetic algorithm and corresponding to the second epoch. Each model of the first plurality of models and the second plurality of models includes data representative of neural networks.Type: GrantFiled: September 6, 2017Date of Patent: July 27, 2021Assignee: SPARKCOGNITION, INC.Inventors: Sari Andoni, Keith D. Moore, Elmira M. Bonab, Junhwan Choi
-
Publication number: 20210087346Abstract: A polymer thin film having stretchability and dielectric properties and a method of forming the same are provided. The method includes forming the polymer thin film having stretchability and dielectric properties depending on a composition of a copolymer using an acrylate-based monomer and a vinyl group monomer.Type: ApplicationFiled: September 18, 2020Publication date: March 25, 2021Inventors: SungGap IM, Juyeon KANG, Junhwan CHOI
-
Publication number: 20200242480Abstract: A method includes receiving, by a processor, an input data set. The input data set includes a plurality of features. The method includes determining, by the processor, one or more characteristics of the input data set. The method includes, based on the one or more characteristics, adjusting, by the processor, one or more architectural parameters of an automated model generation process. The automated model generation process is configured to generate a plurality of models using a weighted randomization process. The one or more architectural parameters weight the weighted randomization process to adjust a probability of generation of models having particular architectural features. The method further includes executing, by the processor, the automated model generation process to output a mode, the model including data representative of a neural network.Type: ApplicationFiled: April 14, 2020Publication date: July 30, 2020Inventors: Tyler S. McDonnell, Sari Andoni, Junhwan Choi, Jimmie Goode, Yiyun Lan, Keith D. Moore, Gavin Sellers
-
Publication number: 20200210847Abstract: A method includes determining, by a processor of a computing device, a subset of models included in a plurality of models generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method includes aggregating the subset of models to generate an ensembler. The ensembler, when executed on an input, provides at least a portion of the input to each model of the subset of models to generate a plurality of intermediate outputs. An ensembler output of the ensembler is based on the plurality of intermediate outputs. The method further includes executing the ensembler on input data to determine the ensembler output.Type: ApplicationFiled: March 6, 2020Publication date: July 2, 2020Inventors: Sari Andoni, Keith D. Moore, Elmira M. Bonab, Junhwan Choi, Tyler S. McDonnell
-
Publication number: 20200175378Abstract: A method includes receiving, by a processor, an input data set. The input data set includes a plurality of features. The method includes determining, by the processor, one or more characteristics of the input data set. The method includes, based on the one or more characteristics, adjusting, by the processor, one or more architectural parameters of an automated model generation process. The automated model generation process is configured to generate a plurality of models using a weighted randomization process. The one or more architectural parameters weight the weighted randomization process to adjust a probability of generation of models having particular architectural features. The method further includes executing, by the processor, the automated model generation process to output a mode, the model including data representative of a neural network.Type: ApplicationFiled: November 29, 2018Publication date: June 4, 2020Inventors: Tyler S. McDonnell, Sari Andoni, Junhwan Choi, Jimmie Goode, Yiyun Lan, Keith D. Moore, Gavin Sellers
-
Patent number: 10657447Abstract: A method includes receiving, by a processor, an input data set. The input data set includes a plurality of features. The method includes determining, by the processor, one or more characteristics of the input data set. The method includes, based on the one or more characteristics, adjusting, by the processor, one or more architectural parameters of an automated model generation process. The automated model generation process is configured to generate a plurality of models using a weighted randomization process. The one or more architectural parameters weight the weighted randomization process to adjust a probability of generation of models having particular architectural features. The method further includes executing, by the processor, the automated model generation process to output a mode, the model including data representative of a neural network.Type: GrantFiled: November 29, 2018Date of Patent: May 19, 2020Assignee: SPARKCOGNITION, INC.Inventors: Tyler S. McDonnell, Sari Andoni, Junhwan Choi, Jimmie Goode, Yiyun Lan, Keith D. Moore, Gavin Sellers
-
Patent number: 10635978Abstract: A method includes determining, by a processor of a computing device, a subset of models included in a plurality of models generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method includes aggregating the subset of models to generate an ensembler. The ensembler, when executed on an input, provides at least a portion of the input to each model of the subset of models to generate a plurality of intermediate outputs. An ensembler output of the ensembler is based on the plurality of intermediate outputs. The method further includes executing the ensembler on input data to determine the ensembler output.Type: GrantFiled: October 26, 2017Date of Patent: April 28, 2020Assignee: SPARKCOGNITION, INC.Inventors: Sari Andoni, Keith D. Moore, Elmira M. Bonab, Junhwan Choi, Tyler S. McDonnell
-
Publication number: 20190130277Abstract: A method includes determining, by a processor of a computing device, a subset of models included in a plurality of models generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method includes aggregating the subset of models to generate an ensembler. The ensembler, when executed on an input, provides at least a portion of the input to each model of the subset of models to generate a plurality of intermediate outputs. An ensembler output of the ensembler is based on the plurality of intermediate outputs. The method further includes executing the ensembler on input data to determine the ensembler output.Type: ApplicationFiled: October 26, 2017Publication date: May 2, 2019Inventors: Sari Andoni, Keith D. Moore, Elmira M. Bonab, Junhwan Choi, Tyler S. McDonnell
-
Publication number: 20190080240Abstract: A method includes generating, by a processor of a computing device, an output set of models corresponding to a first epoch of a genetic algorithm and based on an input set of models of the first epoch. The input set and the output set includes data representative of a neural network. The method includes determining a particular model of the output set based on a fitness function. A first topological parameter of a first model of the input set is modified to generate the particular model of the output set. The method includes modifying a probability that the first topological parameter is to be changed by a genetic operation during a second epoch of the genetic algorithm that is subsequent to the first epoch. The method includes generating a second output set of models corresponding to the second epoch and based on the output set and the modified probability.Type: ApplicationFiled: September 8, 2017Publication date: March 14, 2019Inventors: Sari Andoni, Keith D. Moore, Elmira M. Bonab, Junhwan Choi, Eric O. Korman
-
Publication number: 20190073591Abstract: A method includes generating, by a processor of a computing device, a first plurality of models (including a first number of models) based on a genetic algorithm and corresponding to a first epoch of the genetic algorithm. The method includes determining whether to modify an epoch size for the genetic algorithm during a second epoch of the genetic algorithm based on a convergence metric associated with at least one epoch that is prior to the second epoch. The second epoch is subsequent to the first epoch. The method further includes, based on determining to modify the epoch size, generating a second plurality of models (including a second number of models that is different than the first number) based on the genetic algorithm and corresponding to the second epoch. Each model of the first plurality of models and the second plurality of models includes data representative of neural networks.Type: ApplicationFiled: September 6, 2017Publication date: March 7, 2019Inventors: Sari Andoni, Keith D. Moore, Elmira M. Bonab, Junhwan Choi