公开(公告)号：US20230289624A1

公开(公告)日：2023-09-14

申请号：US18088825

申请日：2022-12-27

Applicant: Fujitsu Limited

Inventor： Takashi KATOH ,  Kento UEMURA ,  Suguru YASUTOMI

IPC: G06N5/022

CPC classification number: G06N5/022

Abstract: A non-transitory computer-readable storage medium storing an information processing program that causes at least one computer to execute a process, the process includes acquiring an update amount of a classification criterion of a classification model in retraining, the classification model being trained by using a first dataset, the classification model classifying input data into one of a plurality of classes, the retraining being performed by using a second dataset; and detecting data with a largest change amount among the second dataset when changing each piece of data included in the second dataset so as to decrease the update amount.

公开(公告)号：US20230281845A1

公开(公告)日：2023-09-07

申请号：US18060338

申请日：2022-11-30

Applicant: Fujitsu Limited

Inventor： Suguru YASUTOMI ,  Akira SAKAI ,  Takashi KATOH ,  Kento UEMURA

IPC: G06T7/507 ,  G06T5/50 ,  G06T7/60 ,  G06V10/75

CPC classification number: G06T7/507 ,  G06T5/50 ,  G06T7/60 ,  G06V10/758 ,  G06T2207/10132 ,  G06T2207/20221

Abstract: An information processing device acquires output image data that is acquired by inputting image data indicating a pseudo-shadow area to an auto-encoder that is generated by machine learning using label image data contained in training data, the label image data indicating a shadow area in ultrasound image data of a captured target. The information processing device generates augmented data corresponding to the training data by combining the acquired output image data with the ultrasound image data.

公开(公告)号：US20220147764A1

公开(公告)日：2022-05-12

申请号：US17473509

申请日：2021-09-13

Applicant: FUJITSU LIMITED

Inventor： Takashi KATOH ,  Kento UEMURA ,  Suguru YASUTOMI ,  Tomohiro HAYASE

IPC: G06K9/62 ,  G06F17/17 ,  G06N20/00

Abstract: A non-transitory computer-readable storage medium storing a data generation program that causes at least one computer to execute a process, the process includes, acquiring a data generation model that is trained by using a first dataset corresponding to a first domain and a second dataset corresponding to a second domain, and that includes an identification loss by an identification model in a parameter; inputting first data corresponding to the first domain to the identification model to acquire a first identification loss, and inputting second data corresponding to the second domain to the identification model to acquire a second identification loss; generating data in which the second identification loss approximates the first identification loss, by using the data generation model; and outputting the data that is generated.

公开(公告)号：US20200334517A1

公开(公告)日：2020-10-22

申请号：US16840635

申请日：2020-04-06

Applicant: FUJITSU LIMITED

Inventor： Kento UEMURA

IPC: G06N3/04 ,  G06N3/08

Abstract: A non-transitory computer-readable recording medium has stored therein a program that causes a computer to execute a process, the process including: obtaining an estimation value of a third variable by subtracting a second output value of a second parametric model to which a second variable is input from a first output value of a first parametric model to which a first variable is input; performing first parameter update of updating first parameters of the first parametric model and second parameters of the second parametric model such that independence between the second variable and the estimation value of the third variable is maximized; and updating the first parameters and third parameters of a third parametric model in the first parameter update, such that a third output value of the third parametric model is approximated to the first variable, the third parametric model being input with the first output value.

公开(公告)号：US20200302611A1

公开(公告)日：2020-09-24

申请号：US16811108

申请日：2020-03-06

Applicant: FUJITSU LIMITED

Inventor： Kento UEMURA ,  Suguru YASUTOMI ,  TAKASHI KATOH

IPC: G06T7/11 ,  G06K9/62 ,  G06N3/08

Abstract: An estimation method implemented by a computer, the estimation method includes: executing learning processing by training an autoencoder with a data group corresponding to a specific task; calculating a degree of compression of each part regarding data included in the data group by using the trained autoencoder; and estimating a common part with another piece of data included in the data group regarding the data corresponding to the specific task based on the calculated degree of compression of each part.

公开(公告)号：US20200234081A1

公开(公告)日：2020-07-23

申请号：US16736911

申请日：2020-01-08

Applicant: FUJITSU LIMITED

Inventor： TAKASHI KATOH ,  Kento UEMURA ,  Suguru YASUTOMI

IPC: G06K9/62

Abstract: A learning device learns at last one parameter of a learning model such that each intermediate feature quantity becomes similar to a reference feature quantity, the each intermediate feature quantity being calculated as a result of inputting a plurality of sets of augmentation training data to a first neural network in the learning model, the plurality of augmentation training data being generated by performing data augmentation based on same first original training data. The learning device learns at last one parameter of a second network, in the learning model, using second original training data, which is different than the first original training data, and using the reference feature quantity.

公开(公告)号：US20190286946A1

公开(公告)日：2019-09-19

申请号：US16274321

申请日：2019-02-13

Applicant: FUJITSU LIMITED

Inventor： Kento UEMURA ,  TAKASHI KATOH ,  Suguru YASUTOMI ,  Toshio Endoh

IPC: G06K9/62 ,  G06N3/08

Abstract: A learning method for an auto-encoder is performed by a computer. The method includes: by using a discriminator configured to generate an estimated label based on a feature value generated by an encoder of an auto-encoder and input data, causing the discriminator to learn such that a label corresponding the input data and the estimated label are matched; and by using the discriminator, causing the encoder to learn such that the label corresponding to the input data and the estimated label are separated.

公开(公告)号：US20240005214A1

公开(公告)日：2024-01-04

申请号：US18468565

申请日：2023-09-15

Applicant: FUJITSU LIMITED

Inventor： Yusuke KOYANAGI ,  Kento UEMURA ,  Kotaro OHORI

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: An information presentation device generates a plurality of training models by executing machine learning that uses training data. The information presentation device generates hierarchical information that represents, in a hierarchical structure, a relationship between hypotheses shared as common and hypotheses regarded as differences for a plurality of hypotheses extracted from each of the plurality of training models and each designated by a combination of one or more explanatory variables.

公开(公告)号：US20230289659A1

公开(公告)日：2023-09-14

申请号：US18174625

申请日：2023-02-26

Applicant: Fujitsu Limited

Inventor： Takashi KATOH ,  Kento UEMURA ,  Suguru YASUTOMI

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: An information processing method comprising: for a classification model for classifying input data into one or another of plural classes that was trained using a first data set, identifying, in a second data set that is different from the first data set one or more items of data having a specific datum of which a degree of contribution to a change in a classification criterion is greater than a predetermined threshold, the classification criterion being a classification criterion of the classification model during re-training based on the second data set; and, from among the one or more items of data, detecting an item of data, for which a loss reduces for the classification model by change to the classification criterion by re-training based on the second data set, as an item of data of an unknown class not contained in the plural classes.

公开(公告)号：US20210012193A1

公开(公告)日：2021-01-14

申请号：US16921944

申请日：2020-07-07

Applicant: FUJITSU LIMITED

Inventor： Suguru YASUTOMI ,  TAKASHI KATOH ,  Kento UEMURA

IPC: G06N3/08 ,  G06N3/04

Abstract: A machine learning method includes: calculating, by a computer, a first loss function based on a first distribution and a previously set second distribution, the first distribution being a distribution of a feature amount output from an intermediate layer when first data is input to an input layer of a model that has the input layer, the intermediate layer, and an output layer; calculating a second loss function based on second data and correct data corresponding to the first data, the second data being output from the output layer when the first data is input to the input layer of the model; and training the model based on both the first loss function and the second loss function.