公开(公告)号：US20190318260A1

公开(公告)日：2019-10-17

申请号：US16364583

申请日：2019-03-26

Applicant: FUJITSU LIMITED

Inventor： Suguru YASUTOMI ,  TAKASHI KATOH ,  Kento UEMURA

IPC: G06N20/00 ,  G06F17/15 ,  G06F17/14 ,  G06N3/08

Abstract: A non-transitory computer-readable recording medium with a machine learning program recorded therein for enabling a computer to perform processing includes: generating augmented data by data-augmenting at least some data of training data or at least some data of data input to a convolutional layer included in a learner, using a filter corresponding to a size depending on details of the processing of the convolutional layer or a filter corresponding to a size of an identification target for the learner; and learning the learner using the training data and the augmented data.

公开(公告)号：US20170286386A1

公开(公告)日：2017-10-05

申请号：US15424495

申请日：2017-02-03

Applicant: FUJITSU LIMITED

Inventor： Keisuke GOTO ,  Yuiko OHTA ,  Hiroya INAKOSHI ,  Kento UEMURA

IPC: G06F17/24

CPC classification number: G06F17/245 ,  G06F17/246 ,  G06F17/247 ,  G06T7/11

Abstract: A processor obtains a table that contains numerical values or character strings in its cells. The processor then replaces each numerical value with a first constant value, and each character string with a second constant value. The two constant values have opposite signs. The processor generates area datasets each including first to third rectangular areas. The right side of the second rectangular area coincides with the left side of the first rectangular area. The bottom side of the third rectangular area coincides with the top side of the first rectangular area. With respect to each generated area dataset, the processor compares a sum of first and second constant values in the first rectangular area with a sum of first and second constant values in the second and third rectangular areas. The processor outputs at least one of the area datasets according to the comparison result.

公开(公告)号：US20240362227A1

公开(公告)日：2024-10-31

申请号：US18769473

申请日：2024-07-11

Applicant: Fujitsu Limited

Inventor： Hiroaki IWASHITA ,  Tatsuya ASAI ,  Kento UEMURA ,  Yusuke KOYANAGI

IPC: G06F16/2455

CPC classification number: G06F16/24558

Abstract: A non-transitory computer-readable recording medium stores an information processing program for causing a computer to execute processing including: generating, from first data in which values of a plurality of attributes included in each sample are accumulated for each sample, second data obtained by binarizing, for each sample, the values of the plurality of attributes included in each sample based on an attribute condition set in advance; enumerating, by using the second data, sets of attribute conditions in which all sample sets indicate true values; computing, for each set of attribute conditions, a correlation between the plurality of attributes in the first data in a sample set associated with each set of attribute conditions; and selecting a set of attribute conditions determined to have a correlation as a condition to be causally searched.

公开(公告)号：US20230306306A1

公开(公告)日：2023-09-28

申请号：US18159106

申请日：2023-01-25

Applicant: Fujitsu Limited

Inventor： TAKASHI KATOH ,  Kento UEMURA ,  Suguru YASUTOMI

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A non-transitory computer-readable storage medium storing a machine learning program that causes at least one computer to execute a process, the process includes estimating a first label distribution of unlabeled training data based on a classification model and an initial value of a label distribution of a transfer target domain, the classification model being trained by using labeled training data which corresponds to a transfer source domain and unlabeled training data which corresponds to the transfer target domain; acquiring a second label distribution based on the labeled training data; acquiring a weight of each label included in the labeled training data and the unlabeled training data based on a difference between the first label distribution and the second label distribution; and re-training the classification model by the labeled training data and the unlabeled training data reflected the weight of each label.

公开(公告)号：US20230289406A1

公开(公告)日：2023-09-14

申请号：US18177189

申请日：2023-03-02

Applicant: Fujitsu Limited

Inventor： Takashi KATOH ,  Kento UEMURA ,  Suguru YASUTOMI

IPC: G06F18/2415 ,  G06F18/2431

CPC classification number: G06F18/2415 ,  G06F18/2431

Abstract: A non-transitory computer-readable recording medium stores a determination program for causing a computer to execute processing including: re-training a classification model that has been trained by using a first data set and that classifies input data into any one of a plurality of classes by using a loss calculatable based on a second data set that is different from the first data set; and determining, in a case where a change in a classification standard of the classification model based on the loss is a predetermined standard or more before and after re-training, that unknown data that is not classified into any one of the plurality of classes is included in the second data set.

公开(公告)号：US20230186118A1

公开(公告)日：2023-06-15

申请号：US18157639

申请日：2023-01-20

Applicant: FUJITSU LIMITED

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

IPC: G06N5/022

CPC classification number: G06N5/022

Abstract: A program for causing a computer to execute processing including: acquiring a plurality of datasets, each of which includes data values associated with a label, the data values having properties different for each dataset; calculating an index indicating a degree of a difference between first and second datasets by using a data value in the second dataset; calculating accuracy of a prediction result for the second dataset, predicted by a prediction model trained using the first dataset; specifying a relationship between the index and the accuracy of the prediction result from the prediction model, based on the index and the accuracy calculated for each of a plurality of combinations of the first and second datasets; and estimating accuracy of the prediction result from the prediction model for a third dataset including data values without labels based on the specified relationship and the index between the first and third datasets.

公开(公告)号：US20220245405A1

公开(公告)日：2022-08-04

申请号：US17727915

申请日：2022-04-25

Applicant: FUJITSU LIMITED

Inventor： TAKASHI KATOH ,  Kento UEMURA ,  Suguru YASUTOMI ,  Tomohiro Hayase ,  YUHEI UMEDA

IPC: G06K9/62 ,  G06N20/00

Abstract: A deterioration suppression device generates a plurality of trained machine learning models having different characteristics on the basis of each training data included in a first training data set and assigned with a label indicating correct answer information. In a case where estimation accuracy of label estimation with respect to input data to be estimated by any trained machine learning model among the plurality of trained machine learning models becomes lower than a predetermined standard, the deterioration suppression device generates a second training data set including a plurality of pieces of training data using an estimation result by a trained machine learning model with the estimation accuracy equal to or higher than the predetermined standard. The deterioration suppression device executes re-learning of the trained machine learning model with the estimation accuracy lower than the predetermined standard using the second training data set.

公开(公告)号：US20200160119A1

公开(公告)日：2020-05-21

申请号：US16680562

申请日：2019-11-12

Applicant: FUJITSU LIMITED

Inventor： Hiroya INAKOSHI ,  TAKASHI KATOH ,  Kento UEMURA ,  Suguru YASUTOMI

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: An apparatus receives, at a discriminator within a generative adversarial network, first generation data from a first generator within the generative adversarial network, where the first generator has performed learning using a first data group. The apparatus receives, at the discriminator, a second data group, and performs learning of a second generator based on the first generation data and the second data group where the first generation data is handled as false data by the discriminator.

公开(公告)号：US20190286939A1

公开(公告)日：2019-09-19

申请号：US16287685

申请日：2019-02-27

Applicant: FUJITSU LIMITED

Inventor： Toshio ENDOH ,  Kento UEMURA

IPC: G06K9/62 ,  G06K9/46

Abstract: A learning apparatus causes a first supervised learning model, which receives feature data generated from input data having data items with which a first label and a second label are associated and outputs a first estimation result, to learn such that the first estimation result is close to the first label. The learning apparatus causes a second supervised learning model, which receives the feature data and outputs a second estimation result, to learn such that the second estimation result is close to the second label. The learning apparatus causes a feature extractor, which generates the feature data from the input data, to learn so as to facilitate recognition of the first label and suppress recognition of the second label.

公开(公告)号：US20240394733A1

公开(公告)日：2024-11-28

申请号：US18791619

申请日：2024-08-01

Applicant: Fujitsu Limited

Inventor： Yuta FUJISHIGE ,  Tatsuya ASAI ,  Kento UEMURA ,  Hirofumi SUZUKI ,  Yusuke KOYANAGI ,  Koji MARUHASHI

IPC: G06Q30/0201

Abstract: A recording medium stores a program for causing a computer to execute a process including: referring to a memory storing data constituted by combinations of features to extract data groups of which the combinations satisfy each condition; identifying relationships between the features included in the data groups; classifying the relationships into a first clusters, based on first similarity; classifying the data groups into second clusters, based on second similarity; classifying the data groups into third clusters so as to classify, into a same cluster, data groups that are in a same one first cluster obtained by classifying the relationships corresponding correspond to each data group and are in a same one second cluster obtained by classifying each data group; identifying first conditions for classifying the data groups classified into each cluster and the data groups classified into other clusters; and outputting the identified first conditions with a classification result.