Patents by Inventor Toshio Endoh

Toshio Endoh 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).

  • Patent number: 11488023
    Abstract: An adaptability calculation device inputs input data to a learning model and an encoder of an autoencoder that have performed learning with learning data, inputs an output from the learning model and an output from the encoder of the autoencoder to a decoder of the autoencoder, and calculates adaptability of the output from the learning model to the input data based on an output from the decoder and the input data.
    Type: Grant
    Filed: March 20, 2019
    Date of Patent: November 1, 2022
    Assignee: FUJITSU LIMITED
    Inventors: Toshio Endoh, Takashi Katoh
  • Patent number: 11462102
    Abstract: A non-transitory computer-readable storage medium storing a program that causes a computer to execute a process, the process comprising: calculating parameters of an expression that describes a model that is associated with a traffic system and estimates a traffic volume between a plurality of points, by using a plurality of measurement data measured in the traffic system that connects the plurality of points to each other, by using a method for solving an optimization problem; generating, when an indefinite solution is obtained by the calculating, indefiniteness information related to a range of the indefinite solution in the method for solving the optimization problem; and determining addition of the plurality of measurement data or output of the indefinite solution, depending on the indefiniteness information.
    Type: Grant
    Filed: March 24, 2020
    Date of Patent: October 4, 2022
    Assignee: FUJITSU LIMITED
    Inventors: Toshio Endoh, Kazuhiro Matsumoto
  • Patent number: 11455523
    Abstract: A risk evaluation method is disclosed. A machine learning is conducted by using a neural network by inputting training data. A data distance corresponding to a permission level is calculated based on restoration data and the training data, the permission level being among a plurality of layers of the neural network, the restoration data being generated by using at least one weight of a plurality of permission level weights at the permission level, the plurality of permission level weights being among a plurality of weights of synapses at the plurality of layers, the plurality of weights being generated by the machine learning.
    Type: Grant
    Filed: May 23, 2018
    Date of Patent: September 27, 2022
    Assignee: FUJITSU LIMITED
    Inventor: Toshio Endoh
  • Patent number: 11367003
    Abstract: A non-transitory computer-readable storage medium storing a program that causes a computer to execute a process, the process including obtaining a feature quantity of input data by using a feature generator, generating a first output based on the feature quantity by using a supervised learner for labeled data, generating a second output based on the feature quantity by using an unsupervised learning processing for unlabeled data, and changing a contribution ratio between a first error and a second error in a learning by the feature generator, the first error being generated from the labeled data and the first output, the second error being generated from the unlabeled data and the second output.
    Type: Grant
    Filed: April 6, 2018
    Date of Patent: June 21, 2022
    Assignee: Fujitsu Limited
    Inventors: Takashi Katoh, Kento Uemura, Suguru Yasutomi, Toshio Endoh
  • Patent number: 11210513
    Abstract: A computer-implemented detection method includes, in response to inputting a first image including a region of one or more objects to a learned model, identifying a first entire image corresponding to entirety of a first object as a detection candidate, the learned model being generated by learning training data including an image corresponding to a part of an object and an entire image corresponding to entirety of the object, detecting an existing region of the first target object in the first image in accordance with a comparison between the identified first entire image and the region of the one or more target objects, and determining, based on a specific image obtained by invalidating the existing region in the first image, whether another target object is included in the first image.
    Type: Grant
    Filed: October 22, 2019
    Date of Patent: December 28, 2021
    Assignee: FUJITSU LIMITED
    Inventors: Toshio Endoh, Keizo Kato
  • Patent number: 11049014
    Abstract: A feature model, which calculates a feature value of an input image, is trained on a plurality of first images. First feature values corresponding one-to-one with the first images are calculated using the feature model, and feature distribution information representing a relationship between a plurality of classes and the first feature values is generated. When a detection model which determines, in an input image, each region with an object and a class to which the object belongs is trained on a plurality of second images, second feature values corresponding to regions determined within the second images by the detection model are calculated using the feature model, an evaluation value, which indicates class determination accuracy of the detection model, is modified using the feature distribution information and the second feature values, and the detection model is updated based on the modified evaluation value.
    Type: Grant
    Filed: October 9, 2019
    Date of Patent: June 29, 2021
    Assignee: FUJITSU LIMITED
    Inventors: Kanata Suzuki, Toshio Endoh
  • Patent number: 10891516
    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.
    Type: Grant
    Filed: February 27, 2019
    Date of Patent: January 12, 2021
    Assignee: FUJITSU LIMITED
    Inventors: Toshio Endoh, Kento Uemura
  • Patent number: 10803357
    Abstract: An object detection device extracts feature for input data utilizing an encoder, the input data including labeled data and unlabeled data and detects object in each of the input data, utilizing an object detector. The object detection device generates region data for each of the input data, each of the region data corresponding to the detected object and generates restoration data from the region data and meta-information related to the detected object for each of the input data utilizing a decoder corresponding to the encoder. The object detection device executes learning of the encoder and the object detector based on a result detected by the object detector and a label associated with the input data, when the input data is labeled data. The object detection device executes learning of the encoder, the object detector, and the decoder, based on the input data and the restoration data.
    Type: Grant
    Filed: May 30, 2018
    Date of Patent: October 13, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Suguru Yasutomi, Toshio Endoh, Takashi Katoh, Kento Uemura
  • Publication number: 20200226923
    Abstract: A non-transitory computer-readable storage medium storing a program that causes a computer to execute a process, the process comprising: calculating parameters of an expression that describes a model that is associated with a traffic system and estimates a traffic volume between a plurality of points, by using a plurality of measurement data measured in the traffic system that connects the plurality of points to each other, by using a method for solving an optimization problem; generating, when an indefinite solution is obtained by the calculating, indefiniteness information related to a range of the indefinite solution in the method for solving the optimization problem; and determining addition of the plurality of measurement data or output of the indefinite solution, depending on the indefiniteness information.
    Type: Application
    Filed: March 24, 2020
    Publication date: July 16, 2020
    Applicant: FUJITSU LIMITED
    Inventors: Toshio Endoh, Kazuhiro Matsumoto
  • Publication number: 20200134313
    Abstract: A computer-implemented detection method includes, in response to inputting a first image including a region of one or more objects to a learned model, identifying a first entire image corresponding to entirety of a first object as a detection candidate, the learned model being generated by learning training data including an image corresponding to a part of an object and an entire image corresponding to entirety of the object, detecting an existing region of the first target object in the first image in accordance with a comparison between the identified first entire image and the region of the one or more target objects, and determining, based on a specific image obtained by invalidating the existing region in the first image, whether another target object is included in the first image.
    Type: Application
    Filed: October 22, 2019
    Publication date: April 30, 2020
    Applicant: FUJITSU LIMITED
    Inventors: Toshio Endoh, Keizo Kato
  • Publication number: 20200117991
    Abstract: A feature model, which calculates a feature value of an input image, is trained on a plurality of first images. First feature values corresponding one-to-one with the first images are calculated using the feature model, and feature distribution information representing a relationship between a plurality of classes and the first feature values is generated. When a detection model which determines, in an input image, each region with an object and a class to which the object belongs is trained on a plurality of second images, second feature values corresponding to regions determined within the second images by the detection model are calculated using the feature model, an evaluation value, which indicates class determination accuracy of the detection model, is modified using the feature distribution information and the second feature values, and the detection model is updated based on the modified evaluation value.
    Type: Application
    Filed: October 9, 2019
    Publication date: April 16, 2020
    Applicant: FUJITSU LIMITED
    Inventors: Kanata Suzuki, Toshio Endoh
  • Publication number: 20200042876
    Abstract: A non-transitory computer-readable recording medium records an estimation program causing a computer to execute processing which includes: calculating a reconfiguration error from an input result value and a reconfiguration value that is estimated by a first estimator, which estimates a parameter value from a result value learned on a basis of past data, and a second estimator, which estimates a result value from a parameter value, by using a specific result value or a neighborhood result value in a neighborhood of the specific result value; searching for a first result value that minimizes a sum of a substitute error that is calculated from the input result value and the specific result value and the reconfiguration error; and outputting a parameter value that is estimated from the first result value by using the first estimator.
    Type: Application
    Filed: October 15, 2019
    Publication date: February 6, 2020
    Applicant: FUJITSU LIMITED
    Inventors: TAKASHI KATOH, Kento UEMURA, Suguru YASUTOMI, Toshio Endoh, Koji MARUHASHI
  • Publication number: 20190303766
    Abstract: An adaptability calculation device inputs input data to a learning model and an encoder of an autoencoder that have performed learning with learning data, inputs an output from the learning model and an output from the encoder of the autoencoder to a decoder of the autoencoder, and calculates adaptability of the output from the learning model to the input data based on an output from the decoder and the input data.
    Type: Application
    Filed: March 20, 2019
    Publication date: October 3, 2019
    Applicant: FUJITSU LIMITED
    Inventors: Toshio ENDOH, Takashi KATOH
  • Publication number: 20190286946
    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.
    Type: Application
    Filed: February 13, 2019
    Publication date: September 19, 2019
    Applicant: FUJITSU LIMITED
    Inventors: Kento UEMURA, TAKASHI KATOH, Suguru YASUTOMI, Toshio Endoh
  • Publication number: 20190287016
    Abstract: A learning device has a characteristic generator to generate data of characteristic quantities by inputting test data, and training data to which labels are respectively given to a first learner; input the data of the characteristic quantities generated by the first learner to a second learner to output a result of estimation; and input the data of the characteristic quantities generated by the first learner to a third learner to output a result of classification of the training data and the test data. The second learner learns using the labels respectively given to the training data so that accuracy of the result of estimation with respect to the training data becomes higher. The third learner learns so that the training data and the test data are classified. The first learner learns so that accuracy of the result of estimation becomes higher and accuracy of the result of classification becomes lower.
    Type: Application
    Filed: March 7, 2019
    Publication date: September 19, 2019
    Applicant: FUJITSU LIMITED
    Inventors: TAKASHI KATOH, Kento Uemura, Toshio Endoh, Suguru Yasutomi
  • Publication number: 20190286939
    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.
    Type: Application
    Filed: February 27, 2019
    Publication date: September 19, 2019
    Applicant: FUJITSU LIMITED
    Inventors: Toshio ENDOH, Kento UEMURA
  • Publication number: 20180349741
    Abstract: An object detection device extracts feature for input data utilizing an encoder, the input data including labeled data and unlabeled data and detects object in each of the input data, utilizing an object detector. The object detection device generates region data for each of the input data, each of the region data corresponding to the detected object and generates restoration data from the region data and meta-information related to the detected object for each of the input data utilizing a decoder corresponding to the encoder. The object detection device executes learning of the encoder and the object detector based on a result detected by the object detector and a label associated with the input data, when the input data is labeled data. The object detection device executes learning of the encoder, the object detector, and the decoder, based on the input data and the restoration data.
    Type: Application
    Filed: May 30, 2018
    Publication date: December 6, 2018
    Applicant: FUJITSU LIMITED
    Inventors: Suguru YASUTOMI, Toshio Endoh, Takashi Katoh, Kento Uemura
  • Publication number: 20180300632
    Abstract: A non-transitory computer-readable storage medium storing a program that causes a computer to execute a process, the process including obtaining a feature quantity of input data by using a feature generator, generating a first output based on the feature quantity by using a supervised learner for labeled data, generating a second output based on the feature quantity by using an unsupervised learning processing for unlabeled data, and changing a contribution ratio between a first error and a second error in a learning by the feature generator, the first error being generated from the labeled data and the first output, the second error being generated from the unlabeled data and the second output.
    Type: Application
    Filed: April 6, 2018
    Publication date: October 18, 2018
    Applicant: FUJITSU LIMITED
    Inventors: TAKASHI KATOH, Kento UEMURA, Suguru YASUTOMI, Toshio Endoh
  • Publication number: 20180268295
    Abstract: A risk evaluation method is disclosed. A machine learning is conducted by using a neural network by inputting training data. A data distance corresponding to a permission level is calculated based on restoration data and the training data, the permission level being among a plurality of layers of the neural network, the restoration data being generated by using at least one weight of a plurality of permission level weights at the permission level, the plurality of permission level weights being among a plurality of weights of synapses at the plurality of layers, the plurality of weights being generated by the machine learning.
    Type: Application
    Filed: May 23, 2018
    Publication date: September 20, 2018
    Applicant: FUJITSU LIMITED
    Inventor: Toshio Endoh
  • Patent number: 9418275
    Abstract: A biometric information processing apparatus includes a processor; and a memory, wherein the processor is configured to extract auxiliary information representing a part of a body being captured together with biometric information from a plurality of images captured by an imaging unit; to trace the auxiliary information in a time direction; to extract the biometric information from at least one image among the plurality of images; to associate the traced auxiliary information with the extracted biometric information in terms of a positional relationship; and to output the auxiliary information having been associated with the biometric information.
    Type: Grant
    Filed: November 11, 2014
    Date of Patent: August 16, 2016
    Assignee: FUJITSU LIMITED
    Inventors: Toshio Endoh, Takashi Shinzaki