Patents by Inventor Suguru YASUTOMI

Suguru YASUTOMI 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: 11409988
    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.
    Type: Grant
    Filed: January 8, 2020
    Date of Patent: August 9, 2022
    Assignee: FUJITSU LIMITED
    Inventors: Takashi Katoh, Kento Uemura, Suguru Yasutomi
  • Publication number: 20220245405
    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.
    Type: Application
    Filed: April 25, 2022
    Publication date: August 4, 2022
    Applicant: FUJITSU LIMITED
    Inventors: TAKASHI KATOH, Kento UEMURA, Suguru YASUTOMI, Tomohiro Hayase, YUHEI UMEDA
  • 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
  • Publication number: 20220147764
    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.
    Type: Application
    Filed: September 13, 2021
    Publication date: May 12, 2022
    Applicant: FUJITSU LIMITED
    Inventors: Takashi KATOH, Kento UEMURA, Suguru YASUTOMI, Tomohiro HAYASE
  • Publication number: 20220101124
    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 a first machine learning model trained by using a training data set including first data and a second machine learning model not trained with the specific data; and retraining the first machine learning model so that an output of the first machine learning model and an output of the second machine learning model when second data corresponding to the first data is input get close to each other.
    Type: Application
    Filed: July 7, 2021
    Publication date: March 31, 2022
    Applicant: FUJITSU LIMITED
    Inventors: Suguru YASUTOMI, Tomohiro HAYASE, Takashi KATOH
  • Publication number: 20220076162
    Abstract: A non-transitory computer-readable storage medium storing a data presentation program that causes at least one computer to execute a process, the process includes acquiring certain data from an estimation target data set that uses an estimation model, based on an estimation result for the estimation target data set; and presenting data obtained by changing the certain data in a direction orthogonal to a direction in which loss of the estimation model fluctuates, in a feature space that relates to feature amounts obtained from the estimation target data set.
    Type: Application
    Filed: July 21, 2021
    Publication date: March 10, 2022
    Applicant: FUJITSU LIMITED
    Inventors: TAKASHI KATOH, Kento UEMURA, Suguru YASUTOMI, Tomohiro Hayase
  • Patent number: 11263479
    Abstract: An anomaly detection apparatus generates pieces of image data using a generator and train the generator and a discriminator that discriminates whether an image data, generated by the generator, is real or fake. The anomaly detection apparatus trains the generator such that the generator, in generating the pieces of image data to maximize the discrimination error of the discriminator, generate at least a piece of specified image data to reduce the discrimination error at a fixed rate with respect to the pieces of image data and trains, based on the pieces of image data and the at least a piece of specified image data, the discriminator to minimize the discrimination error.
    Type: Grant
    Filed: January 28, 2020
    Date of Patent: March 1, 2022
    Assignee: FUJITSU LIMITED
    Inventors: Takashi Katoh, Kazuki Iwamoto, Kento Uemura, Suguru Yasutomi
  • Patent number: 11250297
    Abstract: An anomaly detection apparatus performs training for the generator and the discriminator such that the generator maximizes a discrimination error of the discriminator and the discriminator minimizes the discrimination error The anomaly detection apparatus stores, while the training is being performed, a state of the generator that is half-trained and satisfies a pre-set condition, and retrains the discriminator by using an image generated by the half-trained generator that has the stored state.
    Type: Grant
    Filed: January 28, 2020
    Date of Patent: February 15, 2022
    Assignee: FUJITSU LIMITED
    Inventors: Takashi Katoh, Kazuki Iwamoto, Kento Uemura, Suguru Yasutomi
  • Patent number: 11145062
    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.
    Type: Grant
    Filed: March 6, 2020
    Date of Patent: October 12, 2021
    Assignee: FUJITSU LIMITED
    Inventors: Kento Uemura, Suguru Yasutomi, Takashi Katoh
  • Patent number: 11100678
    Abstract: A non-transitory computer-readable recording medium stores therein a learning program that causes a computer to execute a process including: inputting an output from an encoder to which an input image is input to a first decoder and a second decoder; and executing learning of the encoder, the first decoder and the second decoder, based on a reconstruction error between the input image and an output image obtained by using a combining function for synthesizing a first image that is an output from the first decoder and a second image that is an output from the second decoder, based on a first likelihood function for the first image relating to shades in ultrasound images, and based on a second likelihood function for the second image relating to subjects in ultrasound images.
    Type: Grant
    Filed: December 19, 2019
    Date of Patent: August 24, 2021
    Assignee: FUJITSU LIMITED
    Inventor: Suguru Yasutomi
  • Publication number: 20210232854
    Abstract: A non-transitory computer-readable recording medium recording a learning program for causing a computer to execute processing includes: generating restored data using a plurality of restorers respectively corresponding to a plurality of features from the plurality of features generated by a machine learning model corresponding to each piece of input data, for each piece of the input data input to the machine learning model; and making the plurality of restorers perform learning so that each of the plurality of pieces of restored data respectively generated by the plurality of restorers approaches the input data.
    Type: Application
    Filed: April 12, 2021
    Publication date: July 29, 2021
    Applicant: FUJITSU LIMITED
    Inventors: Kento UEMURA, Suguru YASUTOMI, TAKASHI KATOH
  • Publication number: 20210012193
    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.
    Type: Application
    Filed: July 7, 2020
    Publication date: January 14, 2021
    Applicant: FUJITSU LIMITED
    Inventors: Suguru YASUTOMI, TAKASHI KATOH, 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: 20200302611
    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.
    Type: Application
    Filed: March 6, 2020
    Publication date: September 24, 2020
    Applicant: FUJITSU LIMITED
    Inventors: Kento UEMURA, Suguru YASUTOMI, TAKASHI KATOH
  • Publication number: 20200250544
    Abstract: A learning method executed by a computer, the learning method includes inputting a first data being a data set of transfer source and a second data being one of data sets of transfer destination to an encoder to generate first distributions of feature values of the first data and second distributions of feature values of the second data; selecting one or more feature values from among the feature values so that, for each of the one or more feature values, a first distribution of the feature value of the first data is similar to a second distribution of the feature value of the second data; inputting the one or more feature values to a classifier to calculate prediction labels of the first data; and learning parameters of the encoder and the classifier such that the prediction labels approach correct answer labels of the first data.
    Type: Application
    Filed: February 4, 2020
    Publication date: August 6, 2020
    Applicant: FUJITSU LIMITED
    Inventors: TAKASHI KATOH, Kento UEMURA, Suguru YASUTOMI, Takuya Takagi, KEN KOBAYASHI, Akira URA, Kenichi KOBAYASHI
  • Publication number: 20200242399
    Abstract: An anomaly detection apparatus generates pieces of image data using a generator and train the generator and a discriminator that discriminates whether an image data, generated by the generator, is real or fake. The anomaly detection apparatus trains the generator such that the generator, in generating the pieces of image data to maximize the discrimination error of the discriminator, generate at least a piece of specified image data to reduce the discrimination error at a fixed rate with respect to the pieces of image data and trains, based on the pieces of image data and the at least a piece of specified image data, the discriminator to minimize the discrimination error.
    Type: Application
    Filed: January 28, 2020
    Publication date: July 30, 2020
    Applicant: FUJITSU LIMITED
    Inventors: TAKASHI KATOH, Kazuki IWAMOTO, Kento UEMURA, Suguru YASUTOMI
  • Publication number: 20200242412
    Abstract: An anomaly detection apparatus performs training for the generator and the discriminator such that the generator maximizes a discrimination error of the discriminator and the discriminator minimizes the discrimination error The anomaly detection apparatus stores, while the training is being performed, a state of the generator that is half-trained and satisfies a pre-set condition, and retrains the discriminator by using an image generated by the half-trained generator that has the stored state.
    Type: Application
    Filed: January 28, 2020
    Publication date: July 30, 2020
    Applicant: FUJITSU LIMITED
    Inventors: TAKASHI KATOH, Kazuki IWAMOTO, Kento UEMURA, Suguru YASUTOMI
  • Publication number: 20200234122
    Abstract: A learning device generates a first feature value and a second feature value by inputting original training data to a first neural network included in a learning model. The learning device learns at least one parameter of the learning model and a parameter of a decoder, reconstructing data inputted to the first neural network, such that reconstruction data outputted from the decoder by inputting the first feature value and the second feature value to the decoder becomes close to the original training data, and that outputted data that is outputted from a second neural network, included in the learning model by inputting the second feature value to the second neural network becomes close to correct data of the original training data.
    Type: Application
    Filed: January 14, 2020
    Publication date: July 23, 2020
    Applicant: FUJITSU LIMITED
    Inventors: TAKASHI KATOH, Kento UEMURA, Suguru YASUTOMI
  • Publication number: 20200234081
    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.
    Type: Application
    Filed: January 8, 2020
    Publication date: July 23, 2020
    Applicant: FUJITSU LIMITED
    Inventors: TAKASHI KATOH, Kento UEMURA, Suguru YASUTOMI
  • Publication number: 20200234140
    Abstract: A learning method executed by a computer, the learning method includes: learning parameters of a machine learning model having intermediate feature values by inputting a plurality of augmented training data, which is generated by augmenting original training data, to the machine learning model so that specific intermediate feature values, which are calculated from specific augmented training data augmented from a same original training data, become similar to each other.
    Type: Application
    Filed: January 14, 2020
    Publication date: July 23, 2020
    Applicant: FUJITSU LIMITED
    Inventors: TAKASHI KATOH, Kento UEMURA, Suguru YASUTOMI, Takeshi OSOEKAWA